Austin/firecrawl
1
0
Fork 0
mirror of https://github.com/mendableai/firecrawl.git synced 2024-11-16 11:42:24 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

Merge branch 'main' into nsc/usage-based-overuse

Browse Source
This commit is contained in:
Nicolas 2024-11-04 15:00:04 -05:00
commit 5d55ef3f4d
391 changed files with 62096 additions and 20943 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
.github/ISSUE_TEMPLATE/bug_report.md vendored
View File

@ -1,7 +1,7 @@
---
name: Bug report
about: Create a report to help us improve
title: "[BUG]"
title: "[Bug] "
labels: bug
assignees: ''

2
.github/ISSUE_TEMPLATE/feature_request.md vendored
View File

@ -1,7 +1,7 @@
---
name: Feature request
about: Suggest an idea for this project
title: "[Feat]"
title: "[Feat] "
labels: ''
assignees: ''

40
.github/ISSUE_TEMPLATE/self_host_issue.md vendored Normal file
View File

@ -0,0 +1,40 @@
---
name: Self-host issue
about: Report an issue with self-hosting Firecrawl
title: "[Self-Host] "
labels: self-host
assignees: ''
---
**Describe the Issue**
Provide a clear and concise description of the self-hosting issue you're experiencing.
**To Reproduce**
Steps to reproduce the issue:
1. Configure the environment or settings with '...'
2. Run the command '...'
3. Observe the error or unexpected output at '...'
4. Log output/error message
**Expected Behavior**
A clear and concise description of what you expected to happen when self-hosting.
**Screenshots**
If applicable, add screenshots or copies of the command line output to help explain the self-hosting issue.
**Environment (please complete the following information):**
- OS: [e.g. macOS, Linux, Windows]
- Firecrawl Version: [e.g. 1.2.3]
- Node.js Version: [e.g. 14.x]
- Docker Version (if applicable): [e.g. 20.10.14]
- Database Type and Version: [e.g. PostgreSQL 13.4]
**Logs**
If applicable, include detailed logs to help understand the self-hosting problem.
**Configuration**
Provide relevant parts of your configuration files (with sensitive information redacted).
**Additional Context**
Add any other context about the self-hosting issue here, such as specific infrastructure details, network setup, or any modifications made to the original Firecrawl setup.

42
.github/archive/publish-rust-sdk.yml vendored Normal file
View File

@ -0,0 +1,42 @@
name: Publish Rust SDK
on: []
env:
CRATES_IO_TOKEN: ${{ secrets.CRATES_IO_TOKEN }}
jobs:
build-and-publish:
runs-on: ubuntu-latest
steps:
- name: Checkout repository
uses: actions/checkout@v3
- name: Set up Rust
uses: actions-rs/toolchain@v1
with:
toolchain: stable
default: true
profile: minimal
- name: Install dependencies
run: cargo build --release
- name: Run version check script
id: version_check_script
run: |
VERSION_INCREMENTED=$(cargo search --limit 1 my_crate_name | grep my_crate_name)
echo "VERSION_INCREMENTED=$VERSION_INCREMENTED" >> $GITHUB_ENV
- name: Build the package
if: ${{ env.VERSION_INCREMENTED == 'true' }}
run: cargo package
working-directory: ./apps/rust-sdk
- name: Publish to crates.io
if: ${{ env.VERSION_INCREMENTED == 'true' }}
env:
CARGO_REG_TOKEN: ${{ secrets.CRATES_IO_TOKEN }}
run: cargo publish
working-directory: ./apps/rust-sdk

61
.github/archive/rust-sdk.yml vendored Normal file
View File

@ -0,0 +1,61 @@
name: Run Rust SDK E2E Tests
on: []
env:
ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
BULL_AUTH_KEY: ${{ secrets.BULL_AUTH_KEY }}
FLY_API_TOKEN: ${{ secrets.FLY_API_TOKEN }}
HOST: ${{ secrets.HOST }}
LLAMAPARSE_API_KEY: ${{ secrets.LLAMAPARSE_API_KEY }}
LOGTAIL_KEY: ${{ secrets.LOGTAIL_KEY }}
POSTHOG_API_KEY: ${{ secrets.POSTHOG_API_KEY }}
POSTHOG_HOST: ${{ secrets.POSTHOG_HOST }}
NUM_WORKERS_PER_QUEUE: ${{ secrets.NUM_WORKERS_PER_QUEUE }}
OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
PLAYWRIGHT_MICROSERVICE_URL: ${{ secrets.PLAYWRIGHT_MICROSERVICE_URL }}
PORT: ${{ secrets.PORT }}
REDIS_URL: ${{ secrets.REDIS_URL }}
SCRAPING_BEE_API_KEY: ${{ secrets.SCRAPING_BEE_API_KEY }}
SUPABASE_ANON_TOKEN: ${{ secrets.SUPABASE_ANON_TOKEN }}
SUPABASE_SERVICE_TOKEN: ${{ secrets.SUPABASE_SERVICE_TOKEN }}
SUPABASE_URL: ${{ secrets.SUPABASE_URL }}
TEST_API_KEY: ${{ secrets.TEST_API_KEY }}
HYPERDX_API_KEY: ${{ secrets.HYPERDX_API_KEY }}
HDX_NODE_BETA_MODE: 1
jobs:
build:
runs-on: ubuntu-latest
services:
redis:
image: redis
ports:
- 6379:6379
steps:
- name: Checkout repository
uses: actions/checkout@v3
- name: Install pnpm
run: npm install -g pnpm
- name: Install dependencies for API
run: pnpm install
working-directory: ./apps/api
- name: Start the application
run: npm start &
working-directory: ./apps/api
id: start_app
- name: Start workers
run: npm run workers &
working-directory: ./apps/api
id: start_workers
- name: Set up Rust
uses: actions/setup-rust@v1
with:
rust-version: stable
- name: Try the lib build
working-directory: ./apps/rust-sdk
run: cargo build
- name: Run E2E tests for Rust SDK
run: cargo test --test e2e_with_auth

45
.github/dependabot.yml vendored Normal file
View File

@ -0,0 +1,45 @@
version: 2
updates:
# playwright-service
- package-ecosystem: "pip"
directory: "/apps/playwright-service"
schedule:
interval: "weekly"
open-pull-requests-limit: 0 # Disable version updates
security-updates: "all"
commit-message:
prefix: "apps/playwright-service"
include: "scope"
# python-sdk
- package-ecosystem: "pip"
directory: "/apps/python-sdk"
schedule:
interval: "weekly"
open-pull-requests-limit: 0 # Disable version updates
security-updates: "all"
commit-message:
prefix: "apps/python-sdk"
include: "scope"
# api
- package-ecosystem: "npm"
directory: "/apps/api"
schedule:
interval: "weekly"
open-pull-requests-limit: 0 # Disable version updates
security-updates: "all"
commit-message:
prefix: "apps/api"
include: "scope"
# test-suite
- package-ecosystem: "npm"
directory: "/apps/test-suite"
schedule:
interval: "weekly"
open-pull-requests-limit: 0 # Disable version updates
security-updates: "all"
commit-message:
prefix: "apps/test-suite"
include: "scope"

20
.github/scripts/check_version_has_incremented.py vendored
View File

@ -15,6 +15,7 @@ false
"""
import json
import toml
import os
import re
import sys
@ -53,6 +54,19 @@ def get_npm_version(package_name: str) -> str:
version = response.json()['version']
return version.strip()
def get_rust_version(file_path: str) -> str:
"""Extract version string from Cargo.toml."""
cargo_toml = toml.load(file_path)
if 'package' in cargo_toml and 'version' in cargo_toml['package']:
return cargo_toml['package']['version'].strip()
raise RuntimeError("Unable to find version string in Cargo.toml.")
def get_crates_version(package_name: str) -> str:
"""Get latest version of Rust package from crates.io."""
response = requests.get(f"https://crates.io/api/v1/crates/{package_name}")
version = response.json()['crate']['newest_version']
return version.strip()
def is_version_incremented(local_version: str, published_version: str) -> bool:
"""Compare local and published versions."""
local_version_parsed: Version = parse_version(local_version)
@ -74,6 +88,12 @@ if __name__ == "__main__":
current_version = get_js_version(os.path.join(package_path, 'package.json'))
# Get published version from npm
published_version = get_npm_version(package_name)
if package_type == "rust":
# Get current version from Cargo.toml
current_version = get_rust_version(os.path.join(package_path, 'Cargo.toml'))
# Get published version from crates.io
published_version = get_crates_version(package_name)
else:
raise ValueError("Invalid package type. Use 'python' or 'js'.")

1
.github/scripts/requirements.txt vendored
View File

@ -1,2 +1,3 @@
requests
packaging
toml

4
.github/workflows/ci.yml vendored
View File

@ -27,7 +27,9 @@ env:
TEST_API_KEY: ${{ secrets.TEST_API_KEY }}
HYPERDX_API_KEY: ${{ secrets.HYPERDX_API_KEY }}
HDX_NODE_BETA_MODE: 1
FIRE_ENGINE_BETA_URL: ${{ secrets.FIRE_ENGINE_BETA_URL }}
USE_DB_AUTHENTICATION: ${{ secrets.USE_DB_AUTHENTICATION }}
ENV: ${{ secrets.ENV }}
jobs:
pre-deploy:

6
.github/workflows/clean-before-24h-complete-jobs.yml vendored
View File

@ -1,7 +1,7 @@
name: Clean Before 24h Completed Jobs
name: Clean Every 30 Minutes Before 24h Completed Jobs
on:
schedule:
- cron: '0 0 * * *'
- cron: '30 * * * *'
env:
BULL_AUTH_KEY: ${{ secrets.BULL_AUTH_KEY }}
@ -12,7 +12,7 @@ jobs:
steps:
- name: Send GET request to clean jobs
run: |
response=$(curl --write-out '%{http_code}' --silent --output /dev/null https://api.firecrawl.dev/admin/${{ secrets.BULL_AUTH_KEY }}/clean-before-24h-complete-jobs)
response=$(curl --write-out '%{http_code}' --silent --output /dev/null --max-time 180 https://api.firecrawl.dev/admin/${{ secrets.BULL_AUTH_KEY }}/clean-before-24h-complete-jobs)
if [ "$response" -ne 200 ]; then
echo "Failed to clean jobs. Response: $response"
exit 1

32
.github/workflows/deploy-image.yml vendored Normal file
View File

@ -0,0 +1,32 @@
name: Deploy Images to GHCR
env:
DOTNET_VERSION: '6.0.x'
on:
push:
branches:
- main
workflow_dispatch:
jobs:
push-app-image:
runs-on: ubuntu-latest
defaults:
run:
working-directory: './apps/api'
steps:
- name: 'Checkout GitHub Action'
uses: actions/checkout@main
- name: 'Login to GitHub Container Registry'
uses: docker/login-action@v1
with:
registry: ghcr.io
username: ${{github.actor}}
password: ${{secrets.GITHUB_TOKEN}}
- name: 'Build Inventory Image'
run: |
docker build . --tag ghcr.io/mendableai/firecrawl:latest
docker push ghcr.io/mendableai/firecrawl:latest

37
.github/workflows/fly-direct.yml vendored
View File

@ -1,37 +0,0 @@
name: Fly Deploy Direct
on:
schedule:
- cron: '0 * * * *'
env:
ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
BULL_AUTH_KEY: ${{ secrets.BULL_AUTH_KEY }}
FLY_API_TOKEN: ${{ secrets.FLY_API_TOKEN }}
HOST: ${{ secrets.HOST }}
LLAMAPARSE_API_KEY: ${{ secrets.LLAMAPARSE_API_KEY }}
LOGTAIL_KEY: ${{ secrets.LOGTAIL_KEY }}
POSTHOG_API_KEY: ${{ secrets.POSTHOG_API_KEY }}
POSTHOG_HOST: ${{ secrets.POSTHOG_HOST }}
NUM_WORKERS_PER_QUEUE: ${{ secrets.NUM_WORKERS_PER_QUEUE }}
OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
PLAYWRIGHT_MICROSERVICE_URL: ${{ secrets.PLAYWRIGHT_MICROSERVICE_URL }}
PORT: ${{ secrets.PORT }}
REDIS_URL: ${{ secrets.REDIS_URL }}
SCRAPING_BEE_API_KEY: ${{ secrets.SCRAPING_BEE_API_KEY }}
SUPABASE_ANON_TOKEN: ${{ secrets.SUPABASE_ANON_TOKEN }}
SUPABASE_SERVICE_TOKEN: ${{ secrets.SUPABASE_SERVICE_TOKEN }}
SUPABASE_URL: ${{ secrets.SUPABASE_URL }}
TEST_API_KEY: ${{ secrets.TEST_API_KEY }}
jobs:
deploy:
name: Deploy app
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v3
- name: Change directory
run: cd apps/api
- uses: superfly/flyctl-actions/setup-flyctl@master
- run: flyctl deploy ./apps/api --remote-only -a firecrawl-scraper-js
env:
FLY_API_TOKEN: ${{ secrets.FLY_API_TOKEN }}

265
.github/workflows/fly.yml vendored
View File

@ -1,265 +0,0 @@
name: Fly Deploy
on:
push:
branches:
- main
env:
ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
BULL_AUTH_KEY: ${{ secrets.BULL_AUTH_KEY }}
FLY_API_TOKEN: ${{ secrets.FLY_API_TOKEN }}
HOST: ${{ secrets.HOST }}
LLAMAPARSE_API_KEY: ${{ secrets.LLAMAPARSE_API_KEY }}
LOGTAIL_KEY: ${{ secrets.LOGTAIL_KEY }}
POSTHOG_API_KEY: ${{ secrets.POSTHOG_API_KEY }}
POSTHOG_HOST: ${{ secrets.POSTHOG_HOST }}
NUM_WORKERS_PER_QUEUE: ${{ secrets.NUM_WORKERS_PER_QUEUE }}
OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
PLAYWRIGHT_MICROSERVICE_URL: ${{ secrets.PLAYWRIGHT_MICROSERVICE_URL }}
PORT: ${{ secrets.PORT }}
REDIS_URL: ${{ secrets.REDIS_URL }}
SCRAPING_BEE_API_KEY: ${{ secrets.SCRAPING_BEE_API_KEY }}
SUPABASE_ANON_TOKEN: ${{ secrets.SUPABASE_ANON_TOKEN }}
SUPABASE_SERVICE_TOKEN: ${{ secrets.SUPABASE_SERVICE_TOKEN }}
SUPABASE_URL: ${{ secrets.SUPABASE_URL }}
TEST_API_KEY: ${{ secrets.TEST_API_KEY }}
PYPI_USERNAME: ${{ secrets.PYPI_USERNAME }}
PYPI_PASSWORD: ${{ secrets.PYPI_PASSWORD }}
NPM_TOKEN: ${{ secrets.NPM_TOKEN }}
jobs:
pre-deploy-e2e-tests:
name: Pre-deploy checks
runs-on: ubuntu-latest
services:
redis:
image: redis
ports:
- 6379:6379
steps:
- uses: actions/checkout@v3
- name: Set up Node.js
uses: actions/setup-node@v3
with:
node-version: "20"
- name: Install pnpm
run: npm install -g pnpm
- name: Install dependencies
run: pnpm install
working-directory: ./apps/api
- name: Start the application
run: npm start &
working-directory: ./apps/api
id: start_app
- name: Start workers
run: npm run workers &
working-directory: ./apps/api
id: start_workers
- name: Run E2E tests
run: |
npm run test:prod
working-directory: ./apps/api
pre-deploy-test-suite:
name: Test Suite
needs: pre-deploy-e2e-tests
runs-on: ubuntu-latest
services:
redis:
image: redis
ports:
- 6379:6379
steps:
- uses: actions/checkout@v3
- name: Set up Node.js
uses: actions/setup-node@v3
with:
node-version: "20"
- name: Install pnpm
run: npm install -g pnpm
- name: Install dependencies
run: pnpm install
working-directory: ./apps/api
- name: Start the application
run: npm start &
working-directory: ./apps/api
id: start_app
- name: Start workers
run: npm run workers &
working-directory: ./apps/api
id: start_workers
- name: Install dependencies
run: pnpm install
working-directory: ./apps/test-suite
- name: Run E2E tests
run: |
npm run test
working-directory: ./apps/test-suite
python-sdk-tests:
name: Python SDK Tests
needs: pre-deploy-e2e-tests
runs-on: ubuntu-latest
services:
redis:
image: redis
ports:
- 6379:6379
steps:
- uses: actions/checkout@v3
- name: Set up Python
uses: actions/setup-python@v4
with:
python-version: '3.x'
- name: Install pnpm
run: npm install -g pnpm
- name: Install dependencies
run: pnpm install
working-directory: ./apps/api
- name: Start the application
run: npm start &
working-directory: ./apps/api
id: start_app
- name: Start workers
run: npm run workers &
working-directory: ./apps/api
id: start_workers
- name: Install Python dependencies
run: |
python -m pip install --upgrade pip
pip install -r requirements.txt
working-directory: ./apps/python-sdk
- name: Run E2E tests for Python SDK
run: |
pytest firecrawl/__tests__/e2e_withAuth/test.py
working-directory: ./apps/python-sdk
js-sdk-tests:
name: JavaScript SDK Tests
needs: pre-deploy-e2e-tests
runs-on: ubuntu-latest
services:
redis:
image: redis
ports:
- 6379:6379
steps:
- uses: actions/checkout@v3
- name: Set up Node.js
uses: actions/setup-node@v3
with:
node-version: "20"
- name: Install pnpm
run: npm install -g pnpm
- name: Install dependencies
run: pnpm install
working-directory: ./apps/api
- name: Start the application
run: npm start &
working-directory: ./apps/api
id: start_app
- name: Start workers
run: npm run workers &
working-directory: ./apps/api
id: start_workers
- name: Install dependencies for JavaScript SDK
run: pnpm install
working-directory: ./apps/js-sdk/firecrawl
- name: Run E2E tests for JavaScript SDK
run: npm run test
working-directory: ./apps/js-sdk/firecrawl
deploy:
name: Deploy app
runs-on: ubuntu-latest
needs: [pre-deploy-test-suite, python-sdk-tests, js-sdk-tests]
steps:
- uses: actions/checkout@v3
- name: Change directory
run: cd apps/api
- uses: superfly/flyctl-actions/setup-flyctl@master
- run: flyctl deploy ./apps/api --remote-only -a firecrawl-scraper-js
env:
FLY_API_TOKEN: ${{ secrets.FLY_API_TOKEN }}
build-and-publish-python-sdk:
name: Build and publish Python SDK
runs-on: ubuntu-latest
needs: deploy
steps:
- name: Checkout repository
uses: actions/checkout@v3
- name: Set up Python
uses: actions/setup-python@v4
with:
python-version: '3.x'
- name: Install dependencies
run: |
python -m pip install --upgrade pip
pip install setuptools wheel twine build requests packaging
- name: Run version check script
id: version_check_script
run: |
PYTHON_SDK_VERSION_INCREMENTED=$(python .github/scripts/check_version_has_incremented.py python ./apps/python-sdk/firecrawl firecrawl-py)
echo "PYTHON_SDK_VERSION_INCREMENTED=$PYTHON_SDK_VERSION_INCREMENTED" >> $GITHUB_ENV
- name: Build the package
if: ${{ env.PYTHON_SDK_VERSION_INCREMENTED == 'true' }}
run: |
python -m build
working-directory: ./apps/python-sdk
- name: Publish to PyPI
if: ${{ env.PYTHON_SDK_VERSION_INCREMENTED == 'true' }}
env:
TWINE_USERNAME: ${{ secrets.PYPI_USERNAME }}
TWINE_PASSWORD: ${{ secrets.PYPI_PASSWORD }}
run: |
twine upload dist/*
working-directory: ./apps/python-sdk
build-and-publish-js-sdk:
name: Build and publish JavaScript SDK
runs-on: ubuntu-latest
needs: deploy
steps:
- uses: actions/checkout@v3
- name: Set up Node.js
uses: actions/setup-node@v3
with:
node-version: '20'
registry-url: 'https://registry.npmjs.org/'
scope: '@mendable'
always-auth: true
- name: Install pnpm
run: npm install -g pnpm
- name: Install python for running version check script
run: |
python -m pip install --upgrade pip
pip install setuptools wheel requests packaging
- name: Install dependencies for JavaScript SDK
run: pnpm install
working-directory: ./apps/js-sdk/firecrawl
- name: Run version check script
id: version_check_script
run: |
VERSION_INCREMENTED=$(python .github/scripts/check_version_has_incremented.py js ./apps/js-sdk/firecrawl @mendable/firecrawl-js)
echo "VERSION_INCREMENTED=$VERSION_INCREMENTED" >> $GITHUB_ENV
- name: Build and publish to npm
if: ${{ env.VERSION_INCREMENTED == 'true' }}
env:
NODE_AUTH_TOKEN: ${{ secrets.NPM_TOKEN }}
run: |
npm run build-and-publish
working-directory: ./apps/js-sdk/firecrawl

16
.gitignore vendored
View File

@ -14,3 +14,19 @@ apps/test-suite/node_modules/
apps/test-suite/.env
apps/test-suite/logs
apps/test-suite/load-test-results/test-run-report.json
apps/playwright-service-ts/node_modules/
apps/playwright-service-ts/package-lock.json
/examples/o1_web_crawler/venv
*.pyc
.rdb
apps/js-sdk/firecrawl/dist
/examples/o1_web_crawler/firecrawl_env
/examples/crm_lead_enrichment/crm_lead_enrichment_env
/.venv
/examples/claude_web_crawler/firecrawl_env

6
.gitmodules vendored Normal file
View File

@ -0,0 +1,6 @@
[submodule "apps/go-sdk/firecrawl-go"]
path = apps/go-sdk/firecrawl-go
url = https://github.com/mendableai/firecrawl-go
[submodule "apps/go-sdk/firecrawl-go-examples"]
path = apps/go-sdk/firecrawl-go-examples
url = https://github.com/mendableai/firecrawl-go-examples

5
.vscode/settings.json vendored Normal file
View File

@ -0,0 +1,5 @@
{
"rust-analyzer.linkedProjects": [
"apps/rust-sdk/Cargo.toml"
]
}

6
CONTRIBUTING.md
View File

@ -12,7 +12,7 @@ First, start by installing dependencies
2. pnpm [instructions](https://pnpm.io/installation)
3. redis [instructions](https://redis.io/docs/latest/operate/oss_and_stack/install/install-redis/)
Set environment variables in a .env in the /apps/api/ directoryyou can copy over the template in .env.example.
Set environment variables in a .env in the /apps/api/ directory you can copy over the template in .env.example.
To start, we wont set up authentication, or any optional sub services (pdf parsing, JS blocking support, AI features )
@ -24,6 +24,7 @@ NUM_WORKERS_PER_QUEUE=8
PORT=3002
HOST=0.0.0.0
REDIS_URL=redis://localhost:6379
REDIS_RATE_LIMIT_URL=redis://localhost:6379
## To turn on DB authentication, you need to set up supabase.
USE_DB_AUTHENTICATION=false
@ -43,7 +44,6 @@ BULL_AUTH_KEY= @
LOGTAIL_KEY= # Use if you're configuring basic logging with logtail
PLAYWRIGHT_MICROSERVICE_URL= # set if you'd like to run a playwright fallback
LLAMAPARSE_API_KEY= #Set if you have a llamaparse key you'd like to use to parse pdfs
SERPER_API_KEY= #Set if you have a serper key you'd like to use as a search api
SLACK_WEBHOOK_URL= # set if you'd like to send slack server health status messages
POSTHOG_API_KEY= # set if you'd like to send posthog events like job logs
POSTHOG_HOST= # set if you'd like to send posthog events like job logs
@ -103,7 +103,7 @@ This should return the response Hello, world!
If you’d like to test the crawl endpoint, you can run this
```curl
curl -X POST http://localhost:3002/v0/crawl \
curl -X POST http://localhost:3002/v1/crawl \
-H 'Content-Type: application/json' \
-d '{
"url": "https://mendable.ai"

209
LICENSE
View File

@ -1,35 +1,35 @@
GNU AFFERO GENERAL PUBLIC LICENSE
Version 3, 19 November 2007
Copyright (C) 2007 Free Software Foundation, Inc. <https://fsf.org/>
Everyone is permitted to copy and distribute verbatim copies
of this license document, but changing it is not allowed.
Copyright (C) 2007 Free Software Foundation, Inc. <https://fsf.org/>
Everyone is permitted to copy and distribute verbatim copies
of this license document, but changing it is not allowed.
Preamble
The GNU Affero General Public License is a free, copyleft license for
The GNU Affero General Public License is a free, copyleft license for
software and other kinds of works, specifically designed to ensure
cooperation with the community in the case of network server software.
The licenses for most software and other practical works are designed
The licenses for most software and other practical works are designed
to take away your freedom to share and change the works. By contrast,
our General Public Licenses are intended to guarantee your freedom to
share and change all versions of a program--to make sure it remains free
software for all its users.
When we speak of free software, we are referring to freedom, not
When we speak of free software, we are referring to freedom, not
price. Our General Public Licenses are designed to make sure that you
have the freedom to distribute copies of free software (and charge for
them if you wish), that you receive source code or can get it if you
want it, that you can change the software or use pieces of it in new
free programs, and that you know you can do these things.
Developers that use our General Public Licenses protect your rights
Developers that use our General Public Licenses protect your rights
with two steps: (1) assert copyright on the software, and (2) offer
you this License which gives you legal permission to copy, distribute
and/or modify the software.
A secondary benefit of defending all users' freedom is that
A secondary benefit of defending all users' freedom is that
improvements made in alternate versions of the program, if they
receive widespread use, become available for other developers to
incorporate. Many developers of free software are heartened and
@ -39,7 +39,7 @@ The GNU General Public License permits making a modified version and
letting the public access it on a server without ever releasing its
source code to the public.
The GNU Affero General Public License is designed specifically to
The GNU Affero General Public License is designed specifically to
ensure that, in such cases, the modified source code becomes available
to the community. It requires the operator of a network server to
provide the source code of the modified version running there to the
@ -47,48 +47,48 @@ users of that server. Therefore, public use of a modified version, on
a publicly accessible server, gives the public access to the source
code of the modified version.
An older license, called the Affero General Public License and
An older license, called the Affero General Public License and
published by Affero, was designed to accomplish similar goals. This is
a different license, not a version of the Affero GPL, but Affero has
released a new version of the Affero GPL which permits relicensing under
this license.
The precise terms and conditions for copying, distribution and
The precise terms and conditions for copying, distribution and
modification follow.
TERMS AND CONDITIONS
0. Definitions.
0. Definitions.
"This License" refers to version 3 of the GNU Affero General Public License.
"This License" refers to version 3 of the GNU Affero General Public License.
"Copyright" also means copyright-like laws that apply to other kinds of
"Copyright" also means copyright-like laws that apply to other kinds of
works, such as semiconductor masks.
"The Program" refers to any copyrightable work licensed under this
"The Program" refers to any copyrightable work licensed under this
License. Each licensee is addressed as "you". "Licensees" and
"recipients" may be individuals or organizations.
To "modify" a work means to copy from or adapt all or part of the work
To "modify" a work means to copy from or adapt all or part of the work
in a fashion requiring copyright permission, other than the making of an
exact copy. The resulting work is called a "modified version" of the
earlier work or a work "based on" the earlier work.
A "covered work" means either the unmodified Program or a work based
A "covered work" means either the unmodified Program or a work based
on the Program.
To "propagate" a work means to do anything with it that, without
To "propagate" a work means to do anything with it that, without
permission, would make you directly or secondarily liable for
infringement under applicable copyright law, except executing it on a
computer or modifying a private copy. Propagation includes copying,
distribution (with or without modification), making available to the
public, and in some countries other activities as well.
To "convey" a work means any kind of propagation that enables other
To "convey" a work means any kind of propagation that enables other
parties to make or receive copies. Mere interaction with a user through
a computer network, with no transfer of a copy, is not conveying.
An interactive user interface displays "Appropriate Legal Notices"
An interactive user interface displays "Appropriate Legal Notices"
to the extent that it includes a convenient and prominently visible
feature that (1) displays an appropriate copyright notice, and (2)
tells the user that there is no warranty for the work (except to the
@ -97,18 +97,18 @@ work under this License, and how to view a copy of this License. If
the interface presents a list of user commands or options, such as a
menu, a prominent item in the list meets this criterion.
1. Source Code.
1. Source Code.
The "source code" for a work means the preferred form of the work
The "source code" for a work means the preferred form of the work
for making modifications to it. "Object code" means any non-source
form of a work.
A "Standard Interface" means an interface that either is an official
A "Standard Interface" means an interface that either is an official
standard defined by a recognized standards body, or, in the case of
interfaces specified for a particular programming language, one that
is widely used among developers working in that language.
The "System Libraries" of an executable work include anything, other
The "System Libraries" of an executable work include anything, other
than the work as a whole, that (a) is included in the normal form of
packaging a Major Component, but which is not part of that Major
Component, and (b) serves only to enable use of the work with that
@ -119,7 +119,7 @@ implementation is available to the public in source code form. A
(if any) on which the executable work runs, or a compiler used to
produce the work, or an object code interpreter used to run it.
The "Corresponding Source" for a work in object code form means all
The "Corresponding Source" for a work in object code form means all
the source code needed to generate, install, and (for an executable
work) run the object code and to modify the work, including scripts to
control those activities. However, it does not include the work's
@ -132,16 +132,16 @@ linked subprograms that the work is specifically designed to require,
such as by intimate data communication or control flow between those
subprograms and other parts of the work.
The Corresponding Source need not include anything that users
The Corresponding Source need not include anything that users
can regenerate automatically from other parts of the Corresponding
Source.
The Corresponding Source for a work in source code form is that
The Corresponding Source for a work in source code form is that
same work.
2. Basic Permissions.
2. Basic Permissions.
All rights granted under this License are granted for the term of
All rights granted under this License are granted for the term of
copyright on the Program, and are irrevocable provided the stated
conditions are met. This License explicitly affirms your unlimited
permission to run the unmodified Program. The output from running a
@ -149,7 +149,7 @@ covered work is covered by this License only if the output, given its
content, constitutes a covered work. This License acknowledges your
rights of fair use or other equivalent, as provided by copyright law.
You may make, run and propagate covered works that you do not
You may make, run and propagate covered works that you do not
convey, without conditions so long as your license otherwise remains
in force. You may convey covered works to others for the sole purpose
of having them make modifications exclusively for you, or provide you
@ -160,19 +160,19 @@ for you must do so exclusively on your behalf, under your direction
and control, on terms that prohibit them from making any copies of
your copyrighted material outside their relationship with you.
Conveying under any other circumstances is permitted solely under
Conveying under any other circumstances is permitted solely under
the conditions stated below. Sublicensing is not allowed; section 10
makes it unnecessary.
3. Protecting Users' Legal Rights From Anti-Circumvention Law.
3. Protecting Users' Legal Rights From Anti-Circumvention Law.
No covered work shall be deemed part of an effective technological
No covered work shall be deemed part of an effective technological
measure under any applicable law fulfilling obligations under article
11 of the WIPO copyright treaty adopted on 20 December 1996, or
similar laws prohibiting or restricting circumvention of such
measures.
When you convey a covered work, you waive any legal power to forbid
When you convey a covered work, you waive any legal power to forbid
circumvention of technological measures to the extent such circumvention
is effected by exercising rights under this License with respect to
the covered work, and you disclaim any intention to limit operation or
@ -180,9 +180,9 @@ modification of the work as a means of enforcing, against the work's
users, your or third parties' legal rights to forbid circumvention of
technological measures.
4. Conveying Verbatim Copies.
4. Conveying Verbatim Copies.
You may convey verbatim copies of the Program's source code as you
You may convey verbatim copies of the Program's source code as you
receive it, in any medium, provided that you conspicuously and
appropriately publish on each copy an appropriate copyright notice;
keep intact all notices stating that this License and any
@ -190,12 +190,12 @@ non-permissive terms added in accord with section 7 apply to the code;
keep intact all notices of the absence of any warranty; and give all
recipients a copy of this License along with the Program.
You may charge any price or no price for each copy that you convey,
You may charge any price or no price for each copy that you convey,
and you may offer support or warranty protection for a fee.
5. Conveying Modified Source Versions.
5. Conveying Modified Source Versions.
You may convey a work based on the Program, or the modifications to
You may convey a work based on the Program, or the modifications to
produce it from the Program, in the form of source code under the
terms of section 4, provided that you also meet all of these conditions:
@ -220,7 +220,7 @@ terms of section 4, provided that you also meet all of these conditions:
interfaces that do not display Appropriate Legal Notices, your
work need not make them do so.
A compilation of a covered work with other separate and independent
A compilation of a covered work with other separate and independent
works, which are not by their nature extensions of the covered work,
and which are not combined with it such as to form a larger program,
in or on a volume of a storage or distribution medium, is called an
@ -230,9 +230,9 @@ beyond what the individual works permit. Inclusion of a covered work
in an aggregate does not cause this License to apply to the other
parts of the aggregate.
6. Conveying Non-Source Forms.
6. Conveying Non-Source Forms.
You may convey a covered work in object code form under the terms
You may convey a covered work in object code form under the terms
of sections 4 and 5, provided that you also convey the
machine-readable Corresponding Source under the terms of this License,
in one of these ways:
@ -278,11 +278,11 @@ in one of these ways:
Source of the work are being offered to the general public at no
charge under subsection 6d.
A separable portion of the object code, whose source code is excluded
A separable portion of the object code, whose source code is excluded
from the Corresponding Source as a System Library, need not be
included in conveying the object code work.
A "User Product" is either (1) a "consumer product", which means any
A "User Product" is either (1) a "consumer product", which means any
tangible personal property which is normally used for personal, family,
or household purposes, or (2) anything designed or sold for incorporation
into a dwelling. In determining whether a product is a consumer product,
@ -295,7 +295,7 @@ is a consumer product regardless of whether the product has substantial
commercial, industrial or non-consumer uses, unless such uses represent
the only significant mode of use of the product.
"Installation Information" for a User Product means any methods,
"Installation Information" for a User Product means any methods,
procedures, authorization keys, or other information required to install
and execute modified versions of a covered work in that User Product from
a modified version of its Corresponding Source. The information must
@ -303,7 +303,7 @@ suffice to ensure that the continued functioning of the modified object
code is in no case prevented or interfered with solely because
modification has been made.
If you convey an object code work under this section in, or with, or
If you convey an object code work under this section in, or with, or
specifically for use in, a User Product, and the conveying occurs as
part of a transaction in which the right of possession and use of the
User Product is transferred to the recipient in perpetuity or for a
@ -314,7 +314,7 @@ if neither you nor any third party retains the ability to install
modified object code on the User Product (for example, the work has
been installed in ROM).
The requirement to provide Installation Information does not include a
The requirement to provide Installation Information does not include a
requirement to continue to provide support service, warranty, or updates
for a work that has been modified or installed by the recipient, or for
the User Product in which it has been modified or installed. Access to a
@ -322,15 +322,15 @@ network may be denied when the modification itself materially and
adversely affects the operation of the network or violates the rules and
protocols for communication across the network.
Corresponding Source conveyed, and Installation Information provided,
Corresponding Source conveyed, and Installation Information provided,
in accord with this section must be in a format that is publicly
documented (and with an implementation available to the public in
source code form), and must require no special password or key for
unpacking, reading or copying.
7. Additional Terms.
7. Additional Terms.
"Additional permissions" are terms that supplement the terms of this
"Additional permissions" are terms that supplement the terms of this
License by making exceptions from one or more of its conditions.
Additional permissions that are applicable to the entire Program shall
be treated as though they were included in this License, to the extent
@ -339,14 +339,14 @@ apply only to part of the Program, that part may be used separately
under those permissions, but the entire Program remains governed by
this License without regard to the additional permissions.
When you convey a copy of a covered work, you may at your option
When you convey a copy of a covered work, you may at your option
remove any additional permissions from that copy, or from any part of
it. (Additional permissions may be written to require their own
removal in certain cases when you modify the work.) You may place
additional permissions on material, added by you to a covered work,
for which you have or can give appropriate copyright permission.
Notwithstanding any other provision of this License, for material you
Notwithstanding any other provision of this License, for material you
add to a covered work, you may (if authorized by the copyright holders of
that material) supplement the terms of this License with terms:
@ -373,7 +373,7 @@ that material) supplement the terms of this License with terms:
any liability that these contractual assumptions directly impose on
those licensors and authors.
All other non-permissive additional terms are considered "further
All other non-permissive additional terms are considered "further
restrictions" within the meaning of section 10. If the Program as you
received it, or any part of it, contains a notice stating that it is
governed by this License along with a term that is a further
@ -383,46 +383,46 @@ License, you may add to a covered work material governed by the terms
of that license document, provided that the further restriction does
not survive such relicensing or conveying.
If you add terms to a covered work in accord with this section, you
If you add terms to a covered work in accord with this section, you
must place, in the relevant source files, a statement of the
additional terms that apply to those files, or a notice indicating
where to find the applicable terms.
Additional terms, permissive or non-permissive, may be stated in the
Additional terms, permissive or non-permissive, may be stated in the
form of a separately written license, or stated as exceptions;
the above requirements apply either way.
8. Termination.
8. Termination.
You may not propagate or modify a covered work except as expressly
You may not propagate or modify a covered work except as expressly
provided under this License. Any attempt otherwise to propagate or
modify it is void, and will automatically terminate your rights under
this License (including any patent licenses granted under the third
paragraph of section 11).
However, if you cease all violation of this License, then your
However, if you cease all violation of this License, then your
license from a particular copyright holder is reinstated (a)
provisionally, unless and until the copyright holder explicitly and
finally terminates your license, and (b) permanently, if the copyright
holder fails to notify you of the violation by some reasonable means
prior to 60 days after the cessation.
Moreover, your license from a particular copyright holder is
Moreover, your license from a particular copyright holder is
reinstated permanently if the copyright holder notifies you of the
violation by some reasonable means, this is the first time you have
received notice of violation of this License (for any work) from that
copyright holder, and you cure the violation prior to 30 days after
your receipt of the notice.
Termination of your rights under this section does not terminate the
Termination of your rights under this section does not terminate the
licenses of parties who have received copies or rights from you under
this License. If your rights have been terminated and not permanently
reinstated, you do not qualify to receive new licenses for the same
material under section 10.
9. Acceptance Not Required for Having Copies.
9. Acceptance Not Required for Having Copies.
You are not required to accept this License in order to receive or
You are not required to accept this License in order to receive or
run a copy of the Program. Ancillary propagation of a covered work
occurring solely as a consequence of using peer-to-peer transmission
to receive a copy likewise does not require acceptance. However,
@ -431,14 +431,14 @@ modify any covered work. These actions infringe copyright if you do
not accept this License. Therefore, by modifying or propagating a
covered work, you indicate your acceptance of this License to do so.
10. Automatic Licensing of Downstream Recipients.
10. Automatic Licensing of Downstream Recipients.
Each time you convey a covered work, the recipient automatically
Each time you convey a covered work, the recipient automatically
receives a license from the original licensors, to run, modify and
propagate that work, subject to this License. You are not responsible
for enforcing compliance by third parties with this License.
An "entity transaction" is a transaction transferring control of an
An "entity transaction" is a transaction transferring control of an
organization, or substantially all assets of one, or subdividing an
organization, or merging organizations. If propagation of a covered
work results from an entity transaction, each party to that
@ -448,7 +448,7 @@ give under the previous paragraph, plus a right to possession of the
Corresponding Source of the work from the predecessor in interest, if
the predecessor has it or can get it with reasonable efforts.
You may not impose any further restrictions on the exercise of the
You may not impose any further restrictions on the exercise of the
rights granted or affirmed under this License. For example, you may
not impose a license fee, royalty, or other charge for exercise of
rights granted under this License, and you may not initiate litigation
@ -456,13 +456,13 @@ rights granted under this License, and you may not initiate litigation
any patent claim is infringed by making, using, selling, offering for
sale, or importing the Program or any portion of it.
11. Patents.
11. Patents.
A "contributor" is a copyright holder who authorizes use under this
A "contributor" is a copyright holder who authorizes use under this
License of the Program or a work on which the Program is based. The
work thus licensed is called the contributor's "contributor version".
A contributor's "essential patent claims" are all patent claims
A contributor's "essential patent claims" are all patent claims
owned or controlled by the contributor, whether already acquired or
hereafter acquired, that would be infringed by some manner, permitted
by this License, of making, using, or selling its contributor version,
@ -472,19 +472,19 @@ purposes of this definition, "control" includes the right to grant
patent sublicenses in a manner consistent with the requirements of
this License.
Each contributor grants you a non-exclusive, worldwide, royalty-free
Each contributor grants you a non-exclusive, worldwide, royalty-free
patent license under the contributor's essential patent claims, to
make, use, sell, offer for sale, import and otherwise run, modify and
propagate the contents of its contributor version.
In the following three paragraphs, a "patent license" is any express
In the following three paragraphs, a "patent license" is any express
agreement or commitment, however denominated, not to enforce a patent
(such as an express permission to practice a patent or covenant not to
sue for patent infringement). To "grant" such a patent license to a
party means to make such an agreement or commitment not to enforce a
patent against the party.
If you convey a covered work, knowingly relying on a patent license,
If you convey a covered work, knowingly relying on a patent license,
and the Corresponding Source of the work is not available for anyone
to copy, free of charge and under the terms of this License, through a
publicly available network server or other readily accessible means,
@ -498,7 +498,7 @@ covered work in a country, or your recipient's use of the covered work
in a country, would infringe one or more identifiable patents in that
country that you have reason to believe are valid.
If, pursuant to or in connection with a single transaction or
If, pursuant to or in connection with a single transaction or
arrangement, you convey, or propagate by procuring conveyance of, a
covered work, and grant a patent license to some of the parties
receiving the covered work authorizing them to use, propagate, modify
@ -506,7 +506,7 @@ or convey a specific copy of the covered work, then the patent license
you grant is automatically extended to all recipients of the covered
work and works based on it.
A patent license is "discriminatory" if it does not include within
A patent license is "discriminatory" if it does not include within
the scope of its coverage, prohibits the exercise of, or is
conditioned on the non-exercise of one or more of the rights that are
specifically granted under this License. You may not convey a covered
@ -521,13 +521,13 @@ for and in connection with specific products or compilations that
contain the covered work, unless you entered into that arrangement,
or that patent license was granted, prior to 28 March 2007.
Nothing in this License shall be construed as excluding or limiting
Nothing in this License shall be construed as excluding or limiting
any implied license or other defenses to infringement that may
otherwise be available to you under applicable patent law.
12. No Surrender of Others' Freedom.
12. No Surrender of Others' Freedom.
If conditions are imposed on you (whether by court order, agreement or
If conditions are imposed on you (whether by court order, agreement or
otherwise) that contradict the conditions of this License, they do not
excuse you from the conditions of this License. If you cannot convey a
covered work so as to satisfy simultaneously your obligations under this
@ -537,9 +537,9 @@ to collect a royalty for further conveying from those to whom you convey
the Program, the only way you could satisfy both those terms and this
License would be to refrain entirely from conveying the Program.
13. Remote Network Interaction; Use with the GNU General Public License.
13. Remote Network Interaction; Use with the GNU General Public License.
Notwithstanding any other provision of this License, if you modify the
Notwithstanding any other provision of this License, if you modify the
Program, your modified version must prominently offer all users
interacting with it remotely through a computer network (if your version
supports such interaction) an opportunity to receive the Corresponding
@ -550,7 +550,7 @@ shall include the Corresponding Source for any work covered by version 3
of the GNU General Public License that is incorporated pursuant to the
following paragraph.
Notwithstanding any other provision of this License, you have
Notwithstanding any other provision of this License, you have
permission to link or combine any covered work with a work licensed
under version 3 of the GNU General Public License into a single
combined work, and to convey the resulting work. The terms of this
@ -558,14 +558,14 @@ License will continue to apply to the part which is the covered work,
but the work with which it is combined will remain governed by version
3 of the GNU General Public License.
14. Revised Versions of this License.
14. Revised Versions of this License.
The Free Software Foundation may publish revised and/or new versions of
The Free Software Foundation may publish revised and/or new versions of
the GNU Affero General Public License from time to time. Such new versions
will be similar in spirit to the present version, but may differ in detail to
address new problems or concerns.
Each version is given a distinguishing version number. If the
Each version is given a distinguishing version number. If the
Program specifies that a certain numbered version of the GNU Affero General
Public License "or any later version" applies to it, you have the
option of following the terms and conditions either of that numbered
@ -574,19 +574,19 @@ Foundation. If the Program does not specify a version number of the
GNU Affero General Public License, you may choose any version ever published
by the Free Software Foundation.
If the Program specifies that a proxy can decide which future
If the Program specifies that a proxy can decide which future
versions of the GNU Affero General Public License can be used, that proxy's
public statement of acceptance of a version permanently authorizes you
to choose that version for the Program.
Later license versions may give you additional or different
Later license versions may give you additional or different
permissions. However, no additional obligations are imposed on any
author or copyright holder as a result of your choosing to follow a
later version.
15. Disclaimer of Warranty.
15. Disclaimer of Warranty.
THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY
THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY
APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT
HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY
OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO,
@ -595,9 +595,9 @@ PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM
IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF
ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
16. Limitation of Liability.
16. Limitation of Liability.
IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS
THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY
GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE
@ -607,9 +607,9 @@ PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS),
EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF
SUCH DAMAGES.
17. Interpretation of Sections 15 and 16.
17. Interpretation of Sections 15 and 16.
If the disclaimer of warranty and limitation of liability provided
If the disclaimer of warranty and limitation of liability provided
above cannot be given local legal effect according to their terms,
reviewing courts shall apply local law that most closely approximates
an absolute waiver of all civil liability in connection with the
@ -620,11 +620,11 @@ copy of the Program in return for a fee.
How to Apply These Terms to Your New Programs
If you develop a new program, and you want it to be of the greatest
If you develop a new program, and you want it to be of the greatest
possible use to the public, the best way to achieve this is to make it
free software which everyone can redistribute and change under these terms.
To do so, attach the following notices to the program. It is safest
To do so, attach the following notices to the program. It is safest
to attach them to the start of each source file to most effectively
state the exclusion of warranty; and each file should have at least
the "copyright" line and a pointer to where the full notice is found.
@ -647,7 +647,7 @@ the "copyright" line and a pointer to where the full notice is found.
Also add information on how to contact you by electronic and paper mail.
If your software can interact with users remotely through a computer
If your software can interact with users remotely through a computer
network, you should also make sure that it provides a way for users to
get its source. For example, if your program is a web application, its
interface could display a "Source" link that leads users to an archive
@ -655,7 +655,26 @@ of the code. There are many ways you could offer source, and different
solutions will be better for different programs; see section 13 for the
specific requirements.
You should also get your employer (if you work as a programmer) or school,
You should also get your employer (if you work as a programmer) or school,
if any, to sign a "copyright disclaimer" for the program, if necessary.
For more information on this, and how to apply and follow the GNU AGPL, see
<https://www.gnu.org/licenses/>.
Firecrawl - Web scraping and crawling tool
Copyright (c) 2024 Sideguide Technologies Inc.
This program is free software: you can redistribute it and/or modify
it under the terms of the GNU Affero General Public License as published
by the Free Software Foundation, either version 3 of the License, or
(at your option) any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU Affero General Public License for more details.
You should have received a copy of the GNU Affero General Public License
along with this program. If not, see <https://www.gnu.org/licenses/>.
For more information, please contact:
Sideguide Technologies Inc.

491
README.md
View File

@ -1,27 +1,64 @@
<h3 align="center">
<a name="readme-top"></a>
<img
src="https://raw.githubusercontent.com/mendableai/firecrawl/main/img/firecrawl_logo.png"
height="200"
>
</h3>
<div align="center">
<a href="https://github.com/mendableai/firecrawl/blob/main/LICENSE">
<img src="https://img.shields.io/github/license/mendableai/firecrawl" alt="License">
</a>
<a href="https://pepy.tech/project/firecrawl-py">
<img src="https://static.pepy.tech/badge/firecrawl-py" alt="Downloads">
</a>
<a href="https://GitHub.com/mendableai/firecrawl/graphs/contributors">
<img src="https://img.shields.io/github/contributors/mendableai/firecrawl.svg" alt="GitHub Contributors">
</a>
<a href="https://firecrawl.dev">
<img src="https://img.shields.io/badge/Visit-firecrawl.dev-orange" alt="Visit firecrawl.dev">
</a>
</div>
<div>
<p align="center">
<a href="https://twitter.com/firecrawl_dev">
<img src="https://img.shields.io/badge/Follow%20on%20X-000000?style=for-the-badge&logo=x&logoColor=white" alt="Follow on X" />
</a>
<a href="https://www.linkedin.com/company/104100957">
<img src="https://img.shields.io/badge/Follow%20on%20LinkedIn-0077B5?style=for-the-badge&logo=linkedin&logoColor=white" alt="Follow on LinkedIn" />
</a>
<a href="https://discord.com/invite/gSmWdAkdwd">
<img src="https://img.shields.io/badge/Join%20our%20Discord-5865F2?style=for-the-badge&logo=discord&logoColor=white" alt="Join our Discord" />
</a>
</p>
</div>
# 🔥 Firecrawl
Crawl and convert any website into LLM-ready markdown or structured data. Built by [Mendable.ai](https://mendable.ai?ref=gfirecrawl) and the Firecrawl community. Includes powerful scraping, crawling and data extraction capabilities.
Empower your AI apps with clean data from any website. Featuring advanced scraping, crawling, and data extraction capabilities.
_This repository is in its early development stages. We are still merging custom modules in the mono repo. It's not completely yet ready for full self-host deployment, but you can already run it locally._
_This repository is in development, and we’re still integrating custom modules into the mono repo. It's not fully ready for self-hosted deployment yet, but you can run it locally._
## What is Firecrawl?
[Firecrawl](https://firecrawl.dev?ref=github) is an API service that takes a URL, crawls it, and converts it into clean markdown or structured data. We crawl all accessible subpages and give you clean data for each. No sitemap required.
[Firecrawl](https://firecrawl.dev?ref=github) is an API service that takes a URL, crawls it, and converts it into clean markdown or structured data. We crawl all accessible subpages and give you clean data for each. No sitemap required. Check out our [documentation](https://docs.firecrawl.dev).
_Pst. hey, you, join our stargazers :)_
<img src="https://github.com/mendableai/firecrawl/assets/44934913/53c4483a-0f0e-40c6-bd84-153a07f94d29" width="200">
<a href="https://github.com/mendableai/firecrawl">
<img src="https://img.shields.io/github/stars/mendableai/firecrawl.svg?style=social&label=Star&maxAge=2592000" alt="GitHub stars">
</a>
## How to use it?
We provide an easy to use API with our hosted version. You can find the playground and documentation [here](https://firecrawl.dev/playground). You can also self host the backend if you'd like.
- [x] [API](https://firecrawl.dev/playground)
- [x] [Python SDK](https://github.com/mendableai/firecrawl/tree/main/apps/python-sdk)
- [x] [Node SDK](https://github.com/mendableai/firecrawl/tree/main/apps/js-sdk)
- [x] [Langchain Integration 🦜🔗](https://python.langchain.com/docs/integrations/document_loaders/firecrawl/)
- [x] [Llama Index Integration 🦙](https://docs.llamaindex.ai/en/latest/examples/data_connectors/WebPageDemo/#using-firecrawl-reader)
- [X] [Langchain JS Integration 🦜🔗](https://js.langchain.com/docs/integrations/document_loaders/web_loaders/firecrawl)
Check out the following resources to get started:
- [x] **API**: [Documentation](https://docs.firecrawl.dev/api-reference/introduction)
- [x] **SDKs**: [Python](https://docs.firecrawl.dev/sdks/python), [Node](https://docs.firecrawl.dev/sdks/node), [Go](https://docs.firecrawl.dev/sdks/go), [Rust](https://docs.firecrawl.dev/sdks/rust)
- [x] **LLM Frameworks**: [Langchain (python)](https://python.langchain.com/docs/integrations/document_loaders/firecrawl/), [Langchain (js)](https://js.langchain.com/docs/integrations/document_loaders/web_loaders/firecrawl), [Llama Index](https://docs.llamaindex.ai/en/latest/examples/data_connectors/WebPageDemo/#using-firecrawl-reader), [Crew.ai](https://docs.crewai.com/), [Composio](https://composio.dev/tools/firecrawl/all), [PraisonAI](https://docs.praison.ai/firecrawl/)
- [x] **Low-code Frameworks**: [Dify](https://dify.ai/blog/dify-ai-blog-integrated-with-firecrawl), [Langflow](https://docs.langflow.org/), [Flowise AI](https://docs.flowiseai.com/integrations/langchain/document-loaders/firecrawl), [Cargo](https://docs.getcargo.io/integration/firecrawl), [Pipedream](https://pipedream.com/apps/firecrawl/)
- [x] **Others**: [Zapier](https://zapier.com/apps/firecrawl/integrations), [Pabbly Connect](https://www.pabbly.com/connect/integrations/firecrawl/)
- [ ] Want an SDK or Integration? Let us know by opening an issue.
To run locally, refer to guide [here](https://github.com/mendableai/firecrawl/blob/main/CONTRIBUTING.md).
@ -30,23 +67,48 @@ To run locally, refer to guide [here](https://github.com/mendableai/firecrawl/bl
To use the API, you need to sign up on [Firecrawl](https://firecrawl.dev) and get an API key.
### Features
- [**Scrape**](#scraping): scrapes a URL and get its content in LLM-ready format (markdown, structured data via [LLM Extract](#llm-extraction-beta), screenshot, html)
- [**Crawl**](#crawling): scrapes all the URLs of a web page and return content in LLM-ready format
- [**Map**](#map-alpha): input a website and get all the website urls - extremely fast
### Powerful Capabilities
- **LLM-ready formats**: markdown, structured data, screenshot, HTML, links, metadata
- **The hard stuff**: proxies, anti-bot mechanisms, dynamic content (js-rendered), output parsing, orchestration
- **Customizability**: exclude tags, crawl behind auth walls with custom headers, max crawl depth, etc...
- **Media parsing**: pdfs, docx, images.
- **Reliability first**: designed to get the data you need - no matter how hard it is.
- **Actions**: click, scroll, input, wait and more before extracting data
- **Batching (New)**: scrape thousands of URLs at the same time with a new async endpoint
You can find all of Firecrawl's capabilities and how to use them in our [documentation](https://docs.firecrawl.dev)
### Crawling
Used to crawl a URL and all accessible subpages. This submits a crawl job and returns a job ID to check the status of the crawl.
```bash
curl -X POST https://api.firecrawl.dev/v0/crawl \
curl -X POST https://api.firecrawl.dev/v1/crawl \
-H 'Content-Type: application/json' \
-H 'Authorization: Bearer YOUR_API_KEY' \
-H 'Authorization: Bearer fc-YOUR_API_KEY' \
-d '{
"url": "https://mendable.ai"
"url": "https://docs.firecrawl.dev",
"limit": 100,
"scrapeOptions": {
"formats": ["markdown", "html"]
}
}'
```
Returns a jobId
Returns a crawl job id and the url to check the status of the crawl.
```json
{ "jobId": "1234-5678-9101" }
{
"success": true,
"id": "123-456-789",
"url": "https://api.firecrawl.dev/v1/crawl/123-456-789"
}
```
### Check Crawl Job
@ -54,7 +116,7 @@ Returns a jobId
Used to check the status of a crawl job and get its result.
```bash
curl -X GET https://api.firecrawl.dev/v0/crawl/status/1234-5678-9101 \
curl -X GET https://api.firecrawl.dev/v1/crawl/123-456-789 \
-H 'Content-Type: application/json' \
-H 'Authorization: Bearer YOUR_API_KEY'
```
@ -62,18 +124,20 @@ curl -X GET https://api.firecrawl.dev/v0/crawl/status/1234-5678-9101 \
```json
{
"status": "completed",
"current": 22,
"total": 22,
"total": 36,
"creditsUsed": 36,
"expiresAt": "2024-00-00T00:00:00.000Z",
"data": [
{
"content": "Raw Content ",
"markdown": "# Markdown Content",
"provider": "web-scraper",
"markdown": "[Firecrawl Docs home page![light logo](https://mintlify.s3-us-west-1.amazonaws.com/firecrawl/logo/light.svg)!...",
"html": "<!DOCTYPE html><html lang=\"en\" class=\"js-focus-visible lg:[--scroll-mt:9.5rem]\" data-js-focus-visible=\"\">...",
"metadata": {
"title": "Mendable | AI for CX and Sales",
"description": "AI for CX and Sales",
"language": null,
"sourceURL": "https://www.mendable.ai/"
"title": "Build a 'Chat with website' using Groq Llama 3 | Firecrawl",
"language": "en",
"sourceURL": "https://docs.firecrawl.dev/learn/rag-llama3",
"description": "Learn how to use Firecrawl, Groq Llama 3, and Langchain to build a 'Chat with your website' bot.",
"ogLocaleAlternate": [],
"statusCode": 200
}
}
]
@ -82,14 +146,15 @@ curl -X GET https://api.firecrawl.dev/v0/crawl/status/1234-5678-9101 \
### Scraping
Used to scrape a URL and get its content.
Used to scrape a URL and get its content in the specified formats.
```bash
curl -X POST https://api.firecrawl.dev/v0/scrape \
curl -X POST https://api.firecrawl.dev/v1/scrape \
-H 'Content-Type: application/json' \
-H 'Authorization: Bearer YOUR_API_KEY' \
-d '{
"url": "https://mendable.ai"
"url": "https://docs.firecrawl.dev",
"formats" : ["markdown", "html"]
}'
```
@ -99,68 +164,95 @@ Response:
{
"success": true,
"data": {
"content": "Raw Content ",
"markdown": "# Markdown Content",
"provider": "web-scraper",
"markdown": "Launch Week I is here! [See our Day 2 Release 🚀](https://www.firecrawl.dev/blog/launch-week-i-day-2-doubled-rate-limits)[💥 Get 2 months free...",
"html": "<!DOCTYPE html><html lang=\"en\" class=\"light\" style=\"color-scheme: light;\"><body class=\"__variable_36bd41 __variable_d7dc5d font-inter ...",
"metadata": {
"title": "Mendable | AI for CX and Sales",
"description": "AI for CX and Sales",
"language": null,
"sourceURL": "https://www.mendable.ai/"
"title": "Home - Firecrawl",
"description": "Firecrawl crawls and converts any website into clean markdown.",
"language": "en",
"keywords": "Firecrawl,Markdown,Data,Mendable,Langchain",
"robots": "follow, index",
"ogTitle": "Firecrawl",
"ogDescription": "Turn any website into LLM-ready data.",
"ogUrl": "https://www.firecrawl.dev/",
"ogImage": "https://www.firecrawl.dev/og.png?123",
"ogLocaleAlternate": [],
"ogSiteName": "Firecrawl",
"sourceURL": "https://firecrawl.dev",
"statusCode": 200
}
}
}
```
### Search (Beta)
### Map (Alpha)
Used to search the web, get the most relevant results, scrape each page and return the markdown.
Used to map a URL and get urls of the website. This returns most links present on the website.
```bash
curl -X POST https://api.firecrawl.dev/v0/search \
```bash cURL
curl -X POST https://api.firecrawl.dev/v1/map \
-H 'Content-Type: application/json' \
-H 'Authorization: Bearer YOUR_API_KEY' \
-d '{
"query": "firecrawl",
"pageOptions": {
"fetchPageContent": true // false for a fast serp api
}
"url": "https://firecrawl.dev"
}'
```
Response:
```json
{
"success": true,
"data": [
{
"url": "https://mendable.ai",
"markdown": "# Markdown Content",
"provider": "web-scraper",
"metadata": {
"title": "Mendable | AI for CX and Sales",
"description": "AI for CX and Sales",
"language": null,
"sourceURL": "https://www.mendable.ai/"
}
}
"status": "success",
"links": [
"https://firecrawl.dev",
"https://www.firecrawl.dev/pricing",
"https://www.firecrawl.dev/blog",
"https://www.firecrawl.dev/playground",
"https://www.firecrawl.dev/smart-crawl",
]
}
```
### Intelligent Extraction (Beta)
#### Map with search
Map with `search` param allows you to search for specific urls inside a website.
```bash cURL
curl -X POST https://api.firecrawl.dev/v1/map \
-H 'Content-Type: application/json' \
-H 'Authorization: Bearer YOUR_API_KEY' \
-d '{
"url": "https://firecrawl.dev",
"search": "docs"
}'
```
Response will be an ordered list from the most relevant to the least relevant.
```json
{
"status": "success",
"links": [
"https://docs.firecrawl.dev",
"https://docs.firecrawl.dev/sdks/python",
"https://docs.firecrawl.dev/learn/rag-llama3",
]
}
```
### LLM Extraction (Beta)
Used to extract structured data from scraped pages.
```bash
curl -X POST https://api.firecrawl.dev/v0/scrape \
curl -X POST https://api.firecrawl.dev/v1/scrape \
-H 'Content-Type: application/json' \
-H 'Authorization: Bearer YOUR_API_KEY' \
-d '{
"url": "https://www.mendable.ai/",
"extractorOptions": {
"mode": "llm-extraction",
"extractionPrompt": "Based on the information on the page, extract the information from the schema. ",
"extractionSchema": {
"formats": ["extract"],
"extract": {
"schema": {
"type": "object",
"properties": {
"company_mission": {
@ -212,7 +304,100 @@ curl -X POST https://api.firecrawl.dev/v0/scrape \
}
}
}
```
### Extracting without a schema (New)
You can now extract without a schema by just passing a `prompt` to the endpoint. The llm chooses the structure of the data.
```bash
curl -X POST https://api.firecrawl.dev/v1/scrape \
-H 'Content-Type: application/json' \
-H 'Authorization: Bearer YOUR_API_KEY' \
-d '{
"url": "https://docs.firecrawl.dev/",
"formats": ["extract"],
"extract": {
"prompt": "Extract the company mission from the page."
}
}'
```
### Interacting with the page with Actions (Cloud-only)
Firecrawl allows you to perform various actions on a web page before scraping its content. This is particularly useful for interacting with dynamic content, navigating through pages, or accessing content that requires user interaction.
Here is an example of how to use actions to navigate to google.com, search for Firecrawl, click on the first result, and take a screenshot.
```bash
curl -X POST https://api.firecrawl.dev/v1/scrape \
-H 'Content-Type: application/json' \
-H 'Authorization: Bearer YOUR_API_KEY' \
-d '{
"url": "google.com",
"formats": ["markdown"],
"actions": [
{"type": "wait", "milliseconds": 2000},
{"type": "click", "selector": "textarea[title=\"Search\"]"},
{"type": "wait", "milliseconds": 2000},
{"type": "write", "text": "firecrawl"},
{"type": "wait", "milliseconds": 2000},
{"type": "press", "key": "ENTER"},
{"type": "wait", "milliseconds": 3000},
{"type": "click", "selector": "h3"},
{"type": "wait", "milliseconds": 3000},
{"type": "screenshot"}
]
}'
```
### Batch Scraping Multiple URLs (New)
You can now batch scrape multiple URLs at the same time. It is very similar to how the /crawl endpoint works. It submits a batch scrape job and returns a job ID to check the status of the batch scrape.
```bash
curl -X POST https://api.firecrawl.dev/v1/batch/scrape \
-H 'Content-Type: application/json' \
-H 'Authorization: Bearer YOUR_API_KEY' \
-d '{
"urls": ["https://docs.firecrawl.dev", "https://docs.firecrawl.dev/sdks/overview"],
"formats" : ["markdown", "html"]
}'
```
### Search (v0) (Beta)
Used to search the web, get the most relevant results, scrape each page and return the markdown.
```bash
curl -X POST https://api.firecrawl.dev/v0/search \
-H 'Content-Type: application/json' \
-H 'Authorization: Bearer YOUR_API_KEY' \
-d '{
"query": "firecrawl",
"pageOptions": {
"fetchPageContent": true // false for a fast serp api
}
}'
```
```json
{
"success": true,
"data": [
{
"url": "https://mendable.ai",
"markdown": "# Markdown Content",
"provider": "web-scraper",
"metadata": {
"title": "Mendable | AI for CX and Sales",
"description": "AI for CX and Sales",
"language": null,
"sourceURL": "https://www.mendable.ai/"
}
}
]
}
```
## Using Python SDK
@ -226,31 +411,39 @@ pip install firecrawl-py
### Crawl a website
```python
from firecrawl import FirecrawlApp
from firecrawl.firecrawl import FirecrawlApp
app = FirecrawlApp(api_key="YOUR_API_KEY")
app = FirecrawlApp(api_key="fc-YOUR_API_KEY")
crawl_result = app.crawl_url('mendable.ai', {'crawlerOptions': {'excludes': ['blog/*']}})
# Scrape a website:
scrape_status = app.scrape_url(
'https://firecrawl.dev',
params={'formats': ['markdown', 'html']}
)
print(scrape_status)
# Get the markdown
for result in crawl_result:
print(result['markdown'])
```
### Scraping a URL
To scrape a single URL, use the `scrape_url` method. It takes the URL as a parameter and returns the scraped data as a dictionary.
```python
url = 'https://example.com'
scraped_data = app.scrape_url(url)
# Crawl a website:
crawl_status = app.crawl_url(
'https://firecrawl.dev',
params={
'limit': 100,
'scrapeOptions': {'formats': ['markdown', 'html']}
},
poll_interval=30
)
print(crawl_status)
```
### Extracting structured data from a URL
With LLM extraction, you can easily extract structured data from any URL. We support pydanti schemas to make it easier for you too. Here is how you to use it:
With LLM extraction, you can easily extract structured data from any URL. We support pydantic schemas to make it easier for you too. Here is how you to use it:
```python
from firecrawl.firecrawl import FirecrawlApp
app = FirecrawlApp(api_key="fc-YOUR_API_KEY")
class ArticleSchema(BaseModel):
title: str
points: int
@ -261,24 +454,12 @@ class TopArticlesSchema(BaseModel):
top: List[ArticleSchema] = Field(..., max_items=5, description="Top 5 stories")
data = app.scrape_url('https://news.ycombinator.com', {
'extractorOptions': {
'extractionSchema': TopArticlesSchema.model_json_schema(),
'mode': 'llm-extraction'
},
'pageOptions':{
'onlyMainContent': True
'formats': ['extract'],
'extract': {
'schema': TopArticlesSchema.model_json_schema()
}
})
print(data["llm_extraction"])
```
### Search for a query
Performs a web search, retrieve the top results, extract data from each page, and returns their markdown.
```python
query = 'What is Mendable?'
search_result = app.search(query)
print(data["extract"])
```
## Using the Node SDK
@ -296,64 +477,34 @@ npm install @mendable/firecrawl-js
1. Get an API key from [firecrawl.dev](https://firecrawl.dev)
2. Set the API key as an environment variable named `FIRECRAWL_API_KEY` or pass it as a parameter to the `FirecrawlApp` class.
### Scraping a URL
To scrape a single URL with error handling, use the `scrapeUrl` method. It takes the URL as a parameter and returns the scraped data as a dictionary.
```js
try {
const url = 'https://example.com';
const scrapedData = await app.scrapeUrl(url);
console.log(scrapedData);
import FirecrawlApp, { CrawlParams, CrawlStatusResponse } from '@mendable/firecrawl-js';
} catch (error) {
console.error(
'Error occurred while scraping:',
error.message
);
const app = new FirecrawlApp({apiKey: "fc-YOUR_API_KEY"});
// Scrape a website
const scrapeResponse = await app.scrapeUrl('https://firecrawl.dev', {
formats: ['markdown', 'html'],
});
if (scrapeResponse) {
console.log(scrapeResponse)
}
// Crawl a website
const crawlResponse = await app.crawlUrl('https://firecrawl.dev', {
limit: 100,
scrapeOptions: {
formats: ['markdown', 'html'],
}
} satisfies CrawlParams, true, 30) satisfies CrawlStatusResponse;
if (crawlResponse) {
console.log(crawlResponse)
}
```
### Crawling a Website
To crawl a website with error handling, use the `crawlUrl` method. It takes the starting URL and optional parameters as arguments. The `params` argument allows you to specify additional options for the crawl job, such as the maximum number of pages to crawl, allowed domains, and the output format.
```js
const crawlUrl = 'https://example.com';
const params = {
crawlerOptions: {
excludes: ['blog/'],
includes: [], // leave empty for all pages
limit: 1000,
},
pageOptions: {
onlyMainContent: true
}
};
const waitUntilDone = true;
const timeout = 5;
const crawlResult = await app.crawlUrl(
crawlUrl,
params,
waitUntilDone,
timeout
);
```
### Checking Crawl Status
To check the status of a crawl job with error handling, use the `checkCrawlStatus` method. It takes the job ID as a parameter and returns the current status of the crawl job.
```js
const status = await app.checkCrawlStatus(jobId);
console.log(status);
```
### Extracting structured data from a URL
With LLM extraction, you can easily extract structured data from any URL. We support zod schema to make it easier for you too. Here is how you to use it:
@ -363,7 +514,7 @@ import FirecrawlApp from "@mendable/firecrawl-js";
import { z } from "zod";
const app = new FirecrawlApp({
apiKey: "fc-YOUR_API_KEY",
apiKey: "fc-YOUR_API_KEY"
});
// Define schema to extract contents into
@ -388,22 +539,44 @@ const scrapeResult = await app.scrapeUrl("https://news.ycombinator.com", {
console.log(scrapeResult.data["llm_extraction"]);
```
### Search for a query
## Open Source vs Cloud Offering
With the `search` method, you can search for a query in a search engine and get the top results along with the page content for each result. The method takes the query as a parameter and returns the search results.
Firecrawl is open source available under the AGPL-3.0 license.
```js
const query = 'what is mendable?';
const searchResults = await app.search(query, {
pageOptions: {
fetchPageContent: true // Fetch the page content for each search result
}
});
To deliver the best possible product, we offer a hosted version of Firecrawl alongside our open-source offering. The cloud solution allows us to continuously innovate and maintain a high-quality, sustainable service for all users.
Firecrawl Cloud is available at [firecrawl.dev](https://firecrawl.dev) and offers a range of features that are not available in the open source version:
![Open Source vs Cloud Offering](https://raw.githubusercontent.com/mendableai/firecrawl/main/img/open-source-cloud.png)
```
## Contributing
We love contributions! Please read our [contributing guide](CONTRIBUTING.md) before submitting a pull request.
We love contributions! Please read our [contributing guide](CONTRIBUTING.md) before submitting a pull request. If you'd like to self-host, refer to the [self-hosting guide](SELF_HOST.md).
*It is the sole responsibility of the end users to respect websites' policies when scraping, searching and crawling with Firecrawl. Users are advised to adhere to the applicable privacy policies and terms of use of the websites prior to initiating any scraping activities. By default, Firecrawl respects the directives specified in the websites' robots.txt files when crawling. By utilizing Firecrawl, you expressly agree to comply with these conditions.*
_It is the sole responsibility of the end users to respect websites' policies when scraping, searching and crawling with Firecrawl. Users are advised to adhere to the applicable privacy policies and terms of use of the websites prior to initiating any scraping activities. By default, Firecrawl respects the directives specified in the websites' robots.txt files when crawling. By utilizing Firecrawl, you expressly agree to comply with these conditions._
## Contributors
<a href="https://github.com/mendableai/firecrawl/graphs/contributors">
<img alt="contributors" src="https://contrib.rocks/image?repo=mendableai/firecrawl"/>
</a>
## License Disclaimer
This project is primarily licensed under the GNU Affero General Public License v3.0 (AGPL-3.0), as specified in the LICENSE file in the root directory of this repository. However, certain components of this project are licensed under the MIT License. Refer to the LICENSE files in these specific directories for details.
Please note:
- The AGPL-3.0 license applies to all parts of the project unless otherwise specified.
- The SDKs and some UI components are licensed under the MIT License. Refer to the LICENSE files in these specific directories for details.
- When using or contributing to this project, ensure you comply with the appropriate license terms for the specific component you are working with.
For more details on the licensing of specific components, please refer to the LICENSE files in the respective directories or contact the project maintainers.
<p align="right" style="font-size: 14px; color: #555; margin-top: 20px;">
<a href="#readme-top" style="text-decoration: none; color: #007bff; font-weight: bold;">
↑ Back to Top ↑
</a>
</p>

189
SELF_HOST.md
View File

@ -1,34 +1,179 @@
# Self-hosting Firecrawl
*We're currently working on a more in-depth guide on how to self-host, but in the meantime, here is a simplified version.*
Refer to [CONTRIBUTING.md](https://github.com/mendableai/firecrawl/blob/main/CONTRIBUTING.md) for instructions on how to run it locally.
#### Contributor?
## Getting Started
Welcome to [Firecrawl](https://firecrawl.dev) 🔥! Here are some instructions on how to get the project locally so you can run it on your own and contribute.
First, clone this repository and copy the example env file from api folder `.env.example` to `.env`.
```bash
git clone https://github.com/mendableai/firecrawl.git
cd firecrawl
cp ./apps/api/.env.example ./.env
If you're contributing, note that the process is similar to other open-source repos, i.e., fork Firecrawl, make changes, run tests, PR.
If you have any questions or would like help getting on board, join our Discord community [here](https://discord.gg/gSmWdAkdwd) for more information or submit an issue on Github [here](https://github.com/mendableai/firecrawl/issues/new/choose)!
## Why?
Self-hosting Firecrawl is particularly beneficial for organizations with stringent security policies that require data to remain within controlled environments. Here are some key reasons to consider self-hosting:
- **Enhanced Security and Compliance:** By self-hosting, you ensure that all data handling and processing complies with internal and external regulations, keeping sensitive information within your secure infrastructure. Note that Firecrawl is a Mendable product and relies on SOC2 Type2 certification, which means that the platform adheres to high industry standards for managing data security.
- **Customizable Services:** Self-hosting allows you to tailor the services, such as the Playwright service, to meet specific needs or handle particular use cases that may not be supported by the standard cloud offering.
- **Learning and Community Contribution:** By setting up and maintaining your own instance, you gain a deeper understanding of how Firecrawl works, which can also lead to more meaningful contributions to the project.
### Considerations
However, there are some limitations and additional responsibilities to be aware of:
1. **Limited Access to Fire-engine:** Currently, self-hosted instances of Firecrawl do not have access to Fire-engine, which includes advanced features for handling IP blocks, robot detection mechanisms, and more. This means that while you can manage basic scraping tasks, more complex scenarios might require additional configuration or might not be supported.
2. **Manual Configuration Required:** If you need to use scraping methods beyond the basic fetch and Playwright options, you will need to manually configure these in the `.env` file. This requires a deeper understanding of the technologies and might involve more setup time.
Self-hosting Firecrawl is ideal for those who need full control over their scraping and data processing environments but comes with the trade-off of additional maintenance and configuration efforts.
## Steps
1. First, start by installing the dependencies
- Docker [instructions](https://docs.docker.com/get-docker/)
2. Set environment variables
Create an `.env` in the root directory you can copy over the template in `apps/api/.env.example`
To start, we won't set up authentication or any optional subservices (pdf parsing, JS blocking support, AI features)
`.env:`
```
For running the simplest version of FireCrawl, edit the `USE_DB_AUTHENTICATION` on `.env` to not use the database authentication.
```yml
USE_DB_AUTHENTICATION=false
```
Update the Redis URL in the .env file to align with the Docker configuration:
```yml
# ===== Required ENVS ======
NUM_WORKERS_PER_QUEUE=8
PORT=3002
HOST=0.0.0.0
REDIS_URL=redis://redis:6379
REDIS_RATE_LIMIT_URL=redis://redis:6379
## To turn on DB authentication, you need to set up Supabase.
USE_DB_AUTHENTICATION=false
# ===== Optional ENVS ======
# Supabase Setup (used to support DB authentication, advanced logging, etc.)
SUPABASE_ANON_TOKEN=
SUPABASE_URL=
SUPABASE_SERVICE_TOKEN=
# Other Optionals
TEST_API_KEY= # use if you've set up authentication and want to test with a real API key
SCRAPING_BEE_API_KEY= # use if you'd like to use as a fallback scraper
OPENAI_API_KEY= # add for LLM-dependent features (e.g., image alt generation)
BULL_AUTH_KEY= @
LOGTAIL_KEY= # Use if you're configuring basic logging with logtail
PLAYWRIGHT_MICROSERVICE_URL= # set if you'd like to run a playwright fallback
LLAMAPARSE_API_KEY= #Set if you have a llamaparse key you'd like to use to parse pdfs
SLACK_WEBHOOK_URL= # set if you'd like to send slack server health status messages
POSTHOG_API_KEY= # set if you'd like to send posthog events like job logs
POSTHOG_HOST= # set if you'd like to send posthog events like job logs
```
Once that's complete, you can simply run the following commands to get started:
```bash
docker compose up
```
3. *(Optional) Running with TypeScript Playwright Service*
* Update the `docker-compose.yml` file to change the Playwright service:
```plaintext
build: apps/playwright-service
```
TO
```plaintext
build: apps/playwright-service-ts
```
* Set the `PLAYWRIGHT_MICROSERVICE_URL` in your `.env` file:
```plaintext
PLAYWRIGHT_MICROSERVICE_URL=http://localhost:3000/scrape
```
* Don't forget to set the proxy server in your `.env` file as needed.
4. Build and run the Docker containers:
```bash
docker compose build
docker compose up
```
This will run a local instance of Firecrawl which can be accessed at `http://localhost:3002`.
# Install Firecrawl on a Kubernetes Cluster (Simple Version)
Read the [examples/k8n/README.md](examples/k8n/README.md) for instructions on how to install Firecrawl on a Kubernetes Cluster.
You should be able to see the Bull Queue Manager UI on `http://localhost:3002/admin/@/queues`.
5. *(Optional)* Test the API
If you’d like to test the crawl endpoint, you can run this:
```bash
curl -X POST http://localhost:3002/v1/crawl \
-H 'Content-Type: application/json' \
-d '{
"url": "https://mendable.ai"
}'
```
## Troubleshooting
This section provides solutions to common issues you might encounter while setting up or running your self-hosted instance of Firecrawl.
### Supabase client is not configured
**Symptom:**
```bash
[YYYY-MM-DDTHH:MM:SS.SSSz]ERROR - Attempted to access Supabase client when it's not configured.
[YYYY-MM-DDTHH:MM:SS.SSSz]ERROR - Error inserting scrape event: Error: Supabase client is not configured.
```
**Explanation:**
This error occurs because the Supabase client setup is not completed. You should be able to scrape and crawl with no problems. Right now it's not possible to configure Supabase in self-hosted instances.
### You're bypassing authentication
**Symptom:**
```bash
[YYYY-MM-DDTHH:MM:SS.SSSz]WARN - You're bypassing authentication
```
**Explanation:**
This error occurs because the Supabase client setup is not completed. You should be able to scrape and crawl with no problems. Right now it's not possible to configure Supabase in self-hosted instances.
### Docker containers fail to start
**Symptom:**
Docker containers exit unexpectedly or fail to start.
**Solution:**
Check the Docker logs for any error messages using the command:
```bash
docker logs [container_name]
```
- Ensure all required environment variables are set correctly in the .env file.
- Verify that all Docker services defined in docker-compose.yml are correctly configured and the necessary images are available.
### Connection issues with Redis
**Symptom:**
Errors related to connecting to Redis, such as timeouts or "Connection refused".
**Solution:**
- Ensure that the Redis service is up and running in your Docker environment.
- Verify that the REDIS_URL and REDIS_RATE_LIMIT_URL in your .env file point to the correct Redis instance, ensure that it points to the same URL in the `docker-compose.yaml` file (`redis://redis:6379`)
- Check network settings and firewall rules that may block the connection to the Redis port.
### API endpoint does not respond
**Symptom:**
API requests to the Firecrawl instance timeout or return no response.
**Solution:**
- Ensure that the Firecrawl service is running by checking the Docker container status.
- Verify that the PORT and HOST settings in your .env file are correct and that no other service is using the same port.
- Check the network configuration to ensure that the host is accessible from the client making the API request.
By addressing these common issues, you can ensure a smoother setup and operation of your self-hosted Firecrawl instance.
## Install Firecrawl on a Kubernetes Cluster (Simple Version)
Read the [examples/kubernetes/cluster-install/README.md](https://github.com/mendableai/firecrawl/blob/main/examples/kubernetes/cluster-install/README.md) for instructions on how to install Firecrawl on a Kubernetes Cluster.

55
apps/api/.env.example
View File

@ -2,7 +2,8 @@
NUM_WORKERS_PER_QUEUE=8
PORT=3002
HOST=0.0.0.0
REDIS_URL=redis://localhost:6379
REDIS_URL=redis://redis:6379 #for self-hosting using docker, use redis://redis:6379. For running locally, use redis://localhost:6379
REDIS_RATE_LIMIT_URL=redis://redis:6379 #for self-hosting using docker, use redis://redis:6379. For running locally, use redis://localhost:6379
PLAYWRIGHT_MICROSERVICE_URL=http://playwright-service:3000/html
## To turn on DB authentication, you need to set up supabase.
@ -10,24 +11,38 @@ USE_DB_AUTHENTICATION=true
# ===== Optional ENVS ======
# SearchApi key. Head to https://searchapi.com/ to get your API key
SEARCHAPI_API_KEY=
# SearchApi engine, defaults to google. Available options: google, bing, baidu, google_news, etc. Head to https://searchapi.com/ to explore more engines
SEARCHAPI_ENGINE=
# Supabase Setup (used to support DB authentication, advanced logging, etc.)
SUPABASE_ANON_TOKEN=
SUPABASE_URL=
SUPABASE_SERVICE_TOKEN=
# Other Optionals
TEST_API_KEY= # use if you've set up authentication and want to test with a real API key
RATE_LIMIT_TEST_API_KEY_SCRAPE= # set if you'd like to test the scraping rate limit
RATE_LIMIT_TEST_API_KEY_CRAWL= # set if you'd like to test the crawling rate limit
SCRAPING_BEE_API_KEY= #Set if you'd like to use scraping Be to handle JS blocking
OPENAI_API_KEY= # add for LLM dependednt features (image alt generation, etc.)
BULL_AUTH_KEY= @
LOGTAIL_KEY= # Use if you're configuring basic logging with logtail
LLAMAPARSE_API_KEY= #Set if you have a llamaparse key you'd like to use to parse pdfs
SERPER_API_KEY= #Set if you have a serper key you'd like to use as a search api
SLACK_WEBHOOK_URL= # set if you'd like to send slack server health status messages
POSTHOG_API_KEY= # set if you'd like to send posthog events like job logs
POSTHOG_HOST= # set if you'd like to send posthog events like job logs
# use if you've set up authentication and want to test with a real API key
TEST_API_KEY=
# set if you'd like to test the scraping rate limit
RATE_LIMIT_TEST_API_KEY_SCRAPE=
# set if you'd like to test the crawling rate limit
RATE_LIMIT_TEST_API_KEY_CRAWL=
# set if you'd like to use scraping Be to handle JS blocking
SCRAPING_BEE_API_KEY=
# add for LLM dependednt features (image alt generation, etc.)
OPENAI_API_KEY=
BULL_AUTH_KEY=@
# use if you're configuring basic logging with logtail
LOGTAIL_KEY=
# set if you have a llamaparse key you'd like to use to parse pdfs
LLAMAPARSE_API_KEY=
# set if you'd like to send slack server health status messages
SLACK_WEBHOOK_URL=
# set if you'd like to send posthog events like job logs
POSTHOG_API_KEY=
# set if you'd like to send posthog events like job logs
POSTHOG_HOST=
STRIPE_PRICE_ID_STANDARD=
STRIPE_PRICE_ID_SCALE=
@ -42,7 +57,8 @@ STRIPE_PRICE_ID_GROWTH_YEARLY=
HYPERDX_API_KEY=
HDX_NODE_BETA_MODE=1
FIRE_ENGINE_BETA_URL= # set if you'd like to use the fire engine closed beta
# set if you'd like to use the fire engine closed beta
FIRE_ENGINE_BETA_URL=
# Proxy Settings for Playwright (Alternative you can can use a proxy service like oxylabs, which rotates IPs for you on every request)
PROXY_SERVER=
@ -56,3 +72,14 @@ SELF_HOSTED_WEBHOOK_URL=
# Resend API Key for transactional emails
RESEND_API_KEY=
# LOGGING_LEVEL determines the verbosity of logs that the system will output.
# Available levels are:
# NONE - No logs will be output.
# ERROR - For logging error messages that indicate a failure in a specific operation.
# WARN - For logging potentially harmful situations that are not necessarily errors.
# INFO - For logging informational messages that highlight the progress of the application.
# DEBUG - For logging detailed information on the flow through the system, primarily used for debugging.
# TRACE - For logging more detailed information than the DEBUG level.
# Set LOGGING_LEVEL to one of the above options to control logging output.
LOGGING_LEVEL=INFO

3
apps/api/.env.local
View File

@ -5,10 +5,11 @@ SUPABASE_ANON_TOKEN=
SUPABASE_URL=
SUPABASE_SERVICE_TOKEN=
REDIS_URL=
REDIS_RATE_LIMIT_URL=
SCRAPING_BEE_API_KEY=
OPENAI_API_KEY=
ANTHROPIC_API_KEY=
BULL_AUTH_KEY=
LOGTAIL_KEY=
PLAYWRIGHT_MICROSERVICE_URL=
SEARCHAPI_API_KEY=

5
apps/api/.gitignore vendored
View File

@ -4,3 +4,8 @@
*.csv
dump.rdb
/mongo-data
/.next/
.rdb
.sentryclirc

26
apps/api/Dockerfile
View File

@ -12,25 +12,31 @@ RUN --mount=type=cache,id=pnpm,target=/pnpm/store pnpm install --prod --frozen-l
FROM base AS build
RUN --mount=type=cache,id=pnpm,target=/pnpm/store pnpm install --frozen-lockfile
RUN apt-get update -qq && apt-get install -y ca-certificates && update-ca-certificates
RUN pnpm install
RUN pnpm run build
RUN --mount=type=secret,id=SENTRY_AUTH_TOKEN \
bash -c 'export SENTRY_AUTH_TOKEN="$(cat /run/secrets/SENTRY_AUTH_TOKEN)"; if [ -z $SENTRY_AUTH_TOKEN ]; then pnpm run build:nosentry; else pnpm run build; fi'
# Install packages needed for deployment
# Install Go
FROM golang:1.19 AS go-base
COPY sharedLibs/go-html-to-md /app/sharedLibs/go-html-to-md
# Install Go dependencies and build parser lib
RUN cd /app/sharedLibs/go-html-to-md && \
go mod tidy && \
go build -o html-to-markdown.so -buildmode=c-shared html-to-markdown.go && \
chmod +x html-to-markdown.so
FROM base
RUN apt-get update -qq && \
apt-get install --no-install-recommends -y chromium chromium-sandbox && \
rm -rf /var/lib/apt/lists /var/cache/apt/archives
COPY --from=prod-deps /app/node_modules /app/node_modules
COPY --from=build /app /app
COPY --from=go-base /app/sharedLibs/go-html-to-md/html-to-markdown.so /app/sharedLibs/go-html-to-md/html-to-markdown.so
# Start the server by default, this can be overwritten at runtime
EXPOSE 8080
ENV PUPPETEER_EXECUTABLE_PATH="/usr/bin/chromium"
CMD [ "pnpm", "run", "start:production" ]
CMD [ "pnpm", "run", "worker:production" ]
# Make sure the entrypoint script has the correct line endings
RUN sed -i 's/\r$//' /app/docker-entrypoint.sh
ENTRYPOINT "/app/docker-entrypoint.sh"

19
apps/api/docker-entrypoint.sh Executable file
View File

@ -0,0 +1,19 @@
#!/bin/bash -e
if [ $UID -eq 0 ]; then
ulimit -n 65535
echo "NEW ULIMIT: $(ulimit -n)"
else
echo ENTRYPOINT DID NOT RUN AS ROOT
fi
if [ $FLY_PROCESS_GROUP = "app" ]; then
echo "RUNNING app"
node --max-old-space-size=8192 dist/src/index.js
elif [ $FLY_PROCESS_GROUP = "worker" ]; then
echo "RUNNING worker"
node --max-old-space-size=8192 dist/src/services/queue-worker.js
else
echo "NO FLY PROCESS GROUP"
node --max-old-space-size=8192 dist/src/index.js
fi

66
apps/api/fly.staging.toml Normal file
View File

@ -0,0 +1,66 @@
# fly.toml app configuration file generated for firecrawl-scraper-js on 2024-04-07T21:09:59-03:00
#
# See https://fly.io/docs/reference/configuration/ for information about how to use this file.
#
app = 'staging-firecrawl-scraper-js'
primary_region = 'mia'
kill_signal = 'SIGINT'
kill_timeout = '30s'
[build]
[processes]
app = 'node dist/src/index.js'
worker = 'node dist/src/services/queue-worker.js'
[http_service]
internal_port = 8080
force_https = true
auto_stop_machines = true
auto_start_machines = true
min_machines_running = 2
processes = ['app']
[http_service.concurrency]
type = "requests"
# hard_limit = 100
soft_limit = 100
[[http_service.checks]]
grace_period = "10s"
interval = "30s"
method = "GET"
timeout = "5s"
path = "/"
[[services]]
protocol = 'tcp'
internal_port = 8080
processes = ['worker']
[[services.ports]]
port = 80
handlers = ['http']
force_https = true
[[services.ports]]
port = 443
handlers = ['tls', 'http']
[services.concurrency]
type = 'connections'
# hard_limit = 25
soft_limit = 100
[[vm]]
size = 'performance-2x'
processes = ['app','worker']
memory = 8192

16
apps/api/fly.toml
View File

@ -4,15 +4,15 @@
#
app = 'firecrawl-scraper-js'
primary_region = 'mia'
primary_region = 'iad'
kill_signal = 'SIGINT'
kill_timeout = '5s'
kill_timeout = '30s'
[build]
[processes]
app = 'npm run start:production'
worker = 'npm run worker:production'
app = 'node --max-old-space-size=8192 dist/src/index.js'
worker = 'node --max-old-space-size=8192 dist/src/services/queue-worker.js'
[http_service]
internal_port = 8080
@ -24,8 +24,8 @@ kill_timeout = '5s'
[http_service.concurrency]
type = "requests"
hard_limit = 100
soft_limit = 50
# hard_limit = 200
soft_limit = 200
[[http_service.checks]]
grace_period = "20s"
@ -50,8 +50,8 @@ kill_timeout = '5s'
[services.concurrency]
type = 'connections'
hard_limit = 30
soft_limit = 12
# hard_limit = 30
soft_limit = 200
[[vm]]
size = 'performance-4x'

924
apps/api/openapi-v0.json Normal file
View File

@ -0,0 +1,924 @@
{
"openapi": "3.0.0",
"info": {
"title": "Firecrawl API",
"version": "0.0.0",
"description": "API for interacting with Firecrawl services to perform web scraping and crawling tasks.",
"contact": {
"name": "Firecrawl Support",
"url": "https://firecrawl.dev/support",
"email": "support@firecrawl.dev"
}
},
"servers": [
{
"url": "https://api.firecrawl.dev/v0"
}
],
"paths": {
"/scrape": {
"post": {
"summary": "Scrape a single URL and optionally extract information using an LLM",
"operationId": "scrapeAndExtractFromUrl",
"tags": ["Scraping"],
"security": [
{
"bearerAuth": []
}
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"type": "object",
"properties": {
"url": {
"type": "string",
"format": "uri",
"description": "The URL to scrape"
},
"pageOptions": {
"type": "object",
"properties": {
"headers": {
"type": "object",
"description": "Headers to send with the request. Can be used to send cookies, user-agent, etc."
},
"includeHtml": {
"type": "boolean",
"description": "Include the HTML version of the content on page. Will output a html key in the response.",
"default": false
},
"includeRawHtml": {
"type": "boolean",
"description": "Include the raw HTML content of the page. Will output a rawHtml key in the response.",
"default": false
},
"onlyIncludeTags": {
"type": "array",
"items": {
"type": "string"
},
"description": "Only include tags, classes and ids from the page in the final output. Use comma separated values. Example: 'script, .ad, #footer'"
},
"onlyMainContent": {
"type": "boolean",
"description": "Only return the main content of the page excluding headers, navs, footers, etc.",
"default": false
},
"removeTags": {
"type": "array",
"items": {
"type": "string"
},
"description": "Tags, classes and ids to remove from the page. Use comma separated values. Example: 'script, .ad, #footer'"
},
"replaceAllPathsWithAbsolutePaths": {
"type": "boolean",
"description": "Replace all relative paths with absolute paths for images and links",
"default": false
},
"screenshot": {
"type": "boolean",
"description": "Include a screenshot of the top of the page that you are scraping.",
"default": false
},
"fullPageScreenshot": {
"type": "boolean",
"description": "Include a full page screenshot of the page that you are scraping.",
"default": false
},
"waitFor": {
"type": "integer",
"description": "Wait x amount of milliseconds for the page to load to fetch content",
"default": 0
}
}
},
"extractorOptions": {
"type": "object",
"description": "Options for extraction of structured information from the page content. Note: LLM-based extraction is not performed by default and only occurs when explicitly configured. The 'markdown' mode simply returns the scraped markdown and is the default mode for scraping.",
"default": {},
"properties": {
"mode": {
"type": "string",
"enum": ["markdown", "llm-extraction", "llm-extraction-from-raw-html", "llm-extraction-from-markdown"],
"description": "The extraction mode to use. 'markdown': Returns the scraped markdown content, does not perform LLM extraction. 'llm-extraction': Extracts information from the cleaned and parsed content using LLM. 'llm-extraction-from-raw-html': Extracts information directly from the raw HTML using LLM. 'llm-extraction-from-markdown': Extracts information from the markdown content using LLM."
},
"extractionPrompt": {
"type": "string",
"description": "A prompt describing what information to extract from the page, applicable for LLM extraction modes."
},
"extractionSchema": {
"type": "object",
"additionalProperties": true,
"description": "The schema for the data to be extracted, required only for LLM extraction modes.",
"required": [
"company_mission",
"supports_sso",
"is_open_source"
]
}
}
},
"timeout": {
"type": "integer",
"description": "Timeout in milliseconds for the request",
"default": 30000
}
},
"required": ["url"]
}
}
}
},
"responses": {
"200": {
"description": "Successful response",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/ScrapeResponse"
}
}
}
},
"402": {
"description": "Payment required",
"content": {
"application/json": {
"schema": {
"type": "object",
"properties": {
"error": {
"type": "string",
"example": "Payment required to access this resource."
}
}
}
}
}
},
"429": {
"description": "Too many requests",
"content": {
"application/json": {
"schema": {
"type": "object",
"properties": {
"error": {
"type": "string",
"example": "Request rate limit exceeded. Please wait and try again later."
}
}
}
}
}
},
"500": {
"description": "Server error",
"content": {
"application/json": {
"schema": {
"type": "object",
"properties": {
"error": {
"type": "string",
"example": "An unexpected error occurred on the server."
}
}
}
}
}
}
}
}
},
"/crawl": {
"post": {
"summary": "Crawl multiple URLs based on options",
"operationId": "crawlUrls",
"tags": ["Crawling"],
"security": [
{
"bearerAuth": []
}
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"type": "object",
"properties": {
"url": {
"type": "string",
"format": "uri",
"description": "The base URL to start crawling from"
},
"crawlerOptions": {
"type": "object",
"properties": {
"includes": {
"type": "array",
"items": {
"type": "string"
},
"description": "URL patterns to include"
},
"excludes": {
"type": "array",
"items": {
"type": "string"
},
"description": "URL patterns to exclude"
},
"generateImgAltText": {
"type": "boolean",
"description": "Generate alt text for images using LLMs (must have a paid plan)",
"default": false
},
"returnOnlyUrls": {
"type": "boolean",
"description": "If true, returns only the URLs as a list on the crawl status. Attention: the return response will be a list of URLs inside the data, not a list of documents.",
"default": false
},
"maxDepth": {
"type": "integer",
"description": "Maximum depth to crawl relative to the entered URL. A maxDepth of 0 scrapes only the entered URL. A maxDepth of 1 scrapes the entered URL and all pages one level deep. A maxDepth of 2 scrapes the entered URL and all pages up to two levels deep. Higher values follow the same pattern."
},
"mode": {
"type": "string",
"enum": ["default", "fast"],
"description": "The crawling mode to use. Fast mode crawls 4x faster websites without sitemap, but may not be as accurate and shouldn't be used in heavy js-rendered websites.",
"default": "default"
},
"ignoreSitemap": {
"type": "boolean",
"description": "Ignore the website sitemap when crawling",
"default": false
},
"limit": {
"type": "integer",
"description": "Maximum number of pages to crawl",
"default": 10000
},
"allowBackwardCrawling": {
"type": "boolean",
"description": "Enables the crawler to navigate from a specific URL to previously linked pages. For instance, from 'example.com/product/123' back to 'example.com/product'",
"default": false
},
"allowExternalContentLinks": {
"type": "boolean",
"description": "Allows the crawler to follow links to external websites.",
"default": false
}
}
},
"pageOptions": {
"type": "object",
"properties": {
"headers": {
"type": "object",
"description": "Headers to send with the request. Can be used to send cookies, user-agent, etc."
},
"includeHtml": {
"type": "boolean",
"description": "Include the HTML version of the content on page. Will output a html key in the response.",
"default": false
},
"includeRawHtml": {
"type": "boolean",
"description": "Include the raw HTML content of the page. Will output a rawHtml key in the response.",
"default": false
},
"onlyIncludeTags": {
"type": "array",
"items": {
"type": "string"
},
"description": "Only include tags, classes and ids from the page in the final output. Use comma separated values. Example: 'script, .ad, #footer'"
},
"onlyMainContent": {
"type": "boolean",
"description": "Only return the main content of the page excluding headers, navs, footers, etc.",
"default": false
},
"removeTags": {
"type": "array",
"items": {
"type": "string"
},
"description": "Tags, classes and ids to remove from the page. Use comma separated values. Example: 'script, .ad, #footer'"
},
"replaceAllPathsWithAbsolutePaths": {
"type": "boolean",
"description": "Replace all relative paths with absolute paths for images and links",
"default": false
},
"screenshot": {
"type": "boolean",
"description": "Include a screenshot of the top of the page that you are scraping.",
"default": false
},
"fullPageScreenshot": {
"type": "boolean",
"description": "Include a full page screenshot of the page that you are scraping.",
"default": false
},
"waitFor": {
"type": "integer",
"description": "Wait x amount of milliseconds for the page to load to fetch content",
"default": 0
}
}
}
},
"required": ["url"]
}
}
}
},
"responses": {
"200": {
"description": "Successful response",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/CrawlResponse"
}
}
}
},
"402": {
"description": "Payment required",
"content": {
"application/json": {
"schema": {
"type": "object",
"properties": {
"error": {
"type": "string",
"example": "Payment required to access this resource."
}
}
}
}
}
},
"429": {
"description": "Too many requests",
"content": {
"application/json": {
"schema": {
"type": "object",
"properties": {
"error": {
"type": "string",
"example": "Request rate limit exceeded. Please wait and try again later."
}
}
}
}
}
},
"500": {
"description": "Server error",
"content": {
"application/json": {
"schema": {
"type": "object",
"properties": {
"error": {
"type": "string",
"example": "An unexpected error occurred on the server."
}
}
}
}
}
}
}
}
},
"/search": {
"post": {
"summary": "Search for a keyword in Google, returns top page results with markdown content for each page",
"operationId": "searchGoogle",
"tags": ["Search"],
"security": [
{
"bearerAuth": []
}
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"type": "object",
"properties": {
"query": {
"type": "string",
"format": "uri",
"description": "The query to search for"
},
"pageOptions": {
"type": "object",
"properties": {
"onlyMainContent": {
"type": "boolean",
"description": "Only return the main content of the page excluding headers, navs, footers, etc.",
"default": false
},
"fetchPageContent": {
"type": "boolean",
"description": "Fetch the content of each page. If false, defaults to a basic fast serp API.",
"default": true
},
"includeHtml": {
"type": "boolean",
"description": "Include the HTML version of the content on page. Will output a html key in the response.",
"default": false
},
"includeRawHtml": {
"type": "boolean",
"description": "Include the raw HTML content of the page. Will output a rawHtml key in the response.",
"default": false
}
}
},
"searchOptions": {
"type": "object",
"properties": {
"limit": {
"type": "integer",
"description": "Maximum number of results. Max is 20 during beta."
}
}
}
},
"required": ["query"]
}
}
}
},
"responses": {
"200": {
"description": "Successful response",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/SearchResponse"
}
}
}
},
"402": {
"description": "Payment required",
"content": {
"application/json": {
"schema": {
"type": "object",
"properties": {
"error": {
"type": "string",
"example": "Payment required to access this resource."
}
}
}
}
}
},
"429": {
"description": "Too many requests",
"content": {
"application/json": {
"schema": {
"type": "object",
"properties": {
"error": {
"type": "string",
"example": "Request rate limit exceeded. Please wait and try again later."
}
}
}
}
}
},
"500": {
"description": "Server error",
"content": {
"application/json": {
"schema": {
"type": "object",
"properties": {
"error": {
"type": "string",
"example": "An unexpected error occurred on the server."
}
}
}
}
}
}
}
}
},
"/crawl/status/{jobId}": {
"get": {
"tags": ["Crawl"],
"summary": "Get the status of a crawl job",
"operationId": "getCrawlStatus",
"security": [
{
"bearerAuth": []
}
],
"parameters": [
{
"name": "jobId",
"in": "path",
"description": "ID of the crawl job",
"required": true,
"schema": {
"type": "string"
}
}
],
"responses": {
"200": {
"description": "Successful response",
"content": {
"application/json": {
"schema": {
"type": "object",
"properties": {
"status": {
"type": "string",
"description": "Status of the job (completed, active, failed, paused)"
},
"current": {
"type": "integer",
"description": "Current page number"
},
"total": {
"type": "integer",
"description": "Total number of pages"
},
"data": {
"type": "array",
"items": {
"$ref": "#/components/schemas/CrawlStatusResponseObj"
},
"description": "Data returned from the job (null when it is in progress)"
},
"partial_data": {
"type": "array",
"items": {
"$ref": "#/components/schemas/CrawlStatusResponseObj"
},
"description": "Partial documents returned as it is being crawled (streaming). **This feature is currently in alpha - expect breaking changes** When a page is ready, it will append to the partial_data array, so there is no need to wait for the entire website to be crawled. When the crawl is done, partial_data will become empty and the result will be available in `data`. There is a max of 50 items in the array response. The oldest item (top of the array) will be removed when the new item is added to the array."
}
}
}
}
}
},
"402": {
"description": "Payment required",
"content": {
"application/json": {
"schema": {
"type": "object",
"properties": {
"error": {
"type": "string",
"example": "Payment required to access this resource."
}
}
}
}
}
},
"429": {
"description": "Too many requests",
"content": {
"application/json": {
"schema": {
"type": "object",
"properties": {
"error": {
"type": "string",
"example": "Request rate limit exceeded. Please wait and try again later."
}
}
}
}
}
},
"500": {
"description": "Server error",
"content": {
"application/json": {
"schema": {
"type": "object",
"properties": {
"error": {
"type": "string",
"example": "An unexpected error occurred on the server."
}
}
}
}
}
}
}
}
},
"/crawl/cancel/{jobId}": {
"delete": {
"tags": ["Crawl"],
"summary": "Cancel a crawl job",
"operationId": "cancelCrawlJob",
"security": [
{
"bearerAuth": []
}
],
"parameters": [
{
"name": "jobId",
"in": "path",
"description": "ID of the crawl job",
"required": true,
"schema": {
"type": "string"
}
}
],
"responses": {
"200": {
"description": "Successful response",
"content": {
"application/json": {
"schema": {
"type": "object",
"properties": {
"status": {
"type": "string",
"description": "Returns cancelled."
}
}
}
}
}
},
"402": {
"description": "Payment required",
"content": {
"application/json": {
"schema": {
"type": "object",
"properties": {
"error": {
"type": "string",
"example": "Payment required to access this resource."
}
}
}
}
}
},
"429": {
"description": "Too many requests",
"content": {
"application/json": {
"schema": {
"type": "object",
"properties": {
"error": {
"type": "string",
"example": "Request rate limit exceeded. Please wait and try again later."
}
}
}
}
}
},
"500": {
"description": "Server error",
"content": {
"application/json": {
"schema": {
"type": "object",
"properties": {
"error": {
"type": "string",
"example": "An unexpected error occurred on the server."
}
}
}
}
}
}
}
}
}
},
"components": {
"securitySchemes": {
"bearerAuth": {
"type": "http",
"scheme": "bearer"
}
},
"schemas": {
"ScrapeResponse": {
"type": "object",
"properties": {
"success": {
"type": "boolean"
},
"data": {
"type": "object",
"properties": {
"markdown": {
"type": "string"
},
"content": {
"type": "string"
},
"html": {
"type": "string",
"nullable": true,
"description": "HTML version of the content on page if `includeHtml` is true"
},
"rawHtml": {
"type": "string",
"nullable": true,
"description": "Raw HTML content of the page if `includeRawHtml` is true"
},
"metadata": {
"type": "object",
"properties": {
"title": {
"type": "string"
},
"description": {
"type": "string"
},
"language": {
"type": "string",
"nullable": true
},
"sourceURL": {
"type": "string",
"format": "uri"
},
"<any other metadata> ": {
"type": "string"
},
"pageStatusCode": {
"type": "integer",
"description": "The status code of the page"
},
"pageError": {
"type": "string",
"nullable": true,
"description": "The error message of the page"
}
}
},
"llm_extraction": {
"type": "object",
"description": "Displayed when using LLM Extraction. Extracted data from the page following the schema defined.",
"nullable": true
},
"warning": {
"type": "string",
"nullable": true,
"description": "Can be displayed when using LLM Extraction. Warning message will let you know any issues with the extraction."
}
}
}
}
},
"CrawlStatusResponseObj": {
"type": "object",
"properties": {
"markdown": {
"type": "string"
},
"content": {
"type": "string"
},
"html": {
"type": "string",
"nullable": true,
"description": "HTML version of the content on page if `includeHtml` is true"
},
"rawHtml": {
"type": "string",
"nullable": true,
"description": "Raw HTML content of the page if `includeRawHtml` is true"
},
"index": {
"type": "integer",
"description": "The number of the page that was crawled. This is useful for `partial_data` so you know which page the data is from."
},
"metadata": {
"type": "object",
"properties": {
"title": {
"type": "string"
},
"description": {
"type": "string"
},
"language": {
"type": "string",
"nullable": true
},
"sourceURL": {
"type": "string",
"format": "uri"
},
"<any other metadata> ": {
"type": "string"
},
"pageStatusCode": {
"type": "integer",
"description": "The status code of the page"
},
"pageError": {
"type": "string",
"nullable": true,
"description": "The error message of the page"
}
}
}
}
},
"SearchResponse": {
"type": "object",
"properties": {
"success": {
"type": "boolean"
},
"data": {
"type": "array",
"items": {
"type": "object",
"properties": {
"url": {
"type": "string"
},
"markdown": {
"type": "string"
},
"content": {
"type": "string"
},
"metadata": {
"type": "object",
"properties": {
"title": {
"type": "string"
},
"description": {
"type": "string"
},
"language": {
"type": "string",
"nullable": true
},
"sourceURL": {
"type": "string",
"format": "uri"
}
}
}
}
}
}
}
},
"CrawlResponse": {
"type": "object",
"properties": {
"jobId": {
"type": "string"
}
}
}
}
},
"security": [
{
"bearerAuth": []
}
]
}

530
apps/api/openapi.json
View File

@ -18,8 +18,8 @@
"paths": {
"/scrape": {
"post": {
"summary": "Scrape a single URL and optionally extract information using an LLM",
"operationId": "scrapeAndExtractFromUrl",
"summary": "Scrape a single URL",
"operationId": "scrape",
"tags": ["Scraping"],
"security": [
{
@ -38,71 +38,47 @@
"format": "uri",
"description": "The URL to scrape"
},
"pageOptions": {
"formats": {
"type": "array",
"items": {
"type": "string",
"enum": ["markdown", "html", "rawHtml", "links", "screenshot", "screenshot@fullPage"]
},
"description": "Specific formats to return.\n\n - markdown: The page in Markdown format.\n - html: The page's HTML, trimmed to include only meaningful content.\n - rawHtml: The page's original HTML.\n - links: The links on the page.\n - screenshot: A screenshot of the top of the page.\n - screenshot@fullPage: A screenshot of the full page. (overridden by screenshot if present)",
"default": ["markdown"]
},
"headers": {
"type": "object",
"properties": {
"onlyMainContent": {
"type": "boolean",
"description": "Only return the main content of the page excluding headers, navs, footers, etc.",
"default": false
"description": "Headers to send with the request. Can be used to send cookies, user-agent, etc."
},
"includeHtml": {
"type": "boolean",
"description": "Include the raw HTML content of the page. Will output a html key in the response.",
"default": false
"includeTags": {
"type": "array",
"items": {
"type": "string"
},
"screenshot": {
"type": "boolean",
"description": "Include a screenshot of the top of the page that you are scraping.",
"default": false
"description": "Only include tags, classes and ids from the page in the final output. Use comma separated values. Example: 'script, .ad, #footer'"
},
"waitFor": {
"type": "integer",
"description": "Wait x amount of milliseconds for the page to load to fetch content",
"default": 0
},
"removeTags": {
"excludeTags": {
"type": "array",
"items": {
"type": "string"
},
"description": "Tags, classes and ids to remove from the page. Use comma separated values. Example: 'script, .ad, #footer'"
},
"headers": {
"type": "object",
"description": "Headers to send with the request. Can be used to send cookies, user-agent, etc."
}
}
},
"extractorOptions": {
"type": "object",
"description": "Options for LLM-based extraction of structured information from the page content",
"properties": {
"mode": {
"type": "string",
"enum": ["llm-extraction"],
"description": "The extraction mode to use, currently supports 'llm-extraction'"
},
"extractionPrompt": {
"type": "string",
"description": "A prompt describing what information to extract from the page"
},
"extractionSchema": {
"type": "object",
"additionalProperties": true,
"description": "The schema for the data to be extracted",
"required": [
"company_mission",
"supports_sso",
"is_open_source"
]
}
}
"onlyMainContent": {
"type": "boolean",
"description": "Only return the main content of the page excluding headers, navs, footers, etc.",
"default": true
},
"timeout": {
"type": "integer",
"description": "Timeout in milliseconds for the request",
"default": 30000
},
"waitFor": {
"type": "integer",
"description": "Wait x amount of milliseconds for the page to load to fetch content",
"default": 0
}
},
"required": ["url"]
@ -122,13 +98,52 @@
}
},
"402": {
"description": "Payment required"
"description": "Payment required",
"content": {
"application/json": {
"schema": {
"type": "object",
"properties": {
"error": {
"type": "string",
"example": "Payment required to access this resource."
}
}
}
}
}
},
"429": {
"description": "Too many requests"
"description": "Too many requests",
"content": {
"application/json": {
"schema": {
"type": "object",
"properties": {
"error": {
"type": "string",
"example": "Request rate limit exceeded. Please wait and try again later."
}
}
}
}
}
},
"500": {
"description": "Server error"
"description": "Server error",
"content": {
"application/json": {
"schema": {
"type": "object",
"properties": {
"error": {
"type": "string",
"example": "An unexpected error occurred on the server."
}
}
}
}
}
}
}
}
@ -184,7 +199,7 @@
},
"maxDepth": {
"type": "integer",
"description": "Maximum depth to crawl. Depth 1 is the base URL, depth 2 is the base URL and its direct children, and so on."
"description": "Maximum depth to crawl relative to the entered URL. A maxDepth of 0 scrapes only the entered URL. A maxDepth of 1 scrapes the entered URL and all pages one level deep. A maxDepth of 2 scrapes the entered URL and all pages up to two levels deep. Higher values follow the same pattern."
},
"mode": {
"type": "string",
@ -204,7 +219,12 @@
},
"allowBackwardCrawling": {
"type": "boolean",
"description": "Allow backward crawling (crawl from the base URL to the previous URLs)",
"description": "Enables the crawler to navigate from a specific URL to previously linked pages. For instance, from 'example.com/product/123' back to 'example.com/product'",
"default": false
},
"allowExternalContentLinks": {
"type": "boolean",
"description": "Allows the crawler to follow links to external websites.",
"default": false
}
}
@ -212,25 +232,32 @@
"pageOptions": {
"type": "object",
"properties": {
"headers": {
"type": "object",
"description": "Headers to send with the request. Can be used to send cookies, user-agent, etc."
},
"includeHtml": {
"type": "boolean",
"description": "Include the HTML version of the content on page. Will output a html key in the response.",
"default": false
},
"includeRawHtml": {
"type": "boolean",
"description": "Include the raw HTML content of the page. Will output a rawHtml key in the response.",
"default": false
},
"onlyIncludeTags": {
"type": "array",
"items": {
"type": "string"
},
"description": "Only include tags, classes and ids from the page in the final output. Use comma separated values. Example: 'script, .ad, #footer'"
},
"onlyMainContent": {
"type": "boolean",
"description": "Only return the main content of the page excluding headers, navs, footers, etc.",
"default": false
},
"includeHtml": {
"type": "boolean",
"description": "Include the raw HTML content of the page. Will output a html key in the response.",
"default": false
},
"screenshot": {
"type": "boolean",
"description": "Include a screenshot of the top of the page that you are scraping.",
"default": false
},
"headers": {
"type": "object",
"description": "Headers to send with the request when scraping. Can be used to send cookies, user-agent, etc."
},
"removeTags": {
"type": "array",
"items": {
@ -242,6 +269,21 @@
"type": "boolean",
"description": "Replace all relative paths with absolute paths for images and links",
"default": false
},
"screenshot": {
"type": "boolean",
"description": "Include a screenshot of the top of the page that you are scraping.",
"default": false
},
"fullPageScreenshot": {
"type": "boolean",
"description": "Include a full page screenshot of the page that you are scraping.",
"default": false
},
"waitFor": {
"type": "integer",
"description": "Wait x amount of milliseconds for the page to load to fetch content",
"default": 0
}
}
}
@ -263,13 +305,52 @@
}
},
"402": {
"description": "Payment required"
"description": "Payment required",
"content": {
"application/json": {
"schema": {
"type": "object",
"properties": {
"error": {
"type": "string",
"example": "Payment required to access this resource."
}
}
}
}
}
},
"429": {
"description": "Too many requests"
"description": "Too many requests",
"content": {
"application/json": {
"schema": {
"type": "object",
"properties": {
"error": {
"type": "string",
"example": "Request rate limit exceeded. Please wait and try again later."
}
}
}
}
}
},
"500": {
"description": "Server error"
"description": "Server error",
"content": {
"application/json": {
"schema": {
"type": "object",
"properties": {
"error": {
"type": "string",
"example": "An unexpected error occurred on the server."
}
}
}
}
}
}
}
}
@ -311,7 +392,12 @@
},
"includeHtml": {
"type": "boolean",
"description": "Include the raw HTML content of the page. Will output a html key in the response.",
"description": "Include the HTML version of the content on page. Will output a html key in the response.",
"default": false
},
"includeRawHtml": {
"type": "boolean",
"description": "Include the raw HTML content of the page. Will output a rawHtml key in the response.",
"default": false
}
}
@ -343,13 +429,52 @@
}
},
"402": {
"description": "Payment required"
"description": "Payment required",
"content": {
"application/json": {
"schema": {
"type": "object",
"properties": {
"error": {
"type": "string",
"example": "Payment required to access this resource."
}
}
}
}
}
},
"429": {
"description": "Too many requests"
"description": "Too many requests",
"content": {
"application/json": {
"schema": {
"type": "object",
"properties": {
"error": {
"type": "string",
"example": "Request rate limit exceeded. Please wait and try again later."
}
}
}
}
}
},
"500": {
"description": "Server error"
"description": "Server error",
"content": {
"application/json": {
"schema": {
"type": "object",
"properties": {
"error": {
"type": "string",
"example": "An unexpected error occurred on the server."
}
}
}
}
}
}
}
}
@ -391,14 +516,6 @@
"type": "integer",
"description": "Current page number"
},
"current_url": {
"type": "string",
"description": "Current URL being scraped"
},
"current_step": {
"type": "string",
"description": "Current step in the process"
},
"total": {
"type": "integer",
"description": "Total number of pages"
@ -415,7 +532,7 @@
"items": {
"$ref": "#/components/schemas/CrawlStatusResponseObj"
},
"description": "Partial documents returned as it is being crawled (streaming). **This feature is currently in alpha - expect breaking changes** When a page is ready, it will append to the partial_data array, so there is no need to wait for the entire website to be crawled. There is a max of 50 items in the array response. The oldest item (top of the array) will be removed when the new item is added to the array."
"description": "Partial documents returned as it is being crawled (streaming). **This feature is currently in alpha - expect breaking changes** When a page is ready, it will append to the partial_data array, so there is no need to wait for the entire website to be crawled. When the crawl is done, partial_data will become empty and the result will be available in `data`. There is a max of 50 items in the array response. The oldest item (top of the array) will be removed when the new item is added to the array."
}
}
}
@ -423,13 +540,52 @@
}
},
"402": {
"description": "Payment required"
"description": "Payment required",
"content": {
"application/json": {
"schema": {
"type": "object",
"properties": {
"error": {
"type": "string",
"example": "Payment required to access this resource."
}
}
}
}
}
},
"429": {
"description": "Too many requests"
"description": "Too many requests",
"content": {
"application/json": {
"schema": {
"type": "object",
"properties": {
"error": {
"type": "string",
"example": "Request rate limit exceeded. Please wait and try again later."
}
}
}
}
}
},
"500": {
"description": "Server error"
"description": "Server error",
"content": {
"application/json": {
"schema": {
"type": "object",
"properties": {
"error": {
"type": "string",
"example": "An unexpected error occurred on the server."
}
}
}
}
}
}
}
}
@ -473,13 +629,52 @@
}
},
"402": {
"description": "Payment required"
"description": "Payment required",
"content": {
"application/json": {
"schema": {
"type": "object",
"properties": {
"error": {
"type": "string",
"example": "Payment required to access this resource."
}
}
}
}
}
},
"429": {
"description": "Too many requests"
"description": "Too many requests",
"content": {
"application/json": {
"schema": {
"type": "object",
"properties": {
"error": {
"type": "string",
"example": "Request rate limit exceeded. Please wait and try again later."
}
}
}
}
}
},
"500": {
"description": "Server error"
"description": "Server error",
"content": {
"application/json": {
"schema": {
"type": "object",
"properties": {
"error": {
"type": "string",
"example": "An unexpected error occurred on the server."
}
}
}
}
}
}
}
}
@ -499,19 +694,42 @@
"success": {
"type": "boolean"
},
"warning": {
"type": "string",
"nullable": true,
"description": "Warning message to let you know of any issues."
},
"data": {
"type": "object",
"properties": {
"markdown": {
"type": "string"
},
"content": {
"type": "string"
"type": "string",
"nullable": true,
"description": "Markdown content of the page if the `markdown` format was specified (default)"
},
"html": {
"type": "string",
"nullable": true,
"description": "Raw HTML content of the page if `includeHtml` is true"
"description": "HTML version of the content on page if the `html` format was specified"
},
"rawHtml": {
"type": "string",
"nullable": true,
"description": "Raw HTML content of the page if the `rawHtml` format was specified"
},
"links": {
"type": "array",
"items": {
"type": "string",
"format": "uri"
},
"nullable": true,
"description": "Links on the page if the `links` format was specified"
},
"screenshot": {
"type": "string",
"nullable": true,
"description": "URL of the screenshot of the page if the `screenshot` or `screenshot@fullSize` format was specified"
},
"metadata": {
"type": "object",
@ -529,18 +747,20 @@
"sourceURL": {
"type": "string",
"format": "uri"
}
}
},
"llm_extraction": {
"type": "object",
"description": "Displayed when using LLM Extraction. Extracted data from the page following the schema defined.",
"nullable": true
"<any other metadata> ": {
"type": "string"
},
"warning": {
"statusCode": {
"type": "integer",
"description": "The status code of the page"
},
"error": {
"type": "string",
"nullable": true,
"description": "Can be displayed when using LLM Extraction. Warning message will let you know any issues with the extraction."
"description": "The error message of the page"
}
}
}
}
}
@ -550,19 +770,33 @@
"type": "object",
"properties": {
"markdown": {
"type": "string"
},
"content": {
"type": "string"
"type": "string",
"nullable": true,
"description": "Markdown content of the page if the `markdown` format was specified (default)"
},
"html": {
"type": "string",
"nullable": true,
"description": "Raw HTML content of the page if `includeHtml` is true"
"description": "HTML version of the content on page if the `html` format was specified"
},
"index": {
"type": "integer",
"description": "The number of the page that was crawled. This is useful for `partial_data` so you know which page the data is from."
"rawHtml": {
"type": "string",
"nullable": true,
"description": "Raw HTML content of the page if the `rawHtml` format was specified"
},
"links": {
"type": "array",
"items": {
"type": "string",
"format": "uri"
},
"nullable": true,
"description": "Links on the page if the `links` format was specified"
},
"screenshot": {
"type": "string",
"nullable": true,
"description": "URL of the screenshot of the page if the `screenshot` or `screenshot@fullSize` format was specified"
},
"metadata": {
"type": "object",
@ -580,6 +814,18 @@
"sourceURL": {
"type": "string",
"format": "uri"
},
"<any other metadata> ": {
"type": "string"
},
"statusCode": {
"type": "integer",
"description": "The status code of the page"
},
"error": {
"type": "string",
"nullable": true,
"description": "The error message of the page"
}
}
}
@ -594,16 +840,34 @@
"data": {
"type": "array",
"items": {
"type": "object",
"properties": {
"url": {
"type": "string"
},
"markdown": {
"type": "string"
"type": "string",
"nullable": true,
"description": "Markdown content of the page if the `markdown` format was specified (default)"
},
"content": {
"type": "string"
"html": {
"type": "string",
"nullable": true,
"description": "HTML version of the content on page if the `html` format was specified"
},
"rawHtml": {
"type": "string",
"nullable": true,
"description": "Raw HTML content of the page if the `rawHtml` format was specified"
},
"links": {
"type": "array",
"items": {
"type": "string",
"format": "uri"
},
"nullable": true,
"description": "Links on the page if the `links` format was specified"
},
"screenshot": {
"type": "string",
"nullable": true,
"description": "URL of the screenshot of the page if the `screenshot` or `screenshot@fullSize` format was specified"
},
"metadata": {
"type": "object",
@ -621,7 +885,18 @@
"sourceURL": {
"type": "string",
"format": "uri"
}
},
"<any other metadata> ": {
"type": "string"
},
"statusCode": {
"type": "integer",
"description": "The status code of the page"
},
"error": {
"type": "string",
"nullable": true,
"description": "The error message of the page"
}
}
}
@ -632,8 +907,15 @@
"CrawlResponse": {
"type": "object",
"properties": {
"jobId": {
"success": {
"type": "boolean"
},
"id": {
"type": "string"
},
"url": {
"type": "string",
"format": "uri"
}
}
}

86
apps/api/package.json
View File

@ -9,23 +9,28 @@
"format": "prettier --write \"src/**/*.(js|ts)\"",
"flyio": "node dist/src/index.js",
"start:dev": "nodemon --exec ts-node src/index.ts",
"build": "tsc",
"build": "tsc && pnpm sentry:sourcemaps",
"build:nosentry": "tsc",
"test": "npx jest --detectOpenHandles --forceExit --openHandlesTimeout=120000 --watchAll=false --testPathIgnorePatterns='src/__tests__/e2e_noAuth/*'",
"test:local-no-auth": "npx jest --detectOpenHandles --forceExit --openHandlesTimeout=120000 --watchAll=false --testPathIgnorePatterns='src/__tests__/e2e_withAuth/*'",
"test:prod": "npx jest --detectOpenHandles --forceExit --openHandlesTimeout=120000 --watchAll=false --testPathIgnorePatterns='src/__tests__/e2e_noAuth/*'",
"test:full": "npx jest --detectOpenHandles --forceExit --openHandlesTimeout=120000 --watchAll=false --testPathIgnorePatterns='(src/__tests__/e2e_noAuth|src/__tests__/e2e_withAuth)'",
"test:prod": "npx jest --detectOpenHandles --forceExit --openHandlesTimeout=120000 --watchAll=false --testPathIgnorePatterns='(src/__tests__/e2e_noAuth|src/__tests__/e2e_full_withAuth)'",
"workers": "nodemon --exec ts-node src/services/queue-worker.ts",
"worker:production": "node dist/src/services/queue-worker.js",
"mongo-docker": "docker run -d -p 2717:27017 -v ./mongo-data:/data/db --name mongodb mongo:latest",
"mongo-docker-console": "docker exec -it mongodb mongosh",
"run-example": "npx ts-node src/example.ts"
"run-example": "npx ts-node src/example.ts",
"deploy:fly": "flyctl deploy --build-secret SENTRY_AUTH_TOKEN=$(dotenv -p SENTRY_AUTH_TOKEN) --depot=false",
"deploy:fly:staging": "fly deploy -c fly.staging.toml --depot=false",
"sentry:sourcemaps": "sentry-cli sourcemaps inject --org caleb-peffer --project firecrawl-scraper-js ./dist && sentry-cli sourcemaps upload --org caleb-peffer --project firecrawl-scraper-js ./dist"
},
"author": "",
"license": "ISC",
"devDependencies": {
"@flydotio/dockerfile": "^0.4.10",
"@jest/globals": "^29.7.0",
"@tsconfig/recommended": "^1.0.3",
"@types/body-parser": "^1.19.2",
"@types/bull": "^4.10.0",
"@types/cors": "^2.8.13",
"@types/express": "^4.17.17",
"@types/jest": "^29.5.12",
@ -43,66 +48,77 @@
"typescript": "^5.4.2"
},
"dependencies": {
"@anthropic-ai/sdk": "^0.20.5",
"@anthropic-ai/sdk": "^0.24.3",
"@brillout/import": "^0.2.2",
"@bull-board/api": "^5.14.2",
"@bull-board/express": "^5.8.0",
"@bull-board/api": "^5.20.5",
"@bull-board/express": "^5.20.5",
"@devil7softwares/pos": "^1.0.2",
"@dqbd/tiktoken": "^1.0.13",
"@hyperdx/node-opentelemetry": "^0.7.0",
"@hyperdx/node-opentelemetry": "^0.8.1",
"@logtail/node": "^0.4.12",
"@nangohq/node": "^0.36.33",
"@sentry/node": "^7.48.0",
"@supabase/supabase-js": "^2.7.1",
"ajv": "^8.12.0",
"@nangohq/node": "^0.40.8",
"@sentry/cli": "^2.33.1",
"@sentry/node": "^8.26.0",
"@sentry/profiling-node": "^8.26.0",
"@supabase/supabase-js": "^2.44.2",
"@types/express-ws": "^3.0.4",
"@types/ws": "^8.5.12",
"ajv": "^8.16.0",
"async": "^3.2.5",
"async-mutex": "^0.4.0",
"async-mutex": "^0.5.0",
"axios": "^1.3.4",
"axios-retry": "^4.5.0",
"bottleneck": "^2.19.5",
"bull": "^4.11.4",
"bullmq": "^5.11.0",
"cacheable-lookup": "^6.1.0",
"cheerio": "^1.0.0-rc.12",
"cohere": "^1.1.1",
"cors": "^2.8.5",
"cron-parser": "^4.9.0",
"date-fns": "^2.29.3",
"date-fns": "^3.6.0",
"dotenv": "^16.3.1",
"express-rate-limit": "^6.7.0",
"dotenv-cli": "^7.4.2",
"express-rate-limit": "^7.3.1",
"express-ws": "^5.0.2",
"form-data": "^4.0.0",
"glob": "^10.3.12",
"glob": "^10.4.2",
"gpt3-tokenizer": "^1.1.5",
"ioredis": "^5.3.2",
"ioredis": "^5.4.1",
"joplin-turndown-plugin-gfm": "^1.0.12",
"json-schema-to-zod": "^2.1.0",
"keyword-extractor": "^0.0.25",
"langchain": "^0.1.25",
"json-schema-to-zod": "^2.3.0",
"keyword-extractor": "^0.0.28",
"koffi": "^2.9.0",
"langchain": "^0.2.8",
"languagedetect": "^2.0.0",
"logsnag": "^0.1.6",
"logsnag": "^1.0.0",
"luxon": "^3.4.3",
"md5": "^2.3.0",
"moment": "^2.29.4",
"mongoose": "^8.0.3",
"natural": "^6.3.0",
"openai": "^4.28.4",
"mongoose": "^8.4.4",
"natural": "^7.0.7",
"openai": "^4.57.0",
"pdf-parse": "^1.1.1",
"pos": "^0.4.2",
"posthog-node": "^4.0.1",
"promptable": "^0.0.9",
"puppeteer": "^22.6.3",
"rate-limiter-flexible": "^2.4.2",
"redis": "^4.6.7",
"resend": "^3.2.0",
"promptable": "^0.0.10",
"puppeteer": "^22.12.1",
"rate-limiter-flexible": "2.4.2",
"redlock": "5.0.0-beta.2",
"resend": "^3.4.0",
"robots-parser": "^3.0.1",
"scrapingbee": "^1.7.4",
"stripe": "^15.11.0",
"stripe": "^16.1.0",
"systeminformation": "^5.22.11",
"turndown": "^7.1.3",
"turndown-plugin-gfm": "^1.0.2",
"typesense": "^1.5.4",
"unstructured-client": "^0.9.4",
"uuid": "^9.0.1",
"unstructured-client": "^0.11.3",
"uuid": "^10.0.0",
"wordpos": "^2.1.0",
"ws": "^8.18.0",
"xml2js": "^0.6.2",
"zod": "^3.23.4",
"zod-to-json-schema": "^3.23.0"
"zod": "^3.23.8",
"zod-to-json-schema": "^3.23.1"
},
"nodemonConfig": {
"ignore": [

12064
apps/api/pnpm-lock.yaml
View File

File diff suppressed because it is too large Load Diff

26
apps/api/requests.http
View File

@ -1,12 +1,16 @@
### Crawl Website
POST http://localhost:3002/v0/scrape HTTP/1.1
Authorization: Bearer
Authorization: Bearer fc-
content-type: application/json
{
"url":"https://docs.mendable.ai"
"url":"corterix.com"
}
### Check Job Status
GET http://localhost:3002/v1/crawl/1dd0f924-a36f-4b96-94ea-32ed954dac67 HTTP/1.1
Authorization: Bearer fc-
### Check Job Status
GET http://localhost:3002/v0/jobs/active HTTP/1.1
@ -14,16 +18,24 @@ GET http://localhost:3002/v0/jobs/active HTTP/1.1
### Scrape Website
POST http://localhost:3002/v0/crawl HTTP/1.1
Authorization: Bearer
Authorization: Bearer fc-
content-type: application/json
{
"url":"https://www.mendable.ai",
"crawlerOptions": {
"returnOnlyUrls": true
}
"url": "firecrawl.dev"
}
## "reoveTags": [],
# "mode": "crawl",
# "crawlerOptions": {
# "allowBackwardCrawling": false
# },
# "pageOptions": {
# "onlyMainContent": false,
# "includeHtml": false,
# "parsePDF": true
# }

7
apps/api/sharedLibs/go-html-to-md/README.md Normal file
View File

@ -0,0 +1,7 @@
To build the go-html-to-md library, run the following command:
```bash
cd apps/api/src/lib/go-html-to-md
go build -o html-to-markdown.so -buildmode=c-shared html-to-markdown.go
chmod +x html-to-markdown.so
```

16
apps/api/sharedLibs/go-html-to-md/go.mod Normal file
View File

@ -0,0 +1,16 @@
module html-to-markdown.go
go 1.19
require github.com/tomkosm/html-to-markdown v0.0.0-20241031120941-3a729f6b7751
require (
github.com/PuerkitoBio/goquery v1.9.2 // indirect
github.com/andybalholm/cascadia v1.3.2 // indirect
github.com/kr/pretty v0.3.0 // indirect
golang.org/x/net v0.25.0 // indirect
gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c // indirect
gopkg.in/yaml.v2 v2.4.0 // indirect
)
replace github.com/JohannesKaufmann/html-to-markdown => github.com/tomkosm/html-to-markdown v0.0.0-20241031120941-3a729f6b7751

64
apps/api/sharedLibs/go-html-to-md/go.sum Normal file
View File

@ -0,0 +1,64 @@
github.com/PuerkitoBio/goquery v1.9.2 h1:4/wZksC3KgkQw7SQgkKotmKljk0M6V8TUvA8Wb4yPeE=
github.com/PuerkitoBio/goquery v1.9.2/go.mod h1:GHPCaP0ODyyxqcNoFGYlAprUFH81NuRPd0GX3Zu2Mvk=
github.com/andybalholm/cascadia v1.3.2 h1:3Xi6Dw5lHF15JtdcmAHD3i1+T8plmv7BQ/nsViSLyss=
github.com/andybalholm/cascadia v1.3.2/go.mod h1:7gtRlve5FxPPgIgX36uWBX58OdBsSS6lUvCFb+h7KvU=
github.com/creack/pty v1.1.9/go.mod h1:oKZEueFk5CKHvIhNR5MUki03XCEU+Q6VDXinZuGJ33E=
github.com/kr/pretty v0.1.0/go.mod h1:dAy3ld7l9f0ibDNOQOHHMYYIIbhfbHSm3C4ZsoJORNo=
github.com/kr/pretty v0.2.1/go.mod h1:ipq/a2n7PKx3OHsz4KJII5eveXtPO4qwEXGdVfWzfnI=
github.com/kr/pretty v0.3.0 h1:WgNl7dwNpEZ6jJ9k1snq4pZsg7DOEN8hP9Xw0Tsjwk0=
github.com/kr/pretty v0.3.0/go.mod h1:640gp4NfQd8pI5XOwp5fnNeVWj67G7CFk/SaSQn7NBk=
github.com/kr/pty v1.1.1/go.mod h1:pFQYn66WHrOpPYNljwOMqo10TkYh1fy3cYio2l3bCsQ=
github.com/kr/text v0.1.0/go.mod h1:4Jbv+DJW3UT/LiOwJeYQe1efqtUx/iVham/4vfdArNI=
github.com/kr/text v0.2.0 h1:5Nx0Ya0ZqY2ygV366QzturHI13Jq95ApcVaJBhpS+AY=
github.com/kr/text v0.2.0/go.mod h1:eLer722TekiGuMkidMxC/pM04lWEeraHUUmBw8l2grE=
github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM=
github.com/rogpeppe/go-internal v1.6.1 h1:/FiVV8dS/e+YqF2JvO3yXRFbBLTIuSDkuC7aBOAvL+k=
github.com/rogpeppe/go-internal v1.6.1/go.mod h1:xXDCJY+GAPziupqXw64V24skbSoqbTEfhy4qGm1nDQc=
github.com/sebdah/goldie/v2 v2.5.3 h1:9ES/mNN+HNUbNWpVAlrzuZ7jE+Nrczbj8uFRjM7624Y=
github.com/sergi/go-diff v1.3.1 h1:xkr+Oxo4BOQKmkn/B9eMK0g5Kg/983T9DqqPHwYqD+8=
github.com/tomkosm/html-to-markdown v0.0.0-20241031120941-3a729f6b7751 h1:l6JdzR2ry727okVeBxnH8nh3SAd7l/0gJTWbK/3UBRY=
github.com/tomkosm/html-to-markdown v0.0.0-20241031120941-3a729f6b7751/go.mod h1:I2mfsDlV0RelCsTjeYh9mdXdwD2M70rA7LT/y2girik=
github.com/yuin/goldmark v1.4.13/go.mod h1:6yULJ656Px+3vBD8DxQVa3kxgyrAnzto9xy5taEt/CY=
github.com/yuin/goldmark v1.7.1 h1:3bajkSilaCbjdKVsKdZjZCLBNPL9pYzrCakKaf4U49U=
golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w=
golang.org/x/crypto v0.0.0-20210921155107-089bfa567519/go.mod h1:GvvjBRRGRdwPK5ydBHafDWAxML/pGHZbMvKqRZ5+Abc=
golang.org/x/mod v0.6.0-dev.0.20220419223038-86c51ed26bb4/go.mod h1:jJ57K6gSWd91VN4djpZkiMVwK6gcyfeH4XE8wZrZaV4=
golang.org/x/mod v0.8.0/go.mod h1:iBbtSCu2XBx23ZKBPSOrRkjjQPZFPuis4dIYUhu/chs=
golang.org/x/net v0.0.0-20190620200207-3b0461eec859/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=
golang.org/x/net v0.0.0-20210226172049-e18ecbb05110/go.mod h1:m0MpNAwzfU5UDzcl9v0D8zg8gWTRqZa9RBIspLL5mdg=
golang.org/x/net v0.0.0-20220722155237-a158d28d115b/go.mod h1:XRhObCWvk6IyKnWLug+ECip1KBveYUHfp+8e9klMJ9c=
golang.org/x/net v0.6.0/go.mod h1:2Tu9+aMcznHK/AK1HMvgo6xiTLG5rD5rZLDS+rp2Bjs=
golang.org/x/net v0.9.0/go.mod h1:d48xBJpPfHeWQsugry2m+kC02ZBRGRgulfHnEXEuWns=
golang.org/x/net v0.25.0 h1:d/OCCoBEUq33pjydKrGQhw7IlUPI2Oylr+8qLx49kac=
golang.org/x/net v0.25.0/go.mod h1:JkAGAh7GEvH74S6FOH42FLoXpXbE/aqXSrIQjXgsiwM=
golang.org/x/sync v0.0.0-20190423024810-112230192c58/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
golang.org/x/sync v0.0.0-20220722155255-886fb9371eb4/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
golang.org/x/sync v0.1.0/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
golang.org/x/sys v0.0.0-20201119102817-f84b799fce68/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
golang.org/x/sys v0.0.0-20210615035016-665e8c7367d1/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.0.0-20220520151302-bc2c85ada10a/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.0.0-20220722155257-8c9f86f7a55f/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.5.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.7.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo=
golang.org/x/term v0.0.0-20210927222741-03fcf44c2211/go.mod h1:jbD1KX2456YbFQfuXm/mYQcufACuNUgVhRMnK/tPxf8=
golang.org/x/term v0.5.0/go.mod h1:jMB1sMXY+tzblOD4FWmEbocvup2/aLOaQEp7JmGp78k=
golang.org/x/term v0.7.0/go.mod h1:P32HKFT3hSsZrRxla30E9HqToFYAQPCMs/zFMBUFqPY=
golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
golang.org/x/text v0.3.3/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
golang.org/x/text v0.3.7/go.mod h1:u+2+/6zg+i71rQMx5EYifcz6MCKuco9NR6JIITiCfzQ=
golang.org/x/text v0.7.0/go.mod h1:mrYo+phRRbMaCq/xk9113O4dZlRixOauAjOtrjsXDZ8=
golang.org/x/text v0.9.0/go.mod h1:e1OnstbJyHTd6l/uOt8jFFHp6TRDWZR/bV3emEE/zU8=
golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
golang.org/x/tools v0.0.0-20191119224855-298f0cb1881e/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo=
golang.org/x/tools v0.1.12/go.mod h1:hNGJHUnrk76NpqgfD5Aqm5Crs+Hm0VOH/i9J2+nxYbc=
golang.org/x/tools v0.6.0/go.mod h1:Xwgl3UAJ/d3gWutnCtw505GrjyAbvKui8lOU390QaIU=
golang.org/x/xerrors v0.0.0-20190717185122-a985d3407aa7/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
gopkg.in/check.v1 v1.0.0-20180628173108-788fd7840127/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c h1:Hei/4ADfdWqJk1ZMxUNpqntNwaWcugrBjAiHlqqRiVk=
gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c/go.mod h1:JHkPIbrfpd72SG/EVd6muEfDQjcINNoR0C8j2r3qZ4Q=
gopkg.in/errgo.v2 v2.1.0/go.mod h1:hNsd1EY+bozCKY1Ytp96fpM3vjJbqLJn88ws8XvfDNI=
gopkg.in/yaml.v2 v2.4.0 h1:D8xgwECY7CYvx+Y2n4sBz93Jn9JRvxdiyyo8CTfuKaY=
gopkg.in/yaml.v2 v2.4.0/go.mod h1:RDklbk79AGWmwhnvt/jBztapEOGDOx6ZbXqjP6csGnQ=

25
apps/api/sharedLibs/go-html-to-md/html-to-markdown.go Normal file
View File

@ -0,0 +1,25 @@
package main
import (
"C"
"log"
md "github.com/tomkosm/html-to-markdown"
"github.com/tomkosm/html-to-markdown/plugin"
)
//export ConvertHTMLToMarkdown
func ConvertHTMLToMarkdown(html *C.char) *C.char {
converter := md.NewConverter("", true, nil)
converter.Use(plugin.GitHubFlavored())
markdown, err := converter.ConvertString(C.GoString(html))
if err != nil {
log.Fatal(err)
}
return C.CString(markdown)
}
func main() {
// This function is required for the main package
}

1515
apps/api/src/__tests__/e2e_full_withAuth/index.test.ts Normal file
View File

File diff suppressed because it is too large Load Diff

1005
apps/api/src/__tests__/e2e_v1_withAuth/index.test.ts Normal file
View File

File diff suppressed because it is too large Load Diff

1220
apps/api/src/__tests__/e2e_withAuth/index.test.ts
View File

File diff suppressed because it is too large Load Diff

47
apps/api/src/controllers/__tests__/crawl.test.ts Normal file
View File

@ -0,0 +1,47 @@
import { crawlController } from '../v0/crawl'
import { Request, Response } from 'express';
import { authenticateUser } from '../auth'; // Ensure this import is correct
import { createIdempotencyKey } from '../../services/idempotency/create';
import { validateIdempotencyKey } from '../../services/idempotency/validate';
import { v4 as uuidv4 } from 'uuid';
jest.mock('../auth', () => ({
authenticateUser: jest.fn().mockResolvedValue({
success: true,
team_id: 'team123',
error: null,
status: 200
}),
reduce: jest.fn()
}));
jest.mock('../../services/idempotency/validate');
describe('crawlController', () => {
it('should prevent duplicate requests using the same idempotency key', async () => {
const req = {
headers: {
'x-idempotency-key': await uuidv4(),
'Authorization': `Bearer ${process.env.TEST_API_KEY}`
},
body: {
url: 'https://mendable.ai'
}
} as unknown as Request;
const res = {
status: jest.fn().mockReturnThis(),
json: jest.fn()
} as unknown as Response;
// Mock the idempotency key validation to return false for the second call
(validateIdempotencyKey as jest.Mock).mockResolvedValueOnce(true).mockResolvedValueOnce(false);
// First request should succeed
await crawlController(req, res);
expect(res.status).not.toHaveBeenCalledWith(409);
// Second request with the same key should fail
await crawlController(req, res);
expect(res.status).toHaveBeenCalledWith(409);
expect(res.json).toHaveBeenCalledWith({ error: 'Idempotency key already used' });
});
});

333
apps/api/src/controllers/auth.ts
View File

@ -1,26 +1,166 @@
import { parseApi } from "../../src/lib/parseApi";
import { getRateLimiter, } from "../../src/services/rate-limiter";
import { AuthResponse, NotificationType, RateLimiterMode } from "../../src/types";
import { supabase_service } from "../../src/services/supabase";
import { withAuth } from "../../src/lib/withAuth";
import { parseApi } from "../lib/parseApi";
import { getRateLimiter } from "../services/rate-limiter";
import {
AuthResponse,
NotificationType,
PlanType,
RateLimiterMode,
} from "../types";
import { supabase_service } from "../services/supabase";
import { withAuth } from "../lib/withAuth";
import { RateLimiterRedis } from "rate-limiter-flexible";
import { setTraceAttributes } from '@hyperdx/node-opentelemetry';
import { setTraceAttributes } from "@hyperdx/node-opentelemetry";
import { sendNotification } from "../services/notification/email_notification";
import { Logger } from "../lib/logger";
import { redlock } from "../services/redlock";
import { deleteKey, getValue } from "../services/redis";
import { setValue } from "../services/redis";
import { validate } from "uuid";
import * as Sentry from "@sentry/node";
import { AuthCreditUsageChunk } from "./v1/types";
// const { data, error } = await supabase_service
// .from('api_keys')
// .select(`
// key,
// team_id,
// teams (
// subscriptions (
// price_id
// )
// )
// `)
// .eq('key', normalizedApi)
// .limit(1)
// .single();
function normalizedApiIsUuid(potentialUuid: string): boolean {
// Check if the string is a valid UUID
return validate(potentialUuid);
}
export async function authenticateUser(req, res, mode?: RateLimiterMode): Promise<AuthResponse> {
export async function setCachedACUC(
api_key: string,
acuc:
| AuthCreditUsageChunk
| ((acuc: AuthCreditUsageChunk) => AuthCreditUsageChunk)
) {
const cacheKeyACUC = `acuc_${api_key}`;
const redLockKey = `lock_${cacheKeyACUC}`;
try {
await redlock.using([redLockKey], 10000, {}, async (signal) => {
if (typeof acuc === "function") {
acuc = acuc(JSON.parse(await getValue(cacheKeyACUC)));
if (acuc === null) {
if (signal.aborted) {
throw signal.error;
}
return;
}
}
if (signal.aborted) {
throw signal.error;
}
// Cache for 10 minutes. This means that changing subscription tier could have
// a maximum of 10 minutes of a delay. - mogery
await setValue(cacheKeyACUC, JSON.stringify(acuc), 600, true);
});
} catch (error) {
Logger.error(`Error updating cached ACUC ${cacheKeyACUC}: ${error}`);
}
}
export async function getACUC(
api_key: string,
cacheOnly = false,
useCache = true
): Promise<AuthCreditUsageChunk | null> {
const cacheKeyACUC = `acuc_${api_key}`;
if (useCache) {
const cachedACUC = await getValue(cacheKeyACUC);
if (cachedACUC !== null) {
return JSON.parse(cachedACUC);
}
}
if (!cacheOnly) {
let data;
let error;
let retries = 0;
const maxRetries = 5;
while (retries < maxRetries) {
({ data, error } = await supabase_service.rpc(
"auth_credit_usage_chunk_test_21_credit_pack",
{ input_key: api_key }
));
if (!error) {
break;
}
Logger.warn(
`Failed to retrieve authentication and credit usage data after ${retries}, trying again...`
);
retries++;
if (retries === maxRetries) {
throw new Error(
"Failed to retrieve authentication and credit usage data after 3 attempts: " +
JSON.stringify(error)
);
}
// Wait for a short time before retrying
await new Promise((resolve) => setTimeout(resolve, 200));
}
const chunk: AuthCreditUsageChunk | null =
data.length === 0 ? null : data[0].team_id === null ? null : data[0];
// NOTE: Should we cache null chunks? - mogery
if (chunk !== null && useCache) {
setCachedACUC(api_key, chunk);
}
// console.log(chunk);
return chunk;
} else {
return null;
}
}
export async function clearACUC(
api_key: string,
): Promise<void> {
const cacheKeyACUC = `acuc_${api_key}`;
await deleteKey(cacheKeyACUC);
}
export async function authenticateUser(
req,
res,
mode?: RateLimiterMode
): Promise<AuthResponse> {
return withAuth(supaAuthenticateUser)(req, res, mode);
}
function setTrace(team_id: string, api_key: string) {
try {
setTraceAttributes({
team_id,
api_key
api_key,
});
} catch (error) {
console.error('Error setting trace attributes:', error);
Sentry.captureException(error);
Logger.error(`Error setting trace attributes: ${error.message}`);
}
}
export async function supaAuthenticateUser(
req,
res,
@ -30,9 +170,14 @@ export async function supaAuthenticateUser(
team_id?: string;
error?: string;
status?: number;
plan?: string;
plan?: PlanType;
chunk?: AuthCreditUsageChunk;
}> {
const authHeader = req.headers.authorization;
const authHeader =
req.headers.authorization ??
(req.headers["sec-websocket-protocol"]
? `Bearer ${req.headers["sec-websocket-protocol"]}`
: null);
if (!authHeader) {
return { success: false, error: "Unauthorized", status: 401 };
}
@ -50,69 +195,79 @@ export async function supaAuthenticateUser(
const iptoken = incomingIP + token;
let rateLimiter: RateLimiterRedis;
let subscriptionData: { team_id: string, plan: string } | null = null;
let subscriptionData: { team_id: string; plan: string } | null = null;
let normalizedApi: string;
let team_id: string;
let teamId: string | null = null;
let priceId: string | null = null;
let chunk: AuthCreditUsageChunk;
if (token == "this_is_just_a_preview_token") {
if (mode == RateLimiterMode.CrawlStatus) {
rateLimiter = getRateLimiter(RateLimiterMode.CrawlStatus, token);
} else {
rateLimiter = getRateLimiter(RateLimiterMode.Preview, token);
team_id = "preview";
}
teamId = "preview";
} else {
normalizedApi = parseApi(token);
const { data, error } = await supabase_service.rpc(
'get_key_and_price_id_2', { api_key: normalizedApi }
);
// get_key_and_price_id_2 rpc definition:
// create or replace function get_key_and_price_id_2(api_key uuid)
// returns table(key uuid, team_id uuid, price_id text) as $$
// begin
// if api_key is null then
// return query
// select null::uuid as key, null::uuid as team_id, null::text as price_id;
// end if;
// return query
// select ak.key, ak.team_id, s.price_id
// from api_keys ak
// left join subscriptions s on ak.team_id = s.team_id
// where ak.key = api_key;
// end;
// $$ language plpgsql;
if (error) {
console.error('Error fetching key and price_id:', error);
} else {
// console.log('Key and Price ID:', data);
}
if (error || !data || data.length === 0) {
if (!normalizedApiIsUuid(normalizedApi)) {
return {
success: false,
error: "Unauthorized: Invalid token",
status: 401,
};
}
const internal_team_id = data[0].team_id;
team_id = internal_team_id;
const plan = getPlanByPriceId(data[0].price_id);
// HyperDX Logging
setTrace(team_id, normalizedApi);
subscriptionData = {
team_id: team_id,
plan: plan
chunk = await getACUC(normalizedApi);
if (chunk === null) {
return {
success: false,
error: "Unauthorized: Invalid token",
status: 401,
};
}
teamId = chunk.team_id;
priceId = chunk.price_id;
const plan = getPlanByPriceId(priceId);
// HyperDX Logging
setTrace(teamId, normalizedApi);
subscriptionData = {
team_id: teamId,
plan,
};
switch (mode) {
case RateLimiterMode.Crawl:
rateLimiter = getRateLimiter(RateLimiterMode.Crawl, token, subscriptionData.plan);
rateLimiter = getRateLimiter(
RateLimiterMode.Crawl,
token,
subscriptionData.plan
);
break;
case RateLimiterMode.Scrape:
rateLimiter = getRateLimiter(RateLimiterMode.Scrape, token, subscriptionData.plan);
rateLimiter = getRateLimiter(
RateLimiterMode.Scrape,
token,
subscriptionData.plan,
teamId
);
break;
case RateLimiterMode.Search:
rateLimiter = getRateLimiter(RateLimiterMode.Search, token, subscriptionData.plan);
rateLimiter = getRateLimiter(
RateLimiterMode.Search,
token,
subscriptionData.plan
);
break;
case RateLimiterMode.Map:
rateLimiter = getRateLimiter(
RateLimiterMode.Map,
token,
subscriptionData.plan
);
break;
case RateLimiterMode.CrawlStatus:
rateLimiter = getRateLimiter(RateLimiterMode.CrawlStatus, token);
@ -130,12 +285,13 @@ export async function supaAuthenticateUser(
}
}
const team_endpoint_token = token === "this_is_just_a_preview_token" ? iptoken : team_id;
const team_endpoint_token =
token === "this_is_just_a_preview_token" ? iptoken : teamId;
try {
await rateLimiter.consume(team_endpoint_token);
} catch (rateLimiterRes) {
console.error(rateLimiterRes);
Logger.error(`Rate limit exceeded: ${rateLimiterRes}`);
const secs = Math.round(rateLimiterRes.msBeforeNext / 1000) || 1;
const retryDate = new Date(Date.now() + rateLimiterRes.msBeforeNext);
@ -143,17 +299,24 @@ export async function supaAuthenticateUser(
const startDate = new Date();
const endDate = new Date();
endDate.setDate(endDate.getDate() + 7);
// await sendNotification(team_id, NotificationType.RATE_LIMIT_REACHED, startDate.toISOString(), endDate.toISOString());
return {
success: false,
error: `Rate limit exceeded. Consumed points: ${rateLimiterRes.consumedPoints}, Remaining points: ${rateLimiterRes.remainingPoints}. Upgrade your plan at https://firecrawl.dev/pricing for increased rate limits or please retry after ${secs}s, resets at ${retryDate}`,
error: `Rate limit exceeded. Consumed (req/min): ${rateLimiterRes.consumedPoints}, Remaining (req/min): ${rateLimiterRes.remainingPoints}. Upgrade your plan at https://firecrawl.dev/pricing for increased rate limits or please retry after ${secs}s, resets at ${retryDate}`,
status: 429,
};
}
if (
token === "this_is_just_a_preview_token" &&
(mode === RateLimiterMode.Scrape || mode === RateLimiterMode.Preview || mode === RateLimiterMode.Search)
(mode === RateLimiterMode.Scrape ||
mode === RateLimiterMode.Preview ||
mode === RateLimiterMode.Map ||
mode === RateLimiterMode.Crawl ||
mode === RateLimiterMode.CrawlStatus ||
mode === RateLimiterMode.Search)
) {
return { success: true, team_id: "preview" };
// check the origin of the request and make sure its from firecrawl.dev
@ -168,44 +331,36 @@ export async function supaAuthenticateUser(
// return { success: false, error: "Unauthorized: Invalid token", status: 401 };
}
// make sure api key is valid, based on the api_keys table in supabase
if (!subscriptionData) {
normalizedApi = parseApi(token);
const { data, error } = await supabase_service
.from("api_keys")
.select("*")
.eq("key", normalizedApi);
if (error || !data || data.length === 0) {
return {
success: false,
error: "Unauthorized: Invalid token",
status: 401,
success: true,
team_id: subscriptionData.team_id,
plan: (subscriptionData.plan ?? "") as PlanType,
chunk,
};
}
subscriptionData = data[0];
}
return { success: true, team_id: subscriptionData.team_id, plan: subscriptionData.plan ?? ""};
}
function getPlanByPriceId(price_id: string) {
function getPlanByPriceId(price_id: string): PlanType {
switch (price_id) {
case process.env.STRIPE_PRICE_ID_STARTER:
return 'starter';
return "starter";
case process.env.STRIPE_PRICE_ID_STANDARD:
return 'standard';
return "standard";
case process.env.STRIPE_PRICE_ID_SCALE:
return 'scale';
case process.env.STRIPE_PRICE_ID_HOBBY || process.env.STRIPE_PRICE_ID_HOBBY_YEARLY:
return 'hobby';
case process.env.STRIPE_PRICE_ID_STANDARD_NEW || process.env.STRIPE_PRICE_ID_STANDARD_NEW_YEARLY:
return 'standard-new';
case process.env.STRIPE_PRICE_ID_GROWTH || process.env.STRIPE_PRICE_ID_GROWTH_YEARLY:
return 'growth';
return "scale";
case process.env.STRIPE_PRICE_ID_HOBBY:
case process.env.STRIPE_PRICE_ID_HOBBY_YEARLY:
return "hobby";
case process.env.STRIPE_PRICE_ID_STANDARD_NEW:
case process.env.STRIPE_PRICE_ID_STANDARD_NEW_YEARLY:
return "standardnew";
case process.env.STRIPE_PRICE_ID_GROWTH:
case process.env.STRIPE_PRICE_ID_GROWTH_YEARLY:
case process.env.STRIPE_PRICE_ID_SCALE_2M:
return "growth";
case process.env.STRIPE_PRICE_ID_GROWTH_DOUBLE_MONTHLY:
return "growthdouble";
case process.env.STRIPE_PRICE_ID_ETIER2C:
return "etier2c";
default:
return 'free';
return "free";
}
}

62
apps/api/src/controllers/crawl-cancel.ts
View File

@ -1,62 +0,0 @@
import { Request, Response } from "express";
import { authenticateUser } from "./auth";
import { RateLimiterMode } from "../../src/types";
import { addWebScraperJob } from "../../src/services/queue-jobs";
import { getWebScraperQueue } from "../../src/services/queue-service";
import { supabase_service } from "../../src/services/supabase";
import { billTeam } from "../../src/services/billing/credit_billing";
export async function crawlCancelController(req: Request, res: Response) {
try {
const { success, team_id, error, status } = await authenticateUser(
req,
res,
RateLimiterMode.CrawlStatus
);
if (!success) {
return res.status(status).json({ error });
}
const job = await getWebScraperQueue().getJob(req.params.jobId);
if (!job) {
return res.status(404).json({ error: "Job not found" });
}
// check if the job belongs to the team
const { data, error: supaError } = await supabase_service
.from("bulljobs_teams")
.select("*")
.eq("job_id", req.params.jobId)
.eq("team_id", team_id);
if (supaError) {
return res.status(500).json({ error: supaError.message });
}
if (data.length === 0) {
return res.status(403).json({ error: "Unauthorized" });
}
const jobState = await job.getState();
const { partialDocs } = await job.progress();
if (partialDocs && partialDocs.length > 0 && jobState === "active") {
console.log("Billing team for partial docs...");
// Note: the credits that we will bill them here might be lower than the actual
// due to promises that are not yet resolved
await billTeam(team_id, partialDocs.length);
}
try {
await job.moveToFailed(Error("Job cancelled by user"), true);
} catch (error) {
console.error(error);
}
const newJobState = await job.getState();
res.json({
status: newJobState === "failed" ? "cancelled" : "Cancelling...",
});
} catch (error) {
console.error(error);
return res.status(500).json({ error: error.message });
}
}

37
apps/api/src/controllers/crawl-status.ts
View File

@ -1,37 +0,0 @@
import { Request, Response } from "express";
import { authenticateUser } from "./auth";
import { RateLimiterMode } from "../../src/types";
import { addWebScraperJob } from "../../src/services/queue-jobs";
import { getWebScraperQueue } from "../../src/services/queue-service";
export async function crawlStatusController(req: Request, res: Response) {
try {
const { success, team_id, error, status } = await authenticateUser(
req,
res,
RateLimiterMode.CrawlStatus
);
if (!success) {
return res.status(status).json({ error });
}
const job = await getWebScraperQueue().getJob(req.params.jobId);
if (!job) {
return res.status(404).json({ error: "Job not found" });
}
const { current, current_url, total, current_step, partialDocs } = await job.progress();
res.json({
status: await job.getState(),
// progress: job.progress(),
current: current,
current_url: current_url,
current_step: current_step,
total: total,
data: job.returnvalue,
partial_data: partialDocs ?? [],
});
} catch (error) {
console.error(error);
return res.status(500).json({ error: error.message });
}
}

111
apps/api/src/controllers/crawl.ts
View File

@ -1,111 +0,0 @@
import { Request, Response } from "express";
import { WebScraperDataProvider } from "../../src/scraper/WebScraper";
import { billTeam } from "../../src/services/billing/credit_billing";
import { checkTeamCredits } from "../../src/services/billing/credit_billing";
import { authenticateUser } from "./auth";
import { RateLimiterMode } from "../../src/types";
import { addWebScraperJob } from "../../src/services/queue-jobs";
import { isUrlBlocked } from "../../src/scraper/WebScraper/utils/blocklist";
import { logCrawl } from "../../src/services/logging/crawl_log";
import { validateIdempotencyKey } from "../../src/services/idempotency/validate";
import { createIdempotencyKey } from "../../src/services/idempotency/create";
export async function crawlController(req: Request, res: Response) {
try {
const { success, team_id, error, status } = await authenticateUser(
req,
res,
RateLimiterMode.Crawl
);
if (!success) {
return res.status(status).json({ error });
}
if (req.headers["x-idempotency-key"]) {
const isIdempotencyValid = await validateIdempotencyKey(req);
if (!isIdempotencyValid) {
return res.status(409).json({ error: "Idempotency key already used" });
}
try {
createIdempotencyKey(req);
} catch (error) {
console.error(error);
return res.status(500).json({ error: error.message });
}
}
const { success: creditsCheckSuccess, message: creditsCheckMessage } =
await checkTeamCredits(team_id, 1);
if (!creditsCheckSuccess) {
return res.status(402).json({ error: "Insufficient credits" });
}
const url = req.body.url;
if (!url) {
return res.status(400).json({ error: "Url is required" });
}
if (isUrlBlocked(url)) {
return res
.status(403)
.json({
error:
"Firecrawl currently does not support social media scraping due to policy restrictions. We're actively working on building support for it.",
});
}
const mode = req.body.mode ?? "crawl";
const crawlerOptions = req.body.crawlerOptions ?? {
allowBackwardCrawling: false
};
const pageOptions = req.body.pageOptions ?? {
onlyMainContent: false,
includeHtml: false,
removeTags: []
};
if (mode === "single_urls" && !url.includes(",")) {
try {
const a = new WebScraperDataProvider();
await a.setOptions({
mode: "single_urls",
urls: [url],
crawlerOptions: { ...crawlerOptions, returnOnlyUrls: true },
pageOptions: pageOptions,
});
const docs = await a.getDocuments(false, (progress) => {
job.progress({
current: progress.current,
total: progress.total,
current_step: "SCRAPING",
current_url: progress.currentDocumentUrl,
});
});
return res.json({
success: true,
documents: docs,
});
} catch (error) {
console.error(error);
return res.status(500).json({ error: error.message });
}
}
const job = await addWebScraperJob({
url: url,
mode: mode ?? "crawl", // fix for single urls not working
crawlerOptions: crawlerOptions,
team_id: team_id,
pageOptions: pageOptions,
origin: req.body.origin ?? "api",
});
await logCrawl(job.id.toString(), team_id);
res.json({ jobId: job.id });
} catch (error) {
console.error(error);
return res.status(500).json({ error: error.message });
}
}

45
apps/api/src/controllers/crawlPreview.ts
View File

@ -1,45 +0,0 @@
import { Request, Response } from "express";
import { authenticateUser } from "./auth";
import { RateLimiterMode } from "../../src/types";
import { addWebScraperJob } from "../../src/services/queue-jobs";
import { isUrlBlocked } from "../../src/scraper/WebScraper/utils/blocklist";
export async function crawlPreviewController(req: Request, res: Response) {
try {
const { success, team_id, error, status } = await authenticateUser(
req,
res,
RateLimiterMode.Preview
);
if (!success) {
return res.status(status).json({ error });
}
// authenticate on supabase
const url = req.body.url;
if (!url) {
return res.status(400).json({ error: "Url is required" });
}
if (isUrlBlocked(url)) {
return res.status(403).json({ error: "Firecrawl currently does not support social media scraping due to policy restrictions. We're actively working on building support for it." });
}
const mode = req.body.mode ?? "crawl";
const crawlerOptions = req.body.crawlerOptions ?? {};
const pageOptions = req.body.pageOptions ?? { onlyMainContent: false, includeHtml: false, removeTags: [] };
const job = await addWebScraperJob({
url: url,
mode: mode ?? "crawl", // fix for single urls not working
crawlerOptions: { ...crawlerOptions, limit: 5, maxCrawledLinks: 5 },
team_id: "preview",
pageOptions: pageOptions,
origin: "website-preview",
});
res.json({ jobId: job.id });
} catch (error) {
console.error(error);
return res.status(500).json({ error: error.message });
}
}

162
apps/api/src/controllers/scrape.ts
View File

@ -1,162 +0,0 @@
import { ExtractorOptions, PageOptions } from './../lib/entities';
import { Request, Response } from "express";
import { WebScraperDataProvider } from "../scraper/WebScraper";
import { billTeam, checkTeamCredits } from "../services/billing/credit_billing";
import { authenticateUser } from "./auth";
import { RateLimiterMode } from "../types";
import { logJob } from "../services/logging/log_job";
import { Document } from "../lib/entities";
import { isUrlBlocked } from "../scraper/WebScraper/utils/blocklist"; // Import the isUrlBlocked function
import { numTokensFromString } from '../lib/LLM-extraction/helpers';
export async function scrapeHelper(
req: Request,
team_id: string,
crawlerOptions: any,
pageOptions: PageOptions,
extractorOptions: ExtractorOptions,
timeout: number,
plan?: string
): Promise<{
success: boolean;
error?: string;
data?: Document;
returnCode: number;
}> {
const url = req.body.url;
if (!url) {
return { success: false, error: "Url is required", returnCode: 400 };
}
if (isUrlBlocked(url)) {
return { success: false, error: "Firecrawl currently does not support social media scraping due to policy restrictions. We're actively working on building support for it.", returnCode: 403 };
}
const a = new WebScraperDataProvider();
await a.setOptions({
mode: "single_urls",
urls: [url],
crawlerOptions: {
...crawlerOptions,
},
pageOptions: pageOptions,
extractorOptions: extractorOptions,
});
const timeoutPromise = new Promise<{ success: boolean; error?: string; returnCode: number }>((_, reject) =>
setTimeout(() => reject({ success: false, error: "Request timed out. Increase the timeout by passing `timeout` param to the request.", returnCode: 408 }), timeout)
);
const docsPromise = a.getDocuments(false);
let docs;
try {
docs = await Promise.race([docsPromise, timeoutPromise]);
} catch (error) {
return error;
}
// make sure doc.content is not empty
const filteredDocs = docs.filter(
(doc: { content?: string }) => doc.content && doc.content.trim().length > 0
);
if (filteredDocs.length === 0) {
return { success: true, error: "No page found", returnCode: 200 };
}
let creditsToBeBilled = filteredDocs.length;
const creditsPerLLMExtract = 50;
if (extractorOptions.mode === "llm-extraction") {
creditsToBeBilled = creditsToBeBilled + (creditsPerLLMExtract * filteredDocs.length);
}
const billingResult = await billTeam(
team_id,
creditsToBeBilled
);
if (!billingResult.success) {
return {
success: false,
error:
"Failed to bill team. Insufficient credits or subscription not found.",
returnCode: 402,
};
}
return {
success: true,
data: filteredDocs[0],
returnCode: 200,
};
}
export async function scrapeController(req: Request, res: Response) {
try {
// make sure to authenticate user first, Bearer <token>
const { success, team_id, error, status, plan } = await authenticateUser(
req,
res,
RateLimiterMode.Scrape
);
if (!success) {
return res.status(status).json({ error });
}
const crawlerOptions = req.body.crawlerOptions ?? {};
const pageOptions = req.body.pageOptions ?? { onlyMainContent: false, includeHtml: false, waitFor: 0, screenshot: false };
const extractorOptions = req.body.extractorOptions ?? {
mode: "markdown"
}
if (extractorOptions.mode === "llm-extraction") {
pageOptions.onlyMainContent = true;
}
const origin = req.body.origin ?? "api";
const timeout = req.body.timeout ?? 30000; // Default timeout of 30 seconds
try {
const { success: creditsCheckSuccess, message: creditsCheckMessage } =
await checkTeamCredits(team_id, 1);
if (!creditsCheckSuccess) {
return res.status(402).json({ error: "Insufficient credits" });
}
} catch (error) {
console.error(error);
return res.status(500).json({ error: "Internal server error" });
}
const startTime = new Date().getTime();
const result = await scrapeHelper(
req,
team_id,
crawlerOptions,
pageOptions,
extractorOptions,
timeout,
plan
);
const endTime = new Date().getTime();
const timeTakenInSeconds = (endTime - startTime) / 1000;
const numTokens = (result.data && result.data.markdown) ? numTokensFromString(result.data.markdown, "gpt-3.5-turbo") : 0;
logJob({
success: result.success,
message: result.error,
num_docs: 1,
docs: [result.data],
time_taken: timeTakenInSeconds,
team_id: team_id,
mode: "scrape",
url: req.body.url,
crawlerOptions: crawlerOptions,
pageOptions: pageOptions,
origin: origin,
extractor_options: extractorOptions,
num_tokens: numTokens,
});
return res.status(result.returnCode).json(result);
} catch (error) {
console.error(error);
return res.status(500).json({ error: error.message });
}
}

26
apps/api/src/controllers/status.ts
View File

@ -1,26 +0,0 @@
import { Request, Response } from "express";
import { getWebScraperQueue } from "../../src/services/queue-service";
export async function crawlJobStatusPreviewController(req: Request, res: Response) {
try {
const job = await getWebScraperQueue().getJob(req.params.jobId);
if (!job) {
return res.status(404).json({ error: "Job not found" });
}
const { current, current_url, total, current_step, partialDocs } = await job.progress();
res.json({
status: await job.getState(),
// progress: job.progress(),
current: current,
current_url: current_url,
current_step: current_step,
total: total,
data: job.returnvalue,
partial_data: partialDocs ?? [],
});
} catch (error) {
console.error(error);
return res.status(500).json({ error: error.message });
}
}

22
apps/api/src/controllers/v0/admin/acuc-cache-clear.ts Normal file
View File

@ -0,0 +1,22 @@
import { Request, Response } from "express";
import { supabase_service } from "../../../services/supabase";
import { clearACUC } from "../../auth";
import { Logger } from "../../../lib/logger";
export async function acucCacheClearController(req: Request, res: Response) {
try {
const team_id: string = req.body.team_id;
const keys = await supabase_service
.from("api_keys")
.select("*")
.eq("team_id", team_id);
await Promise.all(keys.data.map((x) => clearACUC(x.key)));
res.json({ ok: true });
} catch (error) {
Logger.error(`Error clearing ACUC cache via API route: ${error}`);
res.status(500).json({ error: "Internal server error" });
}
}

199
apps/api/src/controllers/v0/admin/queue.ts Normal file
View File

@ -0,0 +1,199 @@
import { Request, Response } from "express";
import { Job } from "bullmq";
import { Logger } from "../../../lib/logger";
import { getScrapeQueue } from "../../../services/queue-service";
import { checkAlerts } from "../../../services/alerts";
import { sendSlackWebhook } from "../../../services/alerts/slack";
export async function cleanBefore24hCompleteJobsController(
req: Request,
res: Response
) {
Logger.info("🐂 Cleaning jobs older than 24h");
try {
const scrapeQueue = getScrapeQueue();
const batchSize = 10;
const numberOfBatches = 9; // Adjust based on your needs
const completedJobsPromises: Promise<Job[]>[] = [];
for (let i = 0; i < numberOfBatches; i++) {
completedJobsPromises.push(
scrapeQueue.getJobs(
["completed"],
i * batchSize,
i * batchSize + batchSize,
true
)
);
}
const completedJobs: Job[] = (
await Promise.all(completedJobsPromises)
).flat();
const before24hJobs =
completedJobs.filter(
(job) => job.finishedOn < Date.now() - 24 * 60 * 60 * 1000
) || [];
let count = 0;
if (!before24hJobs) {
return res.status(200).send(`No jobs to remove.`);
}
for (const job of before24hJobs) {
try {
await job.remove();
count++;
} catch (jobError) {
Logger.error(`🐂 Failed to remove job with ID ${job.id}: ${jobError}`);
}
}
return res.status(200).send(`Removed ${count} completed jobs.`);
} catch (error) {
Logger.error(`🐂 Failed to clean last 24h complete jobs: ${error}`);
return res.status(500).send("Failed to clean jobs");
}
}
export async function checkQueuesController(req: Request, res: Response) {
try {
await checkAlerts();
return res.status(200).send("Alerts initialized");
} catch (error) {
Logger.debug(`Failed to initialize alerts: ${error}`);
return res.status(500).send("Failed to initialize alerts");
}
}
// Use this as a "health check" that way we dont destroy the server
export async function queuesController(req: Request, res: Response) {
try {
const scrapeQueue = getScrapeQueue();
const [webScraperActive] = await Promise.all([
scrapeQueue.getActiveCount(),
]);
const noActiveJobs = webScraperActive === 0;
// 200 if no active jobs, 503 if there are active jobs
return res.status(noActiveJobs ? 200 : 500).json({
webScraperActive,
noActiveJobs,
});
} catch (error) {
Logger.error(error);
return res.status(500).json({ error: error.message });
}
}
export async function autoscalerController(req: Request, res: Response) {
try {
const maxNumberOfMachines = 80;
const minNumberOfMachines = 20;
const scrapeQueue = getScrapeQueue();
const [webScraperActive, webScraperWaiting, webScraperPriority] =
await Promise.all([
scrapeQueue.getActiveCount(),
scrapeQueue.getWaitingCount(),
scrapeQueue.getPrioritizedCount(),
]);
let waitingAndPriorityCount = webScraperWaiting + webScraperPriority;
// get number of machines active
const request = await fetch(
"https://api.machines.dev/v1/apps/firecrawl-scraper-js/machines",
{
headers: {
Authorization: `Bearer ${process.env.FLY_API_TOKEN}`,
},
}
);
const machines = await request.json();
// Only worker machines
const activeMachines = machines.filter(
(machine) =>
(machine.state === "started" ||
machine.state === "starting" ||
machine.state === "replacing") &&
machine.config.env["FLY_PROCESS_GROUP"] === "worker"
).length;
let targetMachineCount = activeMachines;
const baseScaleUp = 10;
// Slow scale down
const baseScaleDown = 2;
// Scale up logic
if (webScraperActive > 9000 || waitingAndPriorityCount > 2000) {
targetMachineCount = Math.min(
maxNumberOfMachines,
activeMachines + baseScaleUp * 3
);
} else if (webScraperActive > 5000 || waitingAndPriorityCount > 1000) {
targetMachineCount = Math.min(
maxNumberOfMachines,
activeMachines + baseScaleUp * 2
);
} else if (webScraperActive > 1000 || waitingAndPriorityCount > 500) {
targetMachineCount = Math.min(
maxNumberOfMachines,
activeMachines + baseScaleUp
);
}
// Scale down logic
if (webScraperActive < 100 && waitingAndPriorityCount < 50) {
targetMachineCount = Math.max(
minNumberOfMachines,
activeMachines - baseScaleDown * 3
);
} else if (webScraperActive < 500 && waitingAndPriorityCount < 200) {
targetMachineCount = Math.max(
minNumberOfMachines,
activeMachines - baseScaleDown * 2
);
} else if (webScraperActive < 1000 && waitingAndPriorityCount < 500) {
targetMachineCount = Math.max(
minNumberOfMachines,
activeMachines - baseScaleDown
);
}
if (targetMachineCount !== activeMachines) {
Logger.info(
`🐂 Scaling from ${activeMachines} to ${targetMachineCount} - ${webScraperActive} active, ${webScraperWaiting} waiting`
);
if (targetMachineCount > activeMachines) {
sendSlackWebhook(
`🐂 Scaling from ${activeMachines} to ${targetMachineCount} - ${webScraperActive} active, ${webScraperWaiting} waiting - Current DateTime: ${new Date().toISOString()}`,
false,
process.env.SLACK_AUTOSCALER ?? ""
);
} else {
sendSlackWebhook(
`🐂 Scaling from ${activeMachines} to ${targetMachineCount} - ${webScraperActive} active, ${webScraperWaiting} waiting - Current DateTime: ${new Date().toISOString()}`,
false,
process.env.SLACK_AUTOSCALER ?? ""
);
}
return res.status(200).json({
mode: "scale-descale",
count: targetMachineCount,
});
}
return res.status(200).json({
mode: "normal",
count: activeMachines,
});
} catch (error) {
Logger.error(error);
return res.status(500).send("Failed to initialize autoscaler");
}
}

85
apps/api/src/controllers/v0/admin/redis-health.ts Normal file
View File

@ -0,0 +1,85 @@
import { Request, Response } from "express";
import Redis from "ioredis";
import { Logger } from "../../../lib/logger";
import { redisRateLimitClient } from "../../../services/rate-limiter";
export async function redisHealthController(req: Request, res: Response) {
const retryOperation = async (operation, retries = 3) => {
for (let attempt = 1; attempt <= retries; attempt++) {
try {
return await operation();
} catch (error) {
if (attempt === retries) throw error;
Logger.warn(`Attempt ${attempt} failed: ${error.message}. Retrying...`);
await new Promise((resolve) => setTimeout(resolve, 2000)); // Wait 2 seconds before retrying
}
}
};
try {
const queueRedis = new Redis(process.env.REDIS_URL);
const testKey = "test";
const testValue = "test";
// Test queueRedis
let queueRedisHealth;
try {
await retryOperation(() => queueRedis.set(testKey, testValue));
queueRedisHealth = await retryOperation(() => queueRedis.get(testKey));
await retryOperation(() => queueRedis.del(testKey));
} catch (error) {
Logger.error(`queueRedis health check failed: ${error}`);
queueRedisHealth = null;
}
// Test redisRateLimitClient
let redisRateLimitHealth;
try {
await retryOperation(() => redisRateLimitClient.set(testKey, testValue));
redisRateLimitHealth = await retryOperation(() =>
redisRateLimitClient.get(testKey)
);
await retryOperation(() => redisRateLimitClient.del(testKey));
} catch (error) {
Logger.error(`redisRateLimitClient health check failed: ${error}`);
redisRateLimitHealth = null;
}
const healthStatus = {
queueRedis: queueRedisHealth === testValue ? "healthy" : "unhealthy",
redisRateLimitClient:
redisRateLimitHealth === testValue ? "healthy" : "unhealthy",
};
if (
healthStatus.queueRedis === "healthy" &&
healthStatus.redisRateLimitClient === "healthy"
) {
Logger.info("Both Redis instances are healthy");
return res.status(200).json({ status: "healthy", details: healthStatus });
} else {
Logger.info(
`Redis instances health check: ${JSON.stringify(healthStatus)}`
);
// await sendSlackWebhook(
// `[REDIS DOWN] Redis instances health check: ${JSON.stringify(
// healthStatus
// )}`,
// true
// );
return res
.status(500)
.json({ status: "unhealthy", details: healthStatus });
}
} catch (error) {
Logger.error(`Redis health check failed: ${error}`);
// await sendSlackWebhook(
// `[REDIS DOWN] Redis instances health check: ${error.message}`,
// true
// );
return res
.status(500)
.json({ status: "unhealthy", message: error.message });
}
}

60
apps/api/src/controllers/v0/crawl-cancel.ts Normal file
View File

@ -0,0 +1,60 @@
import { Request, Response } from "express";
import { authenticateUser } from "../auth";
import { RateLimiterMode } from "../../../src/types";
import { supabase_service } from "../../../src/services/supabase";
import { Logger } from "../../../src/lib/logger";
import { getCrawl, saveCrawl } from "../../../src/lib/crawl-redis";
import * as Sentry from "@sentry/node";
import { configDotenv } from "dotenv";
configDotenv();
export async function crawlCancelController(req: Request, res: Response) {
try {
const useDbAuthentication = process.env.USE_DB_AUTHENTICATION === 'true';
const { success, team_id, error, status } = await authenticateUser(
req,
res,
RateLimiterMode.CrawlStatus
);
if (!success) {
return res.status(status).json({ error });
}
const sc = await getCrawl(req.params.jobId);
if (!sc) {
return res.status(404).json({ error: "Job not found" });
}
// check if the job belongs to the team
if (useDbAuthentication) {
const { data, error: supaError } = await supabase_service
.from("bulljobs_teams")
.select("*")
.eq("job_id", req.params.jobId)
.eq("team_id", team_id);
if (supaError) {
return res.status(500).json({ error: supaError.message });
}
if (data.length === 0) {
return res.status(403).json({ error: "Unauthorized" });
}
}
try {
sc.cancelled = true;
await saveCrawl(req.params.jobId, sc);
} catch (error) {
Logger.error(error);
}
res.json({
status: "cancelled"
});
} catch (error) {
Sentry.captureException(error);
Logger.error(error);
return res.status(500).json({ error: error.message });
}
}

101
apps/api/src/controllers/v0/crawl-status.ts Normal file
View File

@ -0,0 +1,101 @@
import { Request, Response } from "express";
import { authenticateUser } from "../auth";
import { RateLimiterMode } from "../../../src/types";
import { getScrapeQueue } from "../../../src/services/queue-service";
import { Logger } from "../../../src/lib/logger";
import { getCrawl, getCrawlJobs } from "../../../src/lib/crawl-redis";
import { supabaseGetJobsByCrawlId } from "../../../src/lib/supabase-jobs";
import * as Sentry from "@sentry/node";
import { configDotenv } from "dotenv";
configDotenv();
export async function getJobs(crawlId: string, ids: string[]) {
const jobs = (await Promise.all(ids.map(x => getScrapeQueue().getJob(x)))).filter(x => x);
if (process.env.USE_DB_AUTHENTICATION === "true") {
const supabaseData = await supabaseGetJobsByCrawlId(crawlId);
supabaseData.forEach(x => {
const job = jobs.find(y => y.id === x.job_id);
if (job) {
job.returnvalue = x.docs;
}
})
}
jobs.forEach(job => {
job.returnvalue = Array.isArray(job.returnvalue) ? job.returnvalue[0] : job.returnvalue;
});
return jobs;
}
export async function crawlStatusController(req: Request, res: Response) {
try {
const { success, team_id, error, status } = await authenticateUser(
req,
res,
RateLimiterMode.CrawlStatus
);
if (!success) {
return res.status(status).json({ error });
}
const sc = await getCrawl(req.params.jobId);
if (!sc) {
return res.status(404).json({ error: "Job not found" });
}
if (sc.team_id !== team_id) {
return res.status(403).json({ error: "Forbidden" });
}
let jobIDs = await getCrawlJobs(req.params.jobId);
let jobs = await getJobs(req.params.jobId, jobIDs);
let jobStatuses = await Promise.all(jobs.map(x => x.getState()));
// Combine jobs and jobStatuses into a single array of objects
let jobsWithStatuses = jobs.map((job, index) => ({
job,
status: jobStatuses[index]
}));
// Filter out failed jobs
jobsWithStatuses = jobsWithStatuses.filter(x => x.status !== "failed" && x.status !== "unknown");
// Sort jobs by timestamp
jobsWithStatuses.sort((a, b) => a.job.timestamp - b.job.timestamp);
// Extract sorted jobs and statuses
jobs = jobsWithStatuses.map(x => x.job);
jobStatuses = jobsWithStatuses.map(x => x.status);
const jobStatus = sc.cancelled ? "failed" : jobStatuses.every(x => x === "completed") ? "completed" : "active";
const data = jobs.filter(x => x.failedReason !== "Concurreny limit hit").map(x => Array.isArray(x.returnvalue) ? x.returnvalue[0] : x.returnvalue);
if (
jobs.length > 0 &&
jobs[0].data &&
jobs[0].data.pageOptions &&
!jobs[0].data.pageOptions.includeRawHtml
) {
data.forEach(item => {
if (item) {
delete item.rawHtml;
}
});
}
res.json({
status: jobStatus,
current: jobStatuses.filter(x => x === "completed" || x === "failed").length,
total: jobs.length,
data: jobStatus === "completed" ? data : null,
partial_data: jobStatus === "completed" ? [] : data.filter(x => x !== null),
});
} catch (error) {
Sentry.captureException(error);
Logger.error(error);
return res.status(500).json({ error: error.message });
}
}

232
apps/api/src/controllers/v0/crawl.ts Normal file
View File

@ -0,0 +1,232 @@
import { Request, Response } from "express";
import { checkTeamCredits } from "../../../src/services/billing/credit_billing";
import { authenticateUser } from "../auth";
import { RateLimiterMode } from "../../../src/types";
import { addScrapeJob } from "../../../src/services/queue-jobs";
import { isUrlBlocked } from "../../../src/scraper/WebScraper/utils/blocklist";
import { logCrawl } from "../../../src/services/logging/crawl_log";
import { validateIdempotencyKey } from "../../../src/services/idempotency/validate";
import { createIdempotencyKey } from "../../../src/services/idempotency/create";
import { defaultCrawlPageOptions, defaultCrawlerOptions, defaultOrigin } from "../../../src/lib/default-values";
import { v4 as uuidv4 } from "uuid";
import { Logger } from "../../../src/lib/logger";
import { addCrawlJob, addCrawlJobs, crawlToCrawler, lockURL, lockURLs, saveCrawl, StoredCrawl } from "../../../src/lib/crawl-redis";
import { getScrapeQueue } from "../../../src/services/queue-service";
import { checkAndUpdateURL } from "../../../src/lib/validateUrl";
import * as Sentry from "@sentry/node";
import { getJobPriority } from "../../lib/job-priority";
export async function crawlController(req: Request, res: Response) {
try {
const { success, team_id, error, status, plan, chunk } = await authenticateUser(
req,
res,
RateLimiterMode.Crawl
);
if (!success) {
return res.status(status).json({ error });
}
if (req.headers["x-idempotency-key"]) {
const isIdempotencyValid = await validateIdempotencyKey(req);
if (!isIdempotencyValid) {
return res.status(409).json({ error: "Idempotency key already used" });
}
try {
createIdempotencyKey(req);
} catch (error) {
Logger.error(error);
return res.status(500).json({ error: error.message });
}
}
const crawlerOptions = {
...defaultCrawlerOptions,
...req.body.crawlerOptions,
};
const pageOptions = { ...defaultCrawlPageOptions, ...req.body.pageOptions };
if (Array.isArray(crawlerOptions.includes)) {
for (const x of crawlerOptions.includes) {
try {
new RegExp(x);
} catch (e) {
return res.status(400).json({ error: e.message });
}
}
}
if (Array.isArray(crawlerOptions.excludes)) {
for (const x of crawlerOptions.excludes) {
try {
new RegExp(x);
} catch (e) {
return res.status(400).json({ error: e.message });
}
}
}
const limitCheck = req.body?.crawlerOptions?.limit ?? 1;
const { success: creditsCheckSuccess, message: creditsCheckMessage, remainingCredits } =
await checkTeamCredits(chunk, team_id, limitCheck);
if (!creditsCheckSuccess) {
return res.status(402).json({ error: "Insufficient credits. You may be requesting with a higher limit than the amount of credits you have left. If not, upgrade your plan at https://firecrawl.dev/pricing or contact us at hello@firecrawl.com" });
}
// TODO: need to do this to v1
crawlerOptions.limit = Math.min(remainingCredits, crawlerOptions.limit);
let url = req.body.url;
if (!url) {
return res.status(400).json({ error: "Url is required" });
}
if (typeof url !== "string") {
return res.status(400).json({ error: "URL must be a string" });
}
try {
url = checkAndUpdateURL(url).url;
} catch (e) {
return res
.status(e instanceof Error && e.message === "Invalid URL" ? 400 : 500)
.json({ error: e.message ?? e });
}
if (isUrlBlocked(url)) {
return res.status(403).json({
error:
"Firecrawl currently does not support social media scraping due to policy restrictions. We're actively working on building support for it.",
});
}
// if (mode === "single_urls" && !url.includes(",")) { // NOTE: do we need this?
// try {
// const a = new WebScraperDataProvider();
// await a.setOptions({
// jobId: uuidv4(),
// mode: "single_urls",
// urls: [url],
// crawlerOptions: { ...crawlerOptions, returnOnlyUrls: true },
// pageOptions: pageOptions,
// });
// const docs = await a.getDocuments(false, (progress) => {
// job.updateProgress({
// current: progress.current,
// total: progress.total,
// current_step: "SCRAPING",
// current_url: progress.currentDocumentUrl,
// });
// });
// return res.json({
// success: true,
// documents: docs,
// });
// } catch (error) {
// Logger.error(error);
// return res.status(500).json({ error: error.message });
// }
// }
const id = uuidv4();
await logCrawl(id, team_id);
const sc: StoredCrawl = {
originUrl: url,
crawlerOptions,
pageOptions,
team_id,
plan,
createdAt: Date.now(),
};
const crawler = crawlToCrawler(id, sc);
try {
sc.robots = await crawler.getRobotsTxt();
} catch (_) {}
await saveCrawl(id, sc);
const sitemap = sc.crawlerOptions?.ignoreSitemap
? null
: await crawler.tryGetSitemap();
if (sitemap !== null && sitemap.length > 0) {
let jobPriority = 20;
// If it is over 1000, we need to get the job priority,
// otherwise we can use the default priority of 20
if(sitemap.length > 1000){
// set base to 21
jobPriority = await getJobPriority({plan, team_id, basePriority: 21})
}
const jobs = sitemap.map((x) => {
const url = x.url;
const uuid = uuidv4();
return {
name: uuid,
data: {
url,
mode: "single_urls",
crawlerOptions: crawlerOptions,
team_id,
plan,
pageOptions: pageOptions,
origin: req.body.origin ?? defaultOrigin,
crawl_id: id,
sitemapped: true,
},
opts: {
jobId: uuid,
priority: jobPriority,
},
};
});
await lockURLs(
id,
jobs.map((x) => x.data.url)
);
await addCrawlJobs(
id,
jobs.map((x) => x.opts.jobId)
);
for (const job of jobs) {
// add with sentry instrumentation
await addScrapeJob(job.data as any, {}, job.opts.jobId);
}
} else {
await lockURL(id, sc, url);
// Not needed, first one should be 15.
// const jobPriority = await getJobPriority({plan, team_id, basePriority: 10})
const jobId = uuidv4();
await addScrapeJob(
{
url,
mode: "single_urls",
crawlerOptions: crawlerOptions,
team_id,
plan,
pageOptions: pageOptions,
origin: req.body.origin ?? defaultOrigin,
crawl_id: id,
},
{
priority: 15, // prioritize request 0 of crawl jobs same as scrape jobs
},
jobId,
);
await addCrawlJob(id, jobId);
}
res.json({ jobId: id });
} catch (error) {
Sentry.captureException(error);
Logger.error(error);
return res.status(500).json({ error: error.message });
}
}

142
apps/api/src/controllers/v0/crawlPreview.ts Normal file
View File

@ -0,0 +1,142 @@
import { Request, Response } from "express";
import { authenticateUser } from "../auth";
import { RateLimiterMode } from "../../../src/types";
import { isUrlBlocked } from "../../../src/scraper/WebScraper/utils/blocklist";
import { v4 as uuidv4 } from "uuid";
import { Logger } from "../../../src/lib/logger";
import { addCrawlJob, crawlToCrawler, lockURL, saveCrawl, StoredCrawl } from "../../../src/lib/crawl-redis";
import { addScrapeJob } from "../../../src/services/queue-jobs";
import { checkAndUpdateURL } from "../../../src/lib/validateUrl";
import * as Sentry from "@sentry/node";
export async function crawlPreviewController(req: Request, res: Response) {
try {
const { success, error, status, team_id:a, plan } = await authenticateUser(
req,
res,
RateLimiterMode.Preview
);
const team_id = "preview";
if (!success) {
return res.status(status).json({ error });
}
let url = req.body.url;
if (!url) {
return res.status(400).json({ error: "Url is required" });
}
try {
url = checkAndUpdateURL(url).url;
} catch (e) {
return res
.status(e instanceof Error && e.message === "Invalid URL" ? 400 : 500)
.json({ error: e.message ?? e });
}
if (isUrlBlocked(url)) {
return res
.status(403)
.json({
error:
"Firecrawl currently does not support social media scraping due to policy restrictions. We're actively working on building support for it.",
});
}
const crawlerOptions = req.body.crawlerOptions ?? {};
const pageOptions = req.body.pageOptions ?? { onlyMainContent: false, includeHtml: false, removeTags: [] };
// if (mode === "single_urls" && !url.includes(",")) { // NOTE: do we need this?
// try {
// const a = new WebScraperDataProvider();
// await a.setOptions({
// jobId: uuidv4(),
// mode: "single_urls",
// urls: [url],
// crawlerOptions: { ...crawlerOptions, returnOnlyUrls: true },
// pageOptions: pageOptions,
// });
// const docs = await a.getDocuments(false, (progress) => {
// job.updateProgress({
// current: progress.current,
// total: progress.total,
// current_step: "SCRAPING",
// current_url: progress.currentDocumentUrl,
// });
// });
// return res.json({
// success: true,
// documents: docs,
// });
// } catch (error) {
// Logger.error(error);
// return res.status(500).json({ error: error.message });
// }
// }
const id = uuidv4();
let robots;
try {
robots = await this.getRobotsTxt();
} catch (_) {}
const sc: StoredCrawl = {
originUrl: url,
crawlerOptions,
pageOptions,
team_id,
plan,
robots,
createdAt: Date.now(),
};
await saveCrawl(id, sc);
const crawler = crawlToCrawler(id, sc);
const sitemap = sc.crawlerOptions?.ignoreSitemap ? null : await crawler.tryGetSitemap();
if (sitemap !== null) {
for (const url of sitemap.map(x => x.url)) {
await lockURL(id, sc, url);
const jobId = uuidv4();
await addScrapeJob({
url,
mode: "single_urls",
crawlerOptions: crawlerOptions,
team_id,
plan,
pageOptions: pageOptions,
origin: "website-preview",
crawl_id: id,
sitemapped: true,
}, {}, jobId);
await addCrawlJob(id, jobId);
}
} else {
await lockURL(id, sc, url);
const jobId = uuidv4();
await addScrapeJob({
url,
mode: "single_urls",
crawlerOptions: crawlerOptions,
team_id,
plan,
pageOptions: pageOptions,
origin: "website-preview",
crawl_id: id,
}, {}, jobId);
await addCrawlJob(id, jobId);
}
res.json({ jobId: id });
} catch (error) {
Sentry.captureException(error);
Logger.error(error);
return res.status(500).json({ error: error.message });
}
}

4
apps/api/src/controllers/keyAuth.ts → apps/api/src/controllers/v0/keyAuth.ts
View File

@ -1,8 +1,8 @@
import { AuthResponse, RateLimiterMode } from "../types";
import { AuthResponse, RateLimiterMode } from "../../types";
import { Request, Response } from "express";
import { authenticateUser } from "./auth";
import { authenticateUser } from "../auth";
export const keyAuthController = async (req: Request, res: Response) => {

6
apps/api/src/controllers/v0/liveness.ts Normal file
View File

@ -0,0 +1,6 @@
import { Request, Response } from "express";
export async function livenessController(req: Request, res: Response) {
//TODO: add checks if the application is live and healthy like checking the redis connection
res.status(200).json({ status: "ok" });
}

6
apps/api/src/controllers/v0/readiness.ts Normal file
View File

@ -0,0 +1,6 @@
import { Request, Response } from "express";
export async function readinessController(req: Request, res: Response) {
// TODO: add checks when the application is ready to serve traffic
res.status(200).json({ status: "ok" });
}

296
apps/api/src/controllers/v0/scrape.ts Normal file
View File

@ -0,0 +1,296 @@
import { ExtractorOptions, PageOptions } from "./../../lib/entities";
import { Request, Response } from "express";
import {
billTeam,
checkTeamCredits,
} from "../../services/billing/credit_billing";
import { authenticateUser } from "../auth";
import { PlanType, RateLimiterMode } from "../../types";
import { logJob } from "../../services/logging/log_job";
import { Document } from "../../lib/entities";
import { isUrlBlocked } from "../../scraper/WebScraper/utils/blocklist"; // Import the isUrlBlocked function
import { numTokensFromString } from "../../lib/LLM-extraction/helpers";
import {
defaultPageOptions,
defaultExtractorOptions,
defaultTimeout,
defaultOrigin,
} from "../../lib/default-values";
import { addScrapeJob, waitForJob } from "../../services/queue-jobs";
import { getScrapeQueue } from "../../services/queue-service";
import { v4 as uuidv4 } from "uuid";
import { Logger } from "../../lib/logger";
import * as Sentry from "@sentry/node";
import { getJobPriority } from "../../lib/job-priority";
export async function scrapeHelper(
jobId: string,
req: Request,
team_id: string,
crawlerOptions: any,
pageOptions: PageOptions,
extractorOptions: ExtractorOptions,
timeout: number,
plan?: PlanType
): Promise<{
success: boolean;
error?: string;
data?: Document;
returnCode: number;
}> {
const url = req.body.url;
if (typeof url !== "string") {
return { success: false, error: "Url is required", returnCode: 400 };
}
if (isUrlBlocked(url)) {
return {
success: false,
error:
"Firecrawl currently does not support social media scraping due to policy restrictions. We're actively working on building support for it.",
returnCode: 403,
};
}
const jobPriority = await getJobPriority({ plan, team_id, basePriority: 10 });
await addScrapeJob(
{
url,
mode: "single_urls",
crawlerOptions,
team_id,
pageOptions,
plan,
extractorOptions,
origin: req.body.origin ?? defaultOrigin,
is_scrape: true,
},
{},
jobId,
jobPriority
);
let doc;
const err = await Sentry.startSpan(
{
name: "Wait for job to finish",
op: "bullmq.wait",
attributes: { job: jobId },
},
async (span) => {
try {
doc = (await waitForJob(jobId, timeout))[0];
} catch (e) {
if (e instanceof Error && e.message.startsWith("Job wait")) {
span.setAttribute("timedOut", true);
return {
success: false,
error: "Request timed out",
returnCode: 408,
};
} else if (
typeof e === "string" &&
(e.includes("Error generating completions: ") ||
e.includes("Invalid schema for function") ||
e.includes(
"LLM extraction did not match the extraction schema you provided."
))
) {
return {
success: false,
error: e,
returnCode: 500,
};
} else {
throw e;
}
}
span.setAttribute("result", JSON.stringify(doc));
return null;
}
);
if (err !== null) {
return err;
}
await getScrapeQueue().remove(jobId);
if (!doc) {
console.error("!!! PANIC DOC IS", doc);
return {
success: true,
error: "No page found",
returnCode: 200,
data: doc,
};
}
delete doc.index;
delete doc.provider;
// Remove rawHtml if pageOptions.rawHtml is false and extractorOptions.mode is llm-extraction-from-raw-html
if (
!pageOptions.includeRawHtml &&
extractorOptions.mode == "llm-extraction-from-raw-html"
) {
if (doc.rawHtml) {
delete doc.rawHtml;
}
}
if (!pageOptions.includeHtml) {
if (doc.html) {
delete doc.html;
}
}
return {
success: true,
data: doc,
returnCode: 200,
};
}
export async function scrapeController(req: Request, res: Response) {
try {
let earlyReturn = false;
// make sure to authenticate user first, Bearer <token>
const { success, team_id, error, status, plan, chunk } = await authenticateUser(
req,
res,
RateLimiterMode.Scrape
);
if (!success) {
return res.status(status).json({ error });
}
const crawlerOptions = req.body.crawlerOptions ?? {};
const pageOptions = { ...defaultPageOptions, ...req.body.pageOptions };
const extractorOptions = {
...defaultExtractorOptions,
...req.body.extractorOptions,
};
const origin = req.body.origin ?? defaultOrigin;
let timeout = req.body.timeout ?? defaultTimeout;
if (extractorOptions.mode.includes("llm-extraction")) {
if (
typeof extractorOptions.extractionSchema !== "object" ||
extractorOptions.extractionSchema === null
) {
return res.status(400).json({
error:
"extractorOptions.extractionSchema must be an object if llm-extraction mode is specified",
});
}
pageOptions.onlyMainContent = true;
timeout = req.body.timeout ?? 90000;
}
// checkCredits
try {
const { success: creditsCheckSuccess, message: creditsCheckMessage } =
await checkTeamCredits(chunk, team_id, 1);
if (!creditsCheckSuccess) {
earlyReturn = true;
return res.status(402).json({ error: "Insufficient credits. For more credits, you can upgrade your plan at https://firecrawl.dev/pricing" });
}
} catch (error) {
Logger.error(error);
earlyReturn = true;
return res.status(500).json({
error:
"Error checking team credits. Please contact hello@firecrawl.com for help.",
});
}
const jobId = uuidv4();
const startTime = new Date().getTime();
const result = await scrapeHelper(
jobId,
req,
team_id,
crawlerOptions,
pageOptions,
extractorOptions,
timeout,
plan
);
const endTime = new Date().getTime();
const timeTakenInSeconds = (endTime - startTime) / 1000;
const numTokens =
result.data && result.data.markdown
? numTokensFromString(result.data.markdown, "gpt-3.5-turbo")
: 0;
if (result.success) {
let creditsToBeBilled = 1;
const creditsPerLLMExtract = 4;
if (extractorOptions.mode.includes("llm-extraction")) {
// creditsToBeBilled = creditsToBeBilled + (creditsPerLLMExtract * filteredDocs.length);
creditsToBeBilled += creditsPerLLMExtract;
}
let startTimeBilling = new Date().getTime();
if (earlyReturn) {
// Don't bill if we're early returning
return;
}
if (creditsToBeBilled > 0) {
// billing for doc done on queue end, bill only for llm extraction
billTeam(team_id, chunk?.sub_id, creditsToBeBilled).catch(error => {
Logger.error(`Failed to bill team ${team_id} for ${creditsToBeBilled} credits: ${error}`);
// Optionally, you could notify an admin or add to a retry queue here
});
}
}
let doc = result.data;
if (!pageOptions || !pageOptions.includeRawHtml) {
if (doc && doc.rawHtml) {
delete doc.rawHtml;
}
}
if(pageOptions && pageOptions.includeExtract) {
if(!pageOptions.includeMarkdown && doc && doc.markdown) {
delete doc.markdown;
}
}
logJob({
job_id: jobId,
success: result.success,
message: result.error,
num_docs: 1,
docs: [doc],
time_taken: timeTakenInSeconds,
team_id: team_id,
mode: "scrape",
url: req.body.url,
crawlerOptions: crawlerOptions,
pageOptions: pageOptions,
origin: origin,
extractor_options: extractorOptions,
num_tokens: numTokens,
});
return res.status(result.returnCode).json(result);
} catch (error) {
Sentry.captureException(error);
Logger.error(error);
return res.status(500).json({
error:
typeof error === "string"
? error
: error?.message ?? "Internal Server Error",
});
}
}

141
apps/api/src/controllers/search.ts → apps/api/src/controllers/v0/search.ts
View File

@ -1,19 +1,28 @@
import { Request, Response } from "express";
import { WebScraperDataProvider } from "../scraper/WebScraper";
import { billTeam, checkTeamCredits } from "../services/billing/credit_billing";
import { authenticateUser } from "./auth";
import { RateLimiterMode } from "../types";
import { logJob } from "../services/logging/log_job";
import { PageOptions, SearchOptions } from "../lib/entities";
import { search } from "../search";
import { isUrlBlocked } from "../scraper/WebScraper/utils/blocklist";
import { WebScraperDataProvider } from "../../scraper/WebScraper";
import { billTeam, checkTeamCredits } from "../../services/billing/credit_billing";
import { authenticateUser } from "../auth";
import { PlanType, RateLimiterMode } from "../../types";
import { logJob } from "../../services/logging/log_job";
import { PageOptions, SearchOptions } from "../../lib/entities";
import { search } from "../../search";
import { isUrlBlocked } from "../../scraper/WebScraper/utils/blocklist";
import { v4 as uuidv4 } from "uuid";
import { Logger } from "../../lib/logger";
import { getScrapeQueue } from "../../services/queue-service";
import { addScrapeJob, waitForJob } from "../../services/queue-jobs";
import * as Sentry from "@sentry/node";
import { getJobPriority } from "../../lib/job-priority";
export async function searchHelper(
jobId: string,
req: Request,
team_id: string,
subscription_id: string,
crawlerOptions: any,
pageOptions: PageOptions,
searchOptions: SearchOptions,
plan: PlanType
): Promise<{
success: boolean;
error?: string;
@ -28,7 +37,12 @@ export async function searchHelper(
const tbs = searchOptions.tbs ?? null;
const filter = searchOptions.filter ?? null;
const num_results = searchOptions.limit ?? 7;
let num_results = Math.min(searchOptions.limit ?? 7, 10);
if (team_id === "d97c4ceb-290b-4957-8432-2b2a02727d95") {
num_results = 1;
}
const num_results_buffer = Math.floor(num_results * 1.5);
let res = await search({
@ -46,18 +60,10 @@ export async function searchHelper(
if (justSearch) {
const billingResult = await billTeam(
team_id,
res.length
);
if (!billingResult.success) {
return {
success: false,
error:
"Failed to bill team. Insufficient credits or subscription not found.",
returnCode: 402,
};
}
billTeam(team_id, subscription_id, res.length).catch(error => {
Logger.error(`Failed to bill team ${team_id} for ${res.length} credits: ${error}`);
// Optionally, you could notify an admin or add to a retry queue here
});
return { success: true, data: res, returnCode: 200 };
}
@ -70,51 +76,50 @@ export async function searchHelper(
return { success: true, error: "No search results found", returnCode: 200 };
}
const jobPriority = await getJobPriority({plan, team_id, basePriority: 20});
// filter out social media links
const a = new WebScraperDataProvider();
await a.setOptions({
const jobDatas = res.map(x => {
const url = x.url;
const uuid = uuidv4();
return {
name: uuid,
data: {
url,
mode: "single_urls",
urls: res.map((r) => r.url).slice(0, searchOptions.limit ?? 7),
crawlerOptions: {
...crawlerOptions,
crawlerOptions: crawlerOptions,
team_id: team_id,
pageOptions: pageOptions,
},
pageOptions: {
...pageOptions,
onlyMainContent: pageOptions?.onlyMainContent ?? true,
fetchPageContent: pageOptions?.fetchPageContent ?? true,
includeHtml: pageOptions?.includeHtml ?? false,
removeTags: pageOptions?.removeTags ?? [],
fallback: false,
},
});
opts: {
jobId: uuid,
priority: jobPriority,
}
};
})
// TODO: addScrapeJobs
for (const job of jobDatas) {
await addScrapeJob(job.data as any, {}, job.opts.jobId, job.opts.priority)
}
const docs = (await Promise.all(jobDatas.map(x => waitForJob(x.opts.jobId, 60000)))).map(x => x[0]);
const docs = await a.getDocuments(false);
if (docs.length === 0) {
return { success: true, error: "No search results found", returnCode: 200 };
}
const sq = getScrapeQueue();
await Promise.all(jobDatas.map(x => sq.remove(x.opts.jobId)));
// make sure doc.content is not empty
const filteredDocs = docs.filter(
(doc: { content?: string }) => doc.content && doc.content.trim().length > 0
(doc: { content?: string }) => doc && doc.content && doc.content.trim().length > 0
);
if (filteredDocs.length === 0) {
return { success: true, error: "No page found", returnCode: 200 };
}
const billingResult = await billTeam(
team_id,
filteredDocs.length
);
if (!billingResult.success) {
return {
success: false,
error:
"Failed to bill team. Insufficient credits or subscription not found.",
returnCode: 402,
};
return { success: true, error: "No page found", returnCode: 200, data: docs };
}
return {
@ -127,7 +132,7 @@ export async function searchHelper(
export async function searchController(req: Request, res: Response) {
try {
// make sure to authenticate user first, Bearer <token>
const { success, team_id, error, status } = await authenticateUser(
const { success, team_id, error, status, plan, chunk } = await authenticateUser(
req,
res,
RateLimiterMode.Search
@ -137,37 +142,44 @@ export async function searchController(req: Request, res: Response) {
}
const crawlerOptions = req.body.crawlerOptions ?? {};
const pageOptions = req.body.pageOptions ?? {
includeHtml: false,
onlyMainContent: true,
fetchPageContent: true,
removeTags: [],
fallback: false,
includeHtml: req.body.pageOptions?.includeHtml ?? false,
onlyMainContent: req.body.pageOptions?.onlyMainContent ?? false,
fetchPageContent: req.body.pageOptions?.fetchPageContent ?? true,
removeTags: req.body.pageOptions?.removeTags ?? [],
fallback: req.body.pageOptions?.fallback ?? false,
};
const origin = req.body.origin ?? "api";
const searchOptions = req.body.searchOptions ?? { limit: 7 };
const searchOptions = req.body.searchOptions ?? { limit: 5 };
const jobId = uuidv4();
try {
const { success: creditsCheckSuccess, message: creditsCheckMessage } =
await checkTeamCredits(team_id, 1);
await checkTeamCredits(chunk, team_id, 1);
if (!creditsCheckSuccess) {
return res.status(402).json({ error: "Insufficient credits" });
}
} catch (error) {
console.error(error);
Sentry.captureException(error);
Logger.error(error);
return res.status(500).json({ error: "Internal server error" });
}
const startTime = new Date().getTime();
const result = await searchHelper(
jobId,
req,
team_id,
chunk?.sub_id,
crawlerOptions,
pageOptions,
searchOptions,
plan
);
const endTime = new Date().getTime();
const timeTakenInSeconds = (endTime - startTime) / 1000;
logJob({
job_id: jobId,
success: result.success,
message: result.error,
num_docs: result.data ? result.data.length : 0,
@ -182,7 +194,12 @@ export async function searchController(req: Request, res: Response) {
});
return res.status(result.returnCode).json(result);
} catch (error) {
console.error(error);
if (error instanceof Error && error.message.startsWith("Job wait")) {
return res.status(408).json({ error: "Request timed out" });
}
Sentry.captureException(error);
Logger.error(error);
return res.status(500).json({ error: error.message });
}
}

43
apps/api/src/controllers/v0/status.ts Normal file
View File

@ -0,0 +1,43 @@
import { Request, Response } from "express";
import { Logger } from "../../../src/lib/logger";
import { getCrawl, getCrawlJobs } from "../../../src/lib/crawl-redis";
import { getJobs } from "./crawl-status";
import * as Sentry from "@sentry/node";
export async function crawlJobStatusPreviewController(req: Request, res: Response) {
try {
const sc = await getCrawl(req.params.jobId);
if (!sc) {
return res.status(404).json({ error: "Job not found" });
}
const jobIDs = await getCrawlJobs(req.params.jobId);
// let data = job.returnvalue;
// if (process.env.USE_DB_AUTHENTICATION === "true") {
// const supabaseData = await supabaseGetJobById(req.params.jobId);
// if (supabaseData) {
// data = supabaseData.docs;
// }
// }
const jobs = (await getJobs(req.params.jobId, jobIDs)).sort((a, b) => a.timestamp - b.timestamp);
const jobStatuses = await Promise.all(jobs.map(x => x.getState()));
const jobStatus = sc.cancelled ? "failed" : jobStatuses.every(x => x === "completed") ? "completed" : jobStatuses.some(x => x === "failed") ? "failed" : "active";
const data = jobs.map(x => Array.isArray(x.returnvalue) ? x.returnvalue[0] : x.returnvalue);
res.json({
status: jobStatus,
current: jobStatuses.filter(x => x === "completed" || x === "failed").length,
total: jobs.length,
data: jobStatus === "completed" ? data : null,
partial_data: jobStatus === "completed" ? [] : data.filter(x => x !== null),
});
} catch (error) {
Sentry.captureException(error);
Logger.error(error);
return res.status(500).json({ error: error.message });
}
}

47
apps/api/src/controllers/v1/__tests__/crawl.test.ts.WIP Normal file
View File

@ -0,0 +1,47 @@
import { crawlController } from '../crawl'
import { Request, Response } from 'express';
import { authenticateUser } from '../auth'; // Ensure this import is correct
import { createIdempotencyKey } from '../../services/idempotency/create';
import { validateIdempotencyKey } from '../../services/idempotency/validate';
import { v4 as uuidv4 } from 'uuid';
jest.mock('../auth', () => ({
authenticateUser: jest.fn().mockResolvedValue({
success: true,
team_id: 'team123',
error: null,
status: 200
}),
reduce: jest.fn()
}));
jest.mock('../../services/idempotency/validate');
describe('crawlController', () => {
it('should prevent duplicate requests using the same idempotency key', async () => {
const req = {
headers: {
'x-idempotency-key': await uuidv4(),
'Authorization': `Bearer ${process.env.TEST_API_KEY}`
},
body: {
url: 'https://mendable.ai'
}
} as unknown as Request;
const res = {
status: jest.fn().mockReturnThis(),
json: jest.fn()
} as unknown as Response;
// Mock the idempotency key validation to return false for the second call
(validateIdempotencyKey as jest.Mock).mockResolvedValueOnce(true).mockResolvedValueOnce(false);
// First request should succeed
await crawlController(req, res);
expect(res.status).not.toHaveBeenCalledWith(409);
// Second request with the same key should fail
await crawlController(req, res);
expect(res.status).toHaveBeenCalledWith(409);
expect(res.json).toHaveBeenCalledWith({ error: 'Idempotency key already used' });
});
});

64
apps/api/src/controllers/v1/__tests__/urlValidation.test.ts Normal file
View File

@ -0,0 +1,64 @@
import { url } from "../types";
describe("URL Schema Validation", () => {
beforeEach(() => {
jest.resetAllMocks();
});
it("should prepend http:// to URLs without a protocol", () => {
const result = url.parse("example.com");
expect(result).toBe("http://example.com");
});
it("should allow valid URLs with http or https", () => {
expect(() => url.parse("http://example.com")).not.toThrow();
expect(() => url.parse("https://example.com")).not.toThrow();
});
it("should allow valid URLs with http or https", () => {
expect(() => url.parse("example.com")).not.toThrow();
});
it("should reject URLs with unsupported protocols", () => {
expect(() => url.parse("ftp://example.com")).toThrow("Invalid URL");
});
it("should reject URLs without a valid top-level domain", () => {
expect(() => url.parse("http://example")).toThrow("URL must have a valid top-level domain or be a valid path");
});
it("should reject blocked URLs", () => {
expect(() => url.parse("https://facebook.com")).toThrow("Firecrawl currently does not support social media scraping due to policy restrictions. We're actively working on building support for it.");
});
it("should handle URLs with subdomains correctly", () => {
expect(() => url.parse("http://sub.example.com")).not.toThrow();
expect(() => url.parse("https://blog.example.com")).not.toThrow();
});
it("should handle URLs with paths correctly", () => {
expect(() => url.parse("http://example.com/path")).not.toThrow();
expect(() => url.parse("https://example.com/another/path")).not.toThrow();
});
it("should handle URLs with subdomains that are blocked", () => {
expect(() => url.parse("https://sub.facebook.com")).toThrow("Firecrawl currently does not support social media scraping due to policy restrictions. We're actively working on building support for it.");
});
it("should handle URLs with paths that are blocked", () => {
expect(() => url.parse("http://facebook.com/path")).toThrow("Firecrawl currently does not support social media scraping due to policy restrictions. We're actively working on building support for it.");
expect(() => url.parse("https://facebook.com/another/path")).toThrow("Firecrawl currently does not support social media scraping due to policy restrictions. We're actively working on building support for it.");
});
it("should reject malformed URLs starting with 'http://http'", () => {
expect(() => url.parse("http://http://example.com")).toThrow("Invalid URL. Invalid protocol.");
});
it("should reject malformed URLs containing multiple 'http://'", () => {
expect(() => url.parse("http://example.com/http://example.com")).not.toThrow();
});
it("should reject malformed URLs containing multiple 'http://'", () => {
expect(() => url.parse("http://ex ample.com/")).toThrow("Invalid URL");
});
})

102
apps/api/src/controllers/v1/batch-scrape.ts Normal file
View File

@ -0,0 +1,102 @@
import { Response } from "express";
import { v4 as uuidv4 } from "uuid";
import {
BatchScrapeRequest,
batchScrapeRequestSchema,
CrawlResponse,
legacyExtractorOptions,
legacyScrapeOptions,
RequestWithAuth,
} from "./types";
import {
addCrawlJobs,
lockURLs,
saveCrawl,
StoredCrawl,
} from "../../lib/crawl-redis";
import { logCrawl } from "../../services/logging/crawl_log";
import { getScrapeQueue } from "../../services/queue-service";
import { getJobPriority } from "../../lib/job-priority";
import { addScrapeJobs } from "../../services/queue-jobs";
export async function batchScrapeController(
req: RequestWithAuth<{}, CrawlResponse, BatchScrapeRequest>,
res: Response<CrawlResponse>
) {
req.body = batchScrapeRequestSchema.parse(req.body);
const id = uuidv4();
await logCrawl(id, req.auth.team_id);
let { remainingCredits } = req.account;
const useDbAuthentication = process.env.USE_DB_AUTHENTICATION === 'true';
if(!useDbAuthentication){
remainingCredits = Infinity;
}
const pageOptions = legacyScrapeOptions(req.body);
const extractorOptions = req.body.extract ? legacyExtractorOptions(req.body.extract) : undefined;
const sc: StoredCrawl = {
crawlerOptions: null,
pageOptions,
team_id: req.auth.team_id,
createdAt: Date.now(),
plan: req.auth.plan,
};
await saveCrawl(id, sc);
let jobPriority = 20;
// If it is over 1000, we need to get the job priority,
// otherwise we can use the default priority of 20
if(req.body.urls.length > 1000){
// set base to 21
jobPriority = await getJobPriority({plan: req.auth.plan, team_id: req.auth.team_id, basePriority: 21})
}
const jobs = req.body.urls.map((x) => {
return {
data: {
url: x,
mode: "single_urls" as const,
team_id: req.auth.team_id,
plan: req.auth.plan,
crawlerOptions: null,
pageOptions,
extractorOptions,
origin: "api",
crawl_id: id,
sitemapped: true,
v1: true,
},
opts: {
jobId: uuidv4(),
priority: 20,
},
};
});
await lockURLs(
id,
jobs.map((x) => x.data.url)
);
await addCrawlJobs(
id,
jobs.map((x) => x.opts.jobId)
);
await addScrapeJobs(jobs);
const protocol = process.env.ENV === "local" ? req.protocol : "https";
return res.status(200).json({
success: true,
id,
url: `${protocol}://${req.get("host")}/v1/batch/scrape/${id}`,
});
}

25
apps/api/src/controllers/v1/concurrency-check.ts Normal file
View File

@ -0,0 +1,25 @@
import { authenticateUser } from "../auth";
import {
ConcurrencyCheckParams,
ConcurrencyCheckResponse,
RequestWithAuth,
} from "./types";
import { RateLimiterMode } from "../../types";
import { Response } from "express";
import { redisConnection } from "../../services/queue-service";
// Basically just middleware and error wrapping
export async function concurrencyCheckController(
req: RequestWithAuth<ConcurrencyCheckParams, undefined, undefined>,
res: Response<ConcurrencyCheckResponse>
) {
const concurrencyLimiterKey = "concurrency-limiter:" + req.auth.team_id;
const now = Date.now();
const activeJobsOfTeam = await redisConnection.zrangebyscore(
concurrencyLimiterKey,
now,
Infinity
);
return res
.status(200)
.json({ success: true, concurrency: activeJobsOfTeam.length });
}

50
apps/api/src/controllers/v1/crawl-cancel.ts Normal file
View File

@ -0,0 +1,50 @@
import { Response } from "express";
import { supabase_service } from "../../services/supabase";
import { Logger } from "../../lib/logger";
import { getCrawl, saveCrawl } from "../../lib/crawl-redis";
import * as Sentry from "@sentry/node";
import { configDotenv } from "dotenv";
import { RequestWithAuth } from "./types";
configDotenv();
export async function crawlCancelController(req: RequestWithAuth<{ jobId: string }>, res: Response) {
try {
const useDbAuthentication = process.env.USE_DB_AUTHENTICATION === 'true';
const sc = await getCrawl(req.params.jobId);
if (!sc) {
return res.status(404).json({ error: "Job not found" });
}
// check if the job belongs to the team
if (useDbAuthentication) {
const { data, error: supaError } = await supabase_service
.from("bulljobs_teams")
.select("*")
.eq("job_id", req.params.jobId)
.eq("team_id", req.auth.team_id);
if (supaError) {
return res.status(500).json({ error: supaError.message });
}
if (data.length === 0) {
return res.status(403).json({ error: "Unauthorized" });
}
}
try {
sc.cancelled = true;
await saveCrawl(req.params.jobId, sc);
} catch (error) {
Logger.error(error);
}
res.json({
status: "cancelled"
});
} catch (error) {
Sentry.captureException(error);
Logger.error(error);
return res.status(500).json({ error: error.message });
}
}

179
apps/api/src/controllers/v1/crawl-status-ws.ts Normal file
View File

@ -0,0 +1,179 @@
import { authMiddleware } from "../../routes/v1";
import { RateLimiterMode } from "../../types";
import { authenticateUser } from "../auth";
import { CrawlStatusParams, CrawlStatusResponse, Document, ErrorResponse, legacyDocumentConverter, RequestWithAuth } from "./types";
import { WebSocket } from "ws";
import { v4 as uuidv4 } from "uuid";
import { Logger } from "../../lib/logger";
import { getCrawl, getCrawlExpiry, getCrawlJobs, getDoneJobsOrdered, getDoneJobsOrderedLength, getThrottledJobs, isCrawlFinished, isCrawlFinishedLocked } from "../../lib/crawl-redis";
import { getScrapeQueue } from "../../services/queue-service";
import { getJob, getJobs } from "./crawl-status";
import * as Sentry from "@sentry/node";
type ErrorMessage = {
type: "error",
error: string,
}
type CatchupMessage = {
type: "catchup",
data: CrawlStatusResponse,
}
type DocumentMessage = {
type: "document",
data: Document,
}
type DoneMessage = { type: "done" }
type Message = ErrorMessage | CatchupMessage | DoneMessage | DocumentMessage;
function send(ws: WebSocket, msg: Message) {
if (ws.readyState === 1) {
return new Promise((resolve, reject) => {
ws.send(JSON.stringify(msg), (err) => {
if (err) reject(err);
else resolve(null);
});
});
}
}
function close(ws: WebSocket, code: number, msg: Message) {
if (ws.readyState <= 1) {
ws.close(code, JSON.stringify(msg));
}
}
async function crawlStatusWS(ws: WebSocket, req: RequestWithAuth<CrawlStatusParams, undefined, undefined>) {
const sc = await getCrawl(req.params.jobId);
if (!sc) {
return close(ws, 1008, { type: "error", error: "Job not found" });
}
if (sc.team_id !== req.auth.team_id) {
return close(ws, 3003, { type: "error", error: "Forbidden" });
}
let doneJobIDs = [];
let finished = false;
const loop = async () => {
if (finished) return;
const jobIDs = await getCrawlJobs(req.params.jobId);
if (jobIDs.length === doneJobIDs.length) {
return close(ws, 1000, { type: "done" });
}
const notDoneJobIDs = jobIDs.filter(x => !doneJobIDs.includes(x));
const jobStatuses = await Promise.all(notDoneJobIDs.map(async x => [x, await getScrapeQueue().getJobState(x)]));
const newlyDoneJobIDs = jobStatuses.filter(x => x[1] === "completed" || x[1] === "failed").map(x => x[0]);
for (const jobID of newlyDoneJobIDs) {
const job = await getJob(jobID);
if (job.returnvalue) {
send(ws, {
type: "document",
data: legacyDocumentConverter(job.returnvalue),
})
} else {
return close(ws, 3000, { type: "error", error: job.failedReason });
}
}
doneJobIDs.push(...newlyDoneJobIDs);
setTimeout(loop, 1000);
};
setTimeout(loop, 1000);
doneJobIDs = await getDoneJobsOrdered(req.params.jobId);
let jobIDs = await getCrawlJobs(req.params.jobId);
let jobStatuses = await Promise.all(jobIDs.map(async x => [x, await getScrapeQueue().getJobState(x)] as const));
const throttledJobs = new Set(...await getThrottledJobs(req.auth.team_id));
const throttledJobsSet = new Set(throttledJobs);
const validJobStatuses = [];
const validJobIDs = [];
for (const [id, status] of jobStatuses) {
if (!throttledJobsSet.has(id) && status !== "failed" && status !== "unknown") {
validJobStatuses.push([id, status]);
validJobIDs.push(id);
}
}
const status: Exclude<CrawlStatusResponse, ErrorResponse>["status"] = sc.cancelled ? "cancelled" : validJobStatuses.every(x => x[1] === "completed") ? "completed" : "scraping";
jobIDs = validJobIDs; // Use validJobIDs instead of jobIDs for further processing
const doneJobs = await getJobs(doneJobIDs);
const data = doneJobs.map(x => x.returnvalue);
send(ws, {
type: "catchup",
data: {
success: true,
status,
total: jobIDs.length,
completed: doneJobIDs.length,
creditsUsed: jobIDs.length,
expiresAt: (await getCrawlExpiry(req.params.jobId)).toISOString(),
data: data.map(x => legacyDocumentConverter(x)),
}
});
if (status !== "scraping") {
finished = true;
return close(ws, 1000, { type: "done" });
}
}
// Basically just middleware and error wrapping
export async function crawlStatusWSController(ws: WebSocket, req: RequestWithAuth<CrawlStatusParams, undefined, undefined>) {
try {
const { success, team_id, error, status, plan } = await authenticateUser(
req,
null,
RateLimiterMode.CrawlStatus,
);
if (!success) {
return close(ws, 3000, {
type: "error",
error,
});
}
req.auth = { team_id, plan };
await crawlStatusWS(ws, req);
} catch (err) {
Sentry.captureException(err);
const id = uuidv4();
let verbose = JSON.stringify(err);
if (verbose === "{}") {
if (err instanceof Error) {
verbose = JSON.stringify({
message: err.message,
name: err.name,
stack: err.stack,
});
}
}
Logger.error("Error occurred in WebSocket! (" + req.path + ") -- ID " + id + " -- " + verbose);
return close(ws, 1011, {
type: "error",
error: "An unexpected error occurred. Please contact hello@firecrawl.com for help. Your exception ID is " + id
});
}
}

148
apps/api/src/controllers/v1/crawl-status.ts Normal file
View File

@ -0,0 +1,148 @@
import { Response } from "express";
import { CrawlStatusParams, CrawlStatusResponse, ErrorResponse, legacyDocumentConverter, RequestWithAuth } from "./types";
import { getCrawl, getCrawlExpiry, getCrawlJobs, getDoneJobsOrdered, getDoneJobsOrderedLength, getThrottledJobs } from "../../lib/crawl-redis";
import { getScrapeQueue } from "../../services/queue-service";
import { supabaseGetJobById, supabaseGetJobsById } from "../../lib/supabase-jobs";
import { configDotenv } from "dotenv";
configDotenv();
export async function getJob(id: string) {
const job = await getScrapeQueue().getJob(id);
if (!job) return job;
if (process.env.USE_DB_AUTHENTICATION === "true") {
const supabaseData = await supabaseGetJobById(id);
if (supabaseData) {
job.returnvalue = supabaseData.docs;
}
}
job.returnvalue = Array.isArray(job.returnvalue) ? job.returnvalue[0] : job.returnvalue;
return job;
}
export async function getJobs(ids: string[]) {
const jobs = (await Promise.all(ids.map(x => getScrapeQueue().getJob(x)))).filter(x => x);
if (process.env.USE_DB_AUTHENTICATION === "true") {
const supabaseData = await supabaseGetJobsById(ids);
supabaseData.forEach(x => {
const job = jobs.find(y => y.id === x.job_id);
if (job) {
job.returnvalue = x.docs;
}
})
}
jobs.forEach(job => {
job.returnvalue = Array.isArray(job.returnvalue) ? job.returnvalue[0] : job.returnvalue;
});
return jobs;
}
export async function crawlStatusController(req: RequestWithAuth<CrawlStatusParams, undefined, CrawlStatusResponse>, res: Response<CrawlStatusResponse>, isBatch = false) {
const sc = await getCrawl(req.params.jobId);
if (!sc) {
return res.status(404).json({ success: false, error: "Job not found" });
}
if (sc.team_id !== req.auth.team_id) {
return res.status(403).json({ success: false, error: "Forbidden" });
}
const start = typeof req.query.skip === "string" ? parseInt(req.query.skip, 10) : 0;
const end = typeof req.query.limit === "string" ? (start + parseInt(req.query.limit, 10) - 1) : undefined;
let jobIDs = await getCrawlJobs(req.params.jobId);
let jobStatuses = await Promise.all(jobIDs.map(async x => [x, await getScrapeQueue().getJobState(x)] as const));
const throttledJobs = new Set(...await getThrottledJobs(req.auth.team_id));
const throttledJobsSet = new Set(throttledJobs);
const validJobStatuses = [];
const validJobIDs = [];
for (const [id, status] of jobStatuses) {
if (!throttledJobsSet.has(id) && status !== "failed" && status !== "unknown") {
validJobStatuses.push([id, status]);
validJobIDs.push(id);
}
}
const status: Exclude<CrawlStatusResponse, ErrorResponse>["status"] = sc.cancelled ? "cancelled" : validJobStatuses.every(x => x[1] === "completed") ? "completed" : "scraping";
// Use validJobIDs instead of jobIDs for further processing
jobIDs = validJobIDs;
const doneJobsLength = await getDoneJobsOrderedLength(req.params.jobId);
const doneJobsOrder = await getDoneJobsOrdered(req.params.jobId, start, end ?? -1);
let doneJobs = [];
if (end === undefined) { // determine 10 megabyte limit
let bytes = 0;
const bytesLimit = 10485760; // 10 MiB in bytes
const factor = 100; // chunking for faster retrieval
for (let i = 0; i < doneJobsOrder.length && bytes < bytesLimit; i += factor) {
// get current chunk and retrieve jobs
const currentIDs = doneJobsOrder.slice(i, i+factor);
const jobs = await getJobs(currentIDs);
// iterate through jobs and add them one them one to the byte counter
// both loops will break once we cross the byte counter
for (let ii = 0; ii < jobs.length && bytes < bytesLimit; ii++) {
const job = jobs[ii];
doneJobs.push(job);
bytes += JSON.stringify(legacyDocumentConverter(job.returnvalue)).length;
}
}
// if we ran over the bytes limit, remove the last document, except if it's the only document
if (bytes > bytesLimit && doneJobs.length !== 1) {
doneJobs.splice(doneJobs.length - 1, 1);
}
} else {
doneJobs = await getJobs(doneJobsOrder);
}
const data = doneJobs.map(x => x.returnvalue);
const protocol = process.env.ENV === "local" ? req.protocol : "https";
const nextURL = new URL(`${protocol}://${req.get("host")}/v1/${isBatch ? "batch/scrape" : "crawl"}/${req.params.jobId}`);
nextURL.searchParams.set("skip", (start + data.length).toString());
if (typeof req.query.limit === "string") {
nextURL.searchParams.set("limit", req.query.limit);
}
if (data.length > 0) {
if (!doneJobs[0].data.pageOptions.includeRawHtml) {
for (let ii = 0; ii < doneJobs.length; ii++) {
if (data[ii]) {
delete data[ii].rawHtml;
}
}
}
}
res.status(200).json({
success: true,
status,
completed: doneJobsLength,
total: jobIDs.length,
creditsUsed: jobIDs.length,
expiresAt: (await getCrawlExpiry(req.params.jobId)).toISOString(),
next:
status !== "scraping" && (start + data.length) === doneJobsLength // if there's not gonna be any documents after this
? undefined
: nextURL.href,
data: data.map(x => legacyDocumentConverter(x)),
});
}

175
apps/api/src/controllers/v1/crawl.ts Normal file
View File

@ -0,0 +1,175 @@
import { Response } from "express";
import { v4 as uuidv4 } from "uuid";
import {
CrawlRequest,
crawlRequestSchema,
CrawlResponse,
legacyCrawlerOptions,
legacyScrapeOptions,
RequestWithAuth,
} from "./types";
import {
addCrawlJob,
addCrawlJobs,
crawlToCrawler,
lockURL,
lockURLs,
saveCrawl,
StoredCrawl,
} from "../../lib/crawl-redis";
import { logCrawl } from "../../services/logging/crawl_log";
import { getScrapeQueue } from "../../services/queue-service";
import { addScrapeJob } from "../../services/queue-jobs";
import { Logger } from "../../lib/logger";
import { getJobPriority } from "../../lib/job-priority";
import { callWebhook } from "../../services/webhook";
export async function crawlController(
req: RequestWithAuth<{}, CrawlResponse, CrawlRequest>,
res: Response<CrawlResponse>
) {
req.body = crawlRequestSchema.parse(req.body);
const id = uuidv4();
await logCrawl(id, req.auth.team_id);
let { remainingCredits } = req.account;
const useDbAuthentication = process.env.USE_DB_AUTHENTICATION === 'true';
if(!useDbAuthentication){
remainingCredits = Infinity;
}
const crawlerOptions = legacyCrawlerOptions(req.body);
const pageOptions = legacyScrapeOptions(req.body.scrapeOptions);
// TODO: @rafa, is this right? copied from v0
if (Array.isArray(crawlerOptions.includes)) {
for (const x of crawlerOptions.includes) {
try {
new RegExp(x);
} catch (e) {
return res.status(400).json({ success: false, error: e.message });
}
}
}
if (Array.isArray(crawlerOptions.excludes)) {
for (const x of crawlerOptions.excludes) {
try {
new RegExp(x);
} catch (e) {
return res.status(400).json({ success: false, error: e.message });
}
}
}
crawlerOptions.limit = Math.min(remainingCredits, crawlerOptions.limit);
const sc: StoredCrawl = {
originUrl: req.body.url,
crawlerOptions,
pageOptions,
team_id: req.auth.team_id,
createdAt: Date.now(),
plan: req.auth.plan,
};
const crawler = crawlToCrawler(id, sc);
try {
sc.robots = await crawler.getRobotsTxt(pageOptions.skipTlsVerification);
} catch (e) {
Logger.debug(
`[Crawl] Failed to get robots.txt (this is probably fine!): ${JSON.stringify(
e
)}`
);
}
await saveCrawl(id, sc);
const sitemap = sc.crawlerOptions.ignoreSitemap
? null
: await crawler.tryGetSitemap();
if (sitemap !== null && sitemap.length > 0) {
let jobPriority = 20;
// If it is over 1000, we need to get the job priority,
// otherwise we can use the default priority of 20
if(sitemap.length > 1000){
// set base to 21
jobPriority = await getJobPriority({plan: req.auth.plan, team_id: req.auth.team_id, basePriority: 21})
}
const jobs = sitemap.map((x) => {
const url = x.url;
const uuid = uuidv4();
return {
name: uuid,
data: {
url,
mode: "single_urls",
team_id: req.auth.team_id,
plan: req.auth.plan,
crawlerOptions,
pageOptions,
origin: "api",
crawl_id: id,
sitemapped: true,
webhook: req.body.webhook,
v1: true,
},
opts: {
jobId: uuid,
priority: 20,
},
};
});
await lockURLs(
id,
jobs.map((x) => x.data.url)
);
await addCrawlJobs(
id,
jobs.map((x) => x.opts.jobId)
);
await getScrapeQueue().addBulk(jobs);
} else {
await lockURL(id, sc, req.body.url);
const jobId = uuidv4();
await addScrapeJob(
{
url: req.body.url,
mode: "single_urls",
crawlerOptions: crawlerOptions,
team_id: req.auth.team_id,
plan: req.auth.plan,
pageOptions: pageOptions,
origin: "api",
crawl_id: id,
webhook: req.body.webhook,
v1: true,
},
{
priority: 15,
},
jobId,
);
await addCrawlJob(id, jobId);
}
if(req.body.webhook) {
await callWebhook(req.auth.team_id, id, null, req.body.webhook, true, "crawl.started");
}
const protocol = process.env.ENV === "local" ? req.protocol : "https";
return res.status(200).json({
success: true,
id,
url: `${protocol}://${req.get("host")}/v1/crawl/${id}`,
});
}

6
apps/api/src/controllers/v1/liveness.ts Normal file
View File

@ -0,0 +1,6 @@
import { Request, Response } from "express";
export async function livenessController(req: Request, res: Response) {
//TODO: add checks if the application is live and healthy like checking the redis connection
res.status(200).json({ status: "ok" });
}

237
apps/api/src/controllers/v1/map.ts Normal file
View File

@ -0,0 +1,237 @@
import { Response } from "express";
import { v4 as uuidv4 } from "uuid";
import {
legacyCrawlerOptions,
mapRequestSchema,
RequestWithAuth,
} from "./types";
import { crawlToCrawler, StoredCrawl } from "../../lib/crawl-redis";
import { MapResponse, MapRequest } from "./types";
import { configDotenv } from "dotenv";
import {
checkAndUpdateURLForMap,
isSameDomain,
isSameSubdomain,
removeDuplicateUrls,
} from "../../lib/validateUrl";
import { fireEngineMap } from "../../search/fireEngine";
import { billTeam } from "../../services/billing/credit_billing";
import { logJob } from "../../services/logging/log_job";
import { performCosineSimilarity } from "../../lib/map-cosine";
import { Logger } from "../../lib/logger";
import Redis from "ioredis";
configDotenv();
const redis = new Redis(process.env.REDIS_URL);
// Max Links that /map can return
const MAX_MAP_LIMIT = 5000;
// Max Links that "Smart /map" can return
const MAX_FIRE_ENGINE_RESULTS = 1000;
export async function mapController(
req: RequestWithAuth<{}, MapResponse, MapRequest>,
res: Response<MapResponse>
) {
const startTime = new Date().getTime();
req.body = mapRequestSchema.parse(req.body);
const limit: number = req.body.limit ?? MAX_MAP_LIMIT;
const id = uuidv4();
let links: string[] = [req.body.url];
const sc: StoredCrawl = {
originUrl: req.body.url,
crawlerOptions: legacyCrawlerOptions(req.body),
pageOptions: {},
team_id: req.auth.team_id,
createdAt: Date.now(),
plan: req.auth.plan,
};
const crawler = crawlToCrawler(id, sc);
let urlWithoutWww = req.body.url.replace("www.", "");
let mapUrl = req.body.search
? `"${req.body.search}" site:${urlWithoutWww}`
: `site:${req.body.url}`;
const resultsPerPage = 100;
const maxPages = Math.ceil(Math.min(MAX_FIRE_ENGINE_RESULTS, limit) / resultsPerPage);
const cacheKey = `fireEngineMap:${mapUrl}`;
const cachedResult = null;
let allResults: any[];
let pagePromises: Promise<any>[];
if (cachedResult) {
allResults = JSON.parse(cachedResult);
} else {
const fetchPage = async (page: number) => {
return fireEngineMap(mapUrl, {
numResults: resultsPerPage,
page: page,
});
};
pagePromises = Array.from({ length: maxPages }, (_, i) => fetchPage(i + 1));
allResults = await Promise.all(pagePromises);
await redis.set(cacheKey, JSON.stringify(allResults), "EX", 24 * 60 * 60); // Cache for 24 hours
}
// Parallelize sitemap fetch with serper search
const [sitemap, ...searchResults] = await Promise.all([
req.body.ignoreSitemap ? null : crawler.tryGetSitemap(),
...(cachedResult ? [] : pagePromises),
]);
if (!cachedResult) {
allResults = searchResults;
}
if (sitemap !== null) {
sitemap.forEach((x) => {
links.push(x.url);
});
}
let mapResults = allResults
.flat()
.filter((result) => result !== null && result !== undefined);
const minumumCutoff = Math.min(MAX_MAP_LIMIT, limit);
if (mapResults.length > minumumCutoff) {
mapResults = mapResults.slice(0, minumumCutoff);
}
if (mapResults.length > 0) {
if (req.body.search) {
// Ensure all map results are first, maintaining their order
links = [
mapResults[0].url,
...mapResults.slice(1).map((x) => x.url),
...links,
];
} else {
mapResults.map((x) => {
links.push(x.url);
});
}
}
// Perform cosine similarity between the search query and the list of links
if (req.body.search) {
const searchQuery = req.body.search.toLowerCase();
links = performCosineSimilarity(links, searchQuery);
}
links = links
.map((x) => {
try {
return checkAndUpdateURLForMap(x).url.trim();
} catch (_) {
return null;
}
})
.filter((x) => x !== null);
// allows for subdomains to be included
links = links.filter((x) => isSameDomain(x, req.body.url));
// if includeSubdomains is false, filter out subdomains
if (!req.body.includeSubdomains) {
links = links.filter((x) => isSameSubdomain(x, req.body.url));
}
// remove duplicates that could be due to http/https or www
links = removeDuplicateUrls(links);
billTeam(req.auth.team_id, req.acuc?.sub_id, 1).catch((error) => {
Logger.error(
`Failed to bill team ${req.auth.team_id} for 1 credit: ${error}`
);
// Optionally, you could notify an admin or add to a retry queue here
});
const endTime = new Date().getTime();
const timeTakenInSeconds = (endTime - startTime) / 1000;
const linksToReturn = links.slice(0, limit);
logJob({
job_id: id,
success: links.length > 0,
message: "Map completed",
num_docs: linksToReturn.length,
docs: linksToReturn,
time_taken: timeTakenInSeconds,
team_id: req.auth.team_id,
mode: "map",
url: req.body.url,
crawlerOptions: {},
pageOptions: {},
origin: req.body.origin,
extractor_options: { mode: "markdown" },
num_tokens: 0,
});
return res.status(200).json({
success: true,
links: linksToReturn,
scrape_id: req.body.origin?.includes("website") ? id : undefined,
});
}
// Subdomain sitemap url checking
// // For each result, check for subdomains, get their sitemaps and add them to the links
// const processedUrls = new Set();
// const processedSubdomains = new Set();
// for (const result of links) {
// let url;
// let hostParts;
// try {
// url = new URL(result);
// hostParts = url.hostname.split('.');
// } catch (e) {
// continue;
// }
// console.log("hostParts", hostParts);
// // Check if it's a subdomain (more than 2 parts, and not 'www')
// if (hostParts.length > 2 && hostParts[0] !== 'www') {
// const subdomain = hostParts[0];
// console.log("subdomain", subdomain);
// const subdomainUrl = `${url.protocol}//${subdomain}.${hostParts.slice(-2).join('.')}`;
// console.log("subdomainUrl", subdomainUrl);
// if (!processedSubdomains.has(subdomainUrl)) {
// processedSubdomains.add(subdomainUrl);
// const subdomainCrawl = crawlToCrawler(id, {
// originUrl: subdomainUrl,
// crawlerOptions: legacyCrawlerOptions(req.body),
// pageOptions: {},
// team_id: req.auth.team_id,
// createdAt: Date.now(),
// plan: req.auth.plan,
// });
// const subdomainSitemap = await subdomainCrawl.tryGetSitemap();
// if (subdomainSitemap) {
// subdomainSitemap.forEach((x) => {
// if (!processedUrls.has(x.url)) {
// processedUrls.add(x.url);
// links.push(x.url);
// }
// });
// }
// }
// }
// }

6
apps/api/src/controllers/v1/readiness.ts Normal file
View File

@ -0,0 +1,6 @@
import { Request, Response } from "express";
export async function readinessController(req: Request, res: Response) {
// TODO: add checks when the application is ready to serve traffic
res.status(200).json({ status: "ok" });
}

38
apps/api/src/controllers/v1/scrape-status.ts Normal file
View File

@ -0,0 +1,38 @@
import { Response } from "express";
import { supabaseGetJobByIdOnlyData } from "../../lib/supabase-jobs";
import { scrapeStatusRateLimiter } from "../../services/rate-limiter";
export async function scrapeStatusController(req: any, res: any) {
try {
const rateLimiter = scrapeStatusRateLimiter;
const incomingIP = (req.headers["x-forwarded-for"] ||
req.socket.remoteAddress) as string;
const iptoken = incomingIP;
await rateLimiter.consume(iptoken);
const job = await supabaseGetJobByIdOnlyData(req.params.jobId);
if(job.team_id !== "41bdbfe1-0579-4d9b-b6d5-809f16be12f5"){
return res.status(403).json({
success: false,
error: "You are not allowed to access this resource.",
});
}
return res.status(200).json({
success: true,
data: job?.docs[0],
});
} catch (error) {
if (error instanceof Error && error.message == "Too Many Requests") {
return res.status(429).json({
success: false,
error: "Rate limit exceeded. Please try again later.",
});
} else {
return res.status(500).json({
success: false,
error: "An unexpected error occurred.",
});
}
}
}

152
apps/api/src/controllers/v1/scrape.ts Normal file
View File

@ -0,0 +1,152 @@
import { Request, Response } from "express";
import { Logger } from "../../lib/logger";
import {
Document,
legacyDocumentConverter,
legacyExtractorOptions,
legacyScrapeOptions,
RequestWithAuth,
ScrapeRequest,
scrapeRequestSchema,
ScrapeResponse,
} from "./types";
import { billTeam } from "../../services/billing/credit_billing";
import { v4 as uuidv4 } from "uuid";
import { numTokensFromString } from "../../lib/LLM-extraction/helpers";
import { addScrapeJob, waitForJob } from "../../services/queue-jobs";
import { logJob } from "../../services/logging/log_job";
import { getJobPriority } from "../../lib/job-priority";
import { PlanType } from "../../types";
import { getScrapeQueue } from "../../services/queue-service";
export async function scrapeController(
req: RequestWithAuth<{}, ScrapeResponse, ScrapeRequest>,
res: Response<ScrapeResponse>
) {
req.body = scrapeRequestSchema.parse(req.body);
let earlyReturn = false;
const origin = req.body.origin;
const timeout = req.body.timeout;
const pageOptions = legacyScrapeOptions(req.body);
const extractorOptions = req.body.extract ? legacyExtractorOptions(req.body.extract) : undefined;
const jobId = uuidv4();
const startTime = new Date().getTime();
const jobPriority = await getJobPriority({
plan: req.auth.plan as PlanType,
team_id: req.auth.team_id,
basePriority: 10,
});
await addScrapeJob(
{
url: req.body.url,
mode: "single_urls",
crawlerOptions: {},
team_id: req.auth.team_id,
plan: req.auth.plan,
pageOptions,
extractorOptions,
origin: req.body.origin,
is_scrape: true,
},
{},
jobId,
jobPriority
);
const totalWait = (req.body.waitFor ?? 0) + (req.body.actions ?? []).reduce((a,x) => (x.type === "wait" ? x.milliseconds : 0) + a, 0);
let doc: any | undefined;
try {
doc = (await waitForJob(jobId, timeout + totalWait))[0];
} catch (e) {
Logger.error(`Error in scrapeController: ${e}`);
if (e instanceof Error && e.message.startsWith("Job wait")) {
return res.status(408).json({
success: false,
error: "Request timed out",
});
} else {
return res.status(500).json({
success: false,
error: `(Internal server error) - ${e && e?.message ? e.message : e} ${
extractorOptions && extractorOptions.mode !== "markdown"
? " - Could be due to LLM parsing issues"
: ""
}`,
});
}
}
await getScrapeQueue().remove(jobId);
if (!doc) {
console.error("!!! PANIC DOC IS", doc);
return res.status(200).json({
success: true,
warning: "No page found",
data: doc,
});
}
delete doc.index;
delete doc.provider;
const endTime = new Date().getTime();
const timeTakenInSeconds = (endTime - startTime) / 1000;
const numTokens =
doc && doc.markdown
? numTokensFromString(doc.markdown, "gpt-3.5-turbo")
: 0;
let creditsToBeBilled = 1; // Assuming 1 credit per document
if (earlyReturn) {
// Don't bill if we're early returning
return;
}
if(req.body.extract && req.body.formats.includes("extract")) {
creditsToBeBilled = 5;
}
billTeam(req.auth.team_id, req.acuc?.sub_id, creditsToBeBilled).catch(error => {
Logger.error(`Failed to bill team ${req.auth.team_id} for ${creditsToBeBilled} credits: ${error}`);
// Optionally, you could notify an admin or add to a retry queue here
});
if (!pageOptions || !pageOptions.includeRawHtml) {
if (doc && doc.rawHtml) {
delete doc.rawHtml;
}
}
if(pageOptions && pageOptions.includeExtract) {
if(!pageOptions.includeMarkdown && doc && doc.markdown) {
delete doc.markdown;
}
}
logJob({
job_id: jobId,
success: true,
message: "Scrape completed",
num_docs: 1,
docs: [doc],
time_taken: timeTakenInSeconds,
team_id: req.auth.team_id,
mode: "scrape",
url: req.body.url,
crawlerOptions: {},
pageOptions: pageOptions,
origin: origin,
extractor_options: extractorOptions,
num_tokens: numTokens,
});
return res.status(200).json({
success: true,
data: legacyDocumentConverter(doc),
scrape_id: origin?.includes("website") ? jobId : undefined,
});
}

520
apps/api/src/controllers/v1/types.ts Normal file
View File

@ -0,0 +1,520 @@
import { Request, Response } from "express";
import { z } from "zod";
import { isUrlBlocked } from "../../scraper/WebScraper/utils/blocklist";
import { Action, ExtractorOptions, PageOptions } from "../../lib/entities";
import { protocolIncluded, checkUrl } from "../../lib/validateUrl";
import { PlanType } from "../../types";
import { countries } from "../../lib/validate-country";
export type Format =
| "markdown"
| "html"
| "rawHtml"
| "links"
| "screenshot"
| "screenshot@fullPage"
| "extract";
export const url = z.preprocess(
(x) => {
if (!protocolIncluded(x as string)) {
return `http://${x}`;
}
return x;
},
z
.string()
.url()
.regex(/^https?:\/\//, "URL uses unsupported protocol")
.refine(
(x) => /\.[a-z]{2,}([\/?#]|$)/i.test(x),
"URL must have a valid top-level domain or be a valid path"
)
.refine(
(x) => {
try {
checkUrl(x as string)
return true;
} catch (_) {
return false;
}
},
"Invalid URL"
)
.refine(
(x) => !isUrlBlocked(x as string),
"Firecrawl currently does not support social media scraping due to policy restrictions. We're actively working on building support for it."
)
);
const strictMessage = "Unrecognized key in body -- please review the v1 API documentation for request body changes";
export const extractOptions = z.object({
mode: z.enum(["llm"]).default("llm"),
schema: z.any().optional(),
systemPrompt: z.string().default("Based on the information on the page, extract all the information from the schema. Try to extract all the fields even those that might not be marked as required."),
prompt: z.string().optional()
}).strict(strictMessage);
export type ExtractOptions = z.infer<typeof extractOptions>;
export const actionsSchema = z.array(z.union([
z.object({
type: z.literal("wait"),
milliseconds: z.number().int().positive().finite().optional(),
selector: z.string().optional(),
}).refine(
(data) => (data.milliseconds !== undefined || data.selector !== undefined) && !(data.milliseconds !== undefined && data.selector !== undefined),
{
message: "Either 'milliseconds' or 'selector' must be provided, but not both.",
}
),
z.object({
type: z.literal("click"),
selector: z.string(),
}),
z.object({
type: z.literal("screenshot"),
fullPage: z.boolean().default(false),
}),
z.object({
type: z.literal("write"),
text: z.string(),
}),
z.object({
type: z.literal("press"),
key: z.string(),
}),
z.object({
type: z.literal("scroll"),
direction: z.enum(["up", "down"]),
}),
z.object({
type: z.literal("scrape"),
}),
]));
export const scrapeOptions = z.object({
formats: z
.enum([
"markdown",
"html",
"rawHtml",
"links",
"screenshot",
"screenshot@fullPage",
"extract"
])
.array()
.optional()
.default(["markdown"])
.refine(x => !(x.includes("screenshot") && x.includes("screenshot@fullPage")), "You may only specify either screenshot or screenshot@fullPage"),
headers: z.record(z.string(), z.string()).optional(),
includeTags: z.string().array().optional(),
excludeTags: z.string().array().optional(),
onlyMainContent: z.boolean().default(true),
timeout: z.number().int().positive().finite().safe().default(30000),
waitFor: z.number().int().nonnegative().finite().safe().default(0),
extract: extractOptions.optional(),
mobile: z.boolean().default(false),
parsePDF: z.boolean().default(true),
actions: actionsSchema.optional(),
// New
location: z.object({
country: z.string().optional().refine(
(val) => !val || Object.keys(countries).includes(val.toUpperCase()),
{
message: "Invalid country code. Please use a valid ISO 3166-1 alpha-2 country code.",
}
).transform(val => val ? val.toUpperCase() : 'US'),
languages: z.string().array().optional(),
}).optional(),
// Deprecated
geolocation: z.object({
country: z.string().optional().refine(
(val) => !val || Object.keys(countries).includes(val.toUpperCase()),
{
message: "Invalid country code. Please use a valid ISO 3166-1 alpha-2 country code.",
}
).transform(val => val ? val.toUpperCase() : 'US'),
languages: z.string().array().optional(),
}).optional(),
skipTlsVerification: z.boolean().default(false),
removeBase64Images: z.boolean().default(true),
}).strict(strictMessage)
export type ScrapeOptions = z.infer<typeof scrapeOptions>;
export const scrapeRequestSchema = scrapeOptions.extend({
url,
origin: z.string().optional().default("api"),
}).strict(strictMessage).refine(
(obj) => {
const hasExtractFormat = obj.formats?.includes("extract");
const hasExtractOptions = obj.extract !== undefined;
return (hasExtractFormat && hasExtractOptions) || (!hasExtractFormat && !hasExtractOptions);
},
{
message: "When 'extract' format is specified, 'extract' options must be provided, and vice versa",
}
).transform((obj) => {
if ((obj.formats?.includes("extract") || obj.extract) && !obj.timeout) {
return { ...obj, timeout: 60000 };
}
return obj;
});
export type ScrapeRequest = z.infer<typeof scrapeRequestSchema>;
export const batchScrapeRequestSchema = scrapeOptions.extend({
urls: url.array(),
origin: z.string().optional().default("api"),
}).strict(strictMessage).refine(
(obj) => {
const hasExtractFormat = obj.formats?.includes("extract");
const hasExtractOptions = obj.extract !== undefined;
return (hasExtractFormat && hasExtractOptions) || (!hasExtractFormat && !hasExtractOptions);
},
{
message: "When 'extract' format is specified, 'extract' options must be provided, and vice versa",
}
).transform((obj) => {
if ((obj.formats?.includes("extract") || obj.extract) && !obj.timeout) {
return { ...obj, timeout: 60000 };
}
return obj;
});
export type BatchScrapeRequest = z.infer<typeof batchScrapeRequestSchema>;
const crawlerOptions = z.object({
includePaths: z.string().array().default([]),
excludePaths: z.string().array().default([]),
maxDepth: z.number().default(10), // default?
limit: z.number().default(10000), // default?
allowBackwardLinks: z.boolean().default(false), // >> TODO: CHANGE THIS NAME???
allowExternalLinks: z.boolean().default(false),
ignoreSitemap: z.boolean().default(true),
}).strict(strictMessage);
// export type CrawlerOptions = {
// includePaths?: string[];
// excludePaths?: string[];
// maxDepth?: number;
// limit?: number;
// allowBackwardLinks?: boolean; // >> TODO: CHANGE THIS NAME???
// allowExternalLinks?: boolean;
// ignoreSitemap?: boolean;
// };
export type CrawlerOptions = z.infer<typeof crawlerOptions>;
export const crawlRequestSchema = crawlerOptions.extend({
url,
origin: z.string().optional().default("api"),
scrapeOptions: scrapeOptions.omit({ timeout: true }).default({}),
webhook: z.string().url().optional(),
limit: z.number().default(10000),
}).strict(strictMessage);
// export type CrawlRequest = {
// url: string;
// crawlerOptions?: CrawlerOptions;
// scrapeOptions?: Exclude<ScrapeRequest, "url">;
// };
// export type ExtractorOptions = {
// mode: "markdown" | "llm-extraction" | "llm-extraction-from-markdown" | "llm-extraction-from-raw-html";
// extractionPrompt?: string;
// extractionSchema?: Record<string, any>;
// }
export type CrawlRequest = z.infer<typeof crawlRequestSchema>;
export const mapRequestSchema = crawlerOptions.extend({
url,
origin: z.string().optional().default("api"),
includeSubdomains: z.boolean().default(true),
search: z.string().optional(),
ignoreSitemap: z.boolean().default(false),
limit: z.number().min(1).max(5000).default(5000).optional(),
}).strict(strictMessage);
// export type MapRequest = {
// url: string;
// crawlerOptions?: CrawlerOptions;
// };
export type MapRequest = z.infer<typeof mapRequestSchema>;
export type Document = {
markdown?: string;
extract?: string;
html?: string;
rawHtml?: string;
links?: string[];
screenshot?: string;
actions?: {
screenshots: string[];
};
warning?: string;
metadata: {
title?: string;
description?: string;
language?: string;
keywords?: string;
robots?: string;
ogTitle?: string;
ogDescription?: string;
ogUrl?: string;
ogImage?: string;
ogAudio?: string;
ogDeterminer?: string;
ogLocale?: string;
ogLocaleAlternate?: string[];
ogSiteName?: string;
ogVideo?: string;
dcTermsCreated?: string;
dcDateCreated?: string;
dcDate?: string;
dcTermsType?: string;
dcType?: string;
dcTermsAudience?: string;
dcTermsSubject?: string;
dcSubject?: string;
dcDescription?: string;
dcTermsKeywords?: string;
modifiedTime?: string;
publishedTime?: string;
articleTag?: string;
articleSection?: string;
sourceURL?: string;
statusCode?: number;
error?: string;
[key: string]: string | string[] | number | undefined;
};
};
export type ErrorResponse = {
success: false;
error: string;
details?: any;
};
export type ScrapeResponse =
| ErrorResponse
| {
success: true;
warning?: string;
data: Document;
scrape_id?: string;
};
export interface ScrapeResponseRequestTest {
statusCode: number;
body: ScrapeResponse;
error?: string;
}
export type CrawlResponse =
| ErrorResponse
| {
success: true;
id: string;
url: string;
};
export type MapResponse =
| ErrorResponse
| {
success: true;
links: string[];
scrape_id?: string;
};
export type CrawlStatusParams = {
jobId: string;
};
export type ConcurrencyCheckParams = {
teamId: string;
};
export type ConcurrencyCheckResponse =
| ErrorResponse
| {
success: true;
concurrency: number;
};
export type CrawlStatusResponse =
| ErrorResponse
| {
success: true;
status: "scraping" | "completed" | "failed" | "cancelled";
completed: number;
total: number;
creditsUsed: number;
expiresAt: string;
next?: string;
data: Document[];
};
type AuthObject = {
team_id: string;
plan: PlanType;
};
type Account = {
remainingCredits: number;
};
export type AuthCreditUsageChunk = {
api_key: string;
team_id: string;
sub_id: string | null;
sub_current_period_start: string | null;
sub_current_period_end: string | null;
price_id: string | null;
price_credits: number; // credit limit with assoicated price, or free_credits (500) if free plan
credits_used: number;
coupon_credits: number; // do not rely on this number to be up to date after calling a billTeam
coupons: any[];
adjusted_credits_used: number; // credits this period minus coupons used
remaining_credits: number;
sub_user_id: string | null;
total_credits_sum: number;
};
export interface RequestWithMaybeACUC<
ReqParams = {},
ReqBody = undefined,
ResBody = undefined
> extends Request<ReqParams, ReqBody, ResBody> {
acuc?: AuthCreditUsageChunk,
}
export interface RequestWithACUC<
ReqParams = {},
ReqBody = undefined,
ResBody = undefined
> extends Request<ReqParams, ReqBody, ResBody> {
acuc: AuthCreditUsageChunk,
}
export interface RequestWithAuth<
ReqParams = {},
ReqBody = undefined,
ResBody = undefined,
> extends Request<ReqParams, ReqBody, ResBody> {
auth: AuthObject;
account?: Account;
}
export interface RequestWithMaybeAuth<
ReqParams = {},
ReqBody = undefined,
ResBody = undefined
> extends RequestWithMaybeACUC<ReqParams, ReqBody, ResBody> {
auth?: AuthObject;
account?: Account;
}
export interface RequestWithAuth<
ReqParams = {},
ReqBody = undefined,
ResBody = undefined,
> extends RequestWithACUC<ReqParams, ReqBody, ResBody> {
auth: AuthObject;
account?: Account;
}
export interface ResponseWithSentry<
ResBody = undefined,
> extends Response<ResBody> {
sentry?: string,
}
export function legacyCrawlerOptions(x: CrawlerOptions) {
return {
includes: x.includePaths,
excludes: x.excludePaths,
maxCrawledLinks: x.limit,
maxDepth: x.maxDepth,
limit: x.limit,
generateImgAltText: false,
allowBackwardCrawling: x.allowBackwardLinks,
allowExternalContentLinks: x.allowExternalLinks,
ignoreSitemap: x.ignoreSitemap,
};
}
export function legacyScrapeOptions(x: ScrapeOptions): PageOptions {
return {
includeMarkdown: x.formats.includes("markdown"),
includeHtml: x.formats.includes("html"),
includeRawHtml: x.formats.includes("rawHtml"),
includeExtract: x.formats.includes("extract"),
onlyIncludeTags: x.includeTags,
removeTags: x.excludeTags,
onlyMainContent: x.onlyMainContent,
waitFor: x.waitFor,
headers: x.headers,
includeLinks: x.formats.includes("links"),
screenshot: x.formats.includes("screenshot"),
fullPageScreenshot: x.formats.includes("screenshot@fullPage"),
parsePDF: x.parsePDF,
actions: x.actions as Action[], // no strict null checking grrrr - mogery
geolocation: x.location ?? x.geolocation,
skipTlsVerification: x.skipTlsVerification,
removeBase64Images: x.removeBase64Images,
mobile: x.mobile,
};
}
export function legacyExtractorOptions(x: ExtractOptions): ExtractorOptions {
return {
mode: x.mode ? "llm-extraction" : "markdown",
extractionPrompt: x.prompt ?? "Based on the information on the page, extract the information from the schema.",
extractionSchema: x.schema,
userPrompt: x.prompt ?? "",
};
}
export function legacyDocumentConverter(doc: any): Document {
if (doc === null || doc === undefined) return null;
if (doc.metadata) {
if (doc.metadata.screenshot) {
doc.screenshot = doc.metadata.screenshot;
delete doc.metadata.screenshot;
}
if (doc.metadata.fullPageScreenshot) {
doc.fullPageScreenshot = doc.metadata.fullPageScreenshot;
delete doc.metadata.fullPageScreenshot;
}
}
return {
markdown: doc.markdown,
links: doc.linksOnPage,
rawHtml: doc.rawHtml,
html: doc.html,
extract: doc.llm_extraction,
screenshot: doc.screenshot ?? doc.fullPageScreenshot,
actions: doc.actions ?? undefined,
warning: doc.warning ?? undefined,
metadata: {
...doc.metadata,
pageError: undefined,
pageStatusCode: undefined,
error: doc.metadata?.pageError,
statusCode: doc.metadata?.pageStatusCode,
},
};
}

1
apps/api/src/example.ts
View File

@ -4,6 +4,7 @@ async function example() {
const example = new WebScraperDataProvider();
await example.setOptions({
jobId: "TEST",
mode: "crawl",
urls: ["https://mendable.ai"],
crawlerOptions: {},

242
apps/api/src/index.ts
View File

@ -1,122 +1,107 @@
import express from "express";
import "dotenv/config";
import "./services/sentry"
import * as Sentry from "@sentry/node";
import express, { NextFunction, Request, Response } from "express";
import bodyParser from "body-parser";
import cors from "cors";
import "dotenv/config";
import { getWebScraperQueue } from "./services/queue-service";
import { redisClient } from "./services/rate-limiter";
import { getScrapeQueue } from "./services/queue-service";
import { v0Router } from "./routes/v0";
import { initSDK } from "@hyperdx/node-opentelemetry";
import cluster from "cluster";
import os from "os";
import { Logger } from "./lib/logger";
import { adminRouter } from "./routes/admin";
import { ScrapeEvents } from "./lib/scrape-events";
import http from 'node:http';
import https from 'node:https';
import CacheableLookup from 'cacheable-lookup';
import { v1Router } from "./routes/v1";
import expressWs from "express-ws";
import { crawlStatusWSController } from "./controllers/v1/crawl-status-ws";
import { ErrorResponse, ResponseWithSentry } from "./controllers/v1/types";
import { ZodError } from "zod";
import { v4 as uuidv4 } from "uuid";
import dns from 'node:dns';
const { createBullBoard } = require("@bull-board/api");
const { BullAdapter } = require("@bull-board/api/bullAdapter");
const { ExpressAdapter } = require("@bull-board/express");
const numCPUs = process.env.ENV === "local" ? 2 : os.cpus().length;
console.log(`Number of CPUs: ${numCPUs} available`);
Logger.info(`Number of CPUs: ${numCPUs} available`);
if (cluster.isMaster) {
console.log(`Master ${process.pid} is running`);
const cacheable = new CacheableLookup()
// Fork workers.
for (let i = 0; i < numCPUs; i++) {
cluster.fork();
}
cluster.on("exit", (worker, code, signal) => {
console.log(`Worker ${worker.process.pid} exited`);
console.log("Starting a new worker");
cluster.fork();
});
} else {
const app = express();
// Install cacheable lookup for all other requests
cacheable.install(http.globalAgent);
cacheable.install(https.globalAgent);
global.isProduction = process.env.IS_PRODUCTION === "true";
app.use(bodyParser.urlencoded({ extended: true }));
app.use(bodyParser.json({ limit: "10mb" }));
const ws = expressWs(express());
const app = ws.app;
app.use(cors()); // Add this line to enable CORS
global.isProduction = process.env.IS_PRODUCTION === "true";
const serverAdapter = new ExpressAdapter();
serverAdapter.setBasePath(`/admin/${process.env.BULL_AUTH_KEY}/queues`);
app.use(bodyParser.urlencoded({ extended: true }));
app.use(bodyParser.json({ limit: "10mb" }));
const { addQueue, removeQueue, setQueues, replaceQueues } = createBullBoard({
queues: [new BullAdapter(getWebScraperQueue())],
app.use(cors()); // Add this line to enable CORS
const serverAdapter = new ExpressAdapter();
serverAdapter.setBasePath(`/admin/${process.env.BULL_AUTH_KEY}/queues`);
const { addQueue, removeQueue, setQueues, replaceQueues } = createBullBoard({
queues: [new BullAdapter(getScrapeQueue())],
serverAdapter: serverAdapter,
});
});
app.use(
app.use(
`/admin/${process.env.BULL_AUTH_KEY}/queues`,
serverAdapter.getRouter()
);
);
app.get("/", (req, res) => {
res.send("SCRAPERS-JS: Hello, world! Fly.io");
});
app.get("/", (req, res) => {
res.send("SCRAPERS-JS: Hello, world! K8s!");
});
//write a simple test function
app.get("/test", async (req, res) => {
//write a simple test function
app.get("/test", async (req, res) => {
res.send("Hello, world!");
});
});
// register router
app.use(v0Router);
// register router
app.use(v0Router);
app.use("/v1", v1Router);
app.use(adminRouter);
const DEFAULT_PORT = process.env.PORT ?? 3002;
const HOST = process.env.HOST ?? "localhost";
redisClient.connect();
const DEFAULT_PORT = process.env.PORT ?? 3002;
const HOST = process.env.HOST ?? "localhost";
// HyperDX OpenTelemetry
if (process.env.ENV === "production") {
// HyperDX OpenTelemetry
if (process.env.ENV === "production") {
initSDK({ consoleCapture: true, additionalInstrumentations: [] });
}
}
function startServer(port = DEFAULT_PORT) {
function startServer(port = DEFAULT_PORT) {
const server = app.listen(Number(port), HOST, () => {
console.log(`Worker ${process.pid} listening on port ${port}`);
console.log(
`For the UI, open http://${HOST}:${port}/admin/${process.env.BULL_AUTH_KEY}/queues`
);
console.log("");
console.log("1. Make sure Redis is running on port 6379 by default");
console.log(
"2. If you want to run nango, make sure you do port forwarding in 3002 using ngrok http 3002 "
Logger.info(`Worker ${process.pid} listening on port ${port}`);
Logger.info(
`For the Queue UI, open: http://${HOST}:${port}/admin/${process.env.BULL_AUTH_KEY}/queues`
);
});
return server;
}
}
if (require.main === module) {
if (require.main === module) {
startServer();
}
}
// Use this as a "health check" that way we dont destroy the server
app.get(`/admin/${process.env.BULL_AUTH_KEY}/queues`, async (req, res) => {
app.get(`/serverHealthCheck`, async (req, res) => {
try {
const webScraperQueue = getWebScraperQueue();
const [webScraperActive] = await Promise.all([
webScraperQueue.getActiveCount(),
]);
const noActiveJobs = webScraperActive === 0;
// 200 if no active jobs, 503 if there are active jobs
return res.status(noActiveJobs ? 200 : 500).json({
webScraperActive,
noActiveJobs,
});
} catch (error) {
console.error(error);
return res.status(500).json({ error: error.message });
}
});
app.get(`/serverHealthCheck`, async (req, res) => {
try {
const webScraperQueue = getWebScraperQueue();
const scrapeQueue = getScrapeQueue();
const [waitingJobs] = await Promise.all([
webScraperQueue.getWaitingCount(),
scrapeQueue.getWaitingCount(),
]);
const noWaitingJobs = waitingJobs === 0;
@ -125,20 +110,21 @@ if (cluster.isMaster) {
waitingJobs,
});
} catch (error) {
console.error(error);
Sentry.captureException(error);
Logger.error(error);
return res.status(500).json({ error: error.message });
}
});
});
app.get("/serverHealthCheck/notify", async (req, res) => {
app.get("/serverHealthCheck/notify", async (req, res) => {
if (process.env.SLACK_WEBHOOK_URL) {
const treshold = 1; // The treshold value for the active jobs
const timeout = 60000; // 1 minute // The timeout value for the check in milliseconds
const getWaitingJobsCount = async () => {
const webScraperQueue = getWebScraperQueue();
const scrapeQueue = getScrapeQueue();
const [waitingJobsCount] = await Promise.all([
webScraperQueue.getWaitingCount(),
scrapeQueue.getWaitingCount(),
]);
return waitingJobsCount;
@ -170,50 +156,70 @@ if (cluster.isMaster) {
});
if (!response.ok) {
console.error("Failed to send Slack notification");
Logger.error("Failed to send Slack notification");
}
}
}, timeout);
}
} catch (error) {
console.error(error);
Sentry.captureException(error);
Logger.debug(error);
}
};
checkWaitingJobs();
}
});
});
app.get(
`/admin/${process.env.BULL_AUTH_KEY}/clean-before-24h-complete-jobs`,
async (req, res) => {
try {
const webScraperQueue = getWebScraperQueue();
const completedJobs = await webScraperQueue.getJobs(["completed"]);
const before24hJobs = completedJobs.filter(
(job) => job.finishedOn < Date.now() - 24 * 60 * 60 * 1000
);
const jobIds = before24hJobs.map((job) => job.id) as string[];
let count = 0;
for (const jobId of jobIds) {
try {
await webScraperQueue.removeJobs(jobId);
count++;
} catch (jobError) {
console.error(`Failed to remove job with ID ${jobId}:`, jobError);
}
}
res.status(200).send(`Removed ${count} completed jobs.`);
} catch (error) {
console.error("Failed to clean last 24h complete jobs:", error);
res.status(500).send("Failed to clean jobs");
}
}
);
app.get("/is-production", (req, res) => {
app.get("/is-production", (req, res) => {
res.send({ isProduction: global.isProduction });
});
});
app.use((err: unknown, req: Request<{}, ErrorResponse, undefined>, res: Response<ErrorResponse>, next: NextFunction) => {
if (err instanceof ZodError) {
if (Array.isArray(err.errors) && err.errors.find(x => x.message === "URL uses unsupported protocol")) {
Logger.warn("Unsupported protocol error: " + JSON.stringify(req.body));
}
res.status(400).json({ success: false, error: "Bad Request", details: err.errors });
} else {
next(err);
}
});
Sentry.setupExpressErrorHandler(app);
app.use((err: unknown, req: Request<{}, ErrorResponse, undefined>, res: ResponseWithSentry<ErrorResponse>, next: NextFunction) => {
if (err instanceof SyntaxError && 'status' in err && err.status === 400 && 'body' in err) {
return res.status(400).json({ success: false, error: 'Bad request, malformed JSON' });
}
const id = res.sentry ?? uuidv4();
let verbose = JSON.stringify(err);
if (verbose === "{}") {
if (err instanceof Error) {
verbose = JSON.stringify({
message: err.message,
name: err.name,
stack: err.stack,
});
}
}
Logger.error("Error occurred in request! (" + req.path + ") -- ID " + id + " -- " + verbose);
res.status(500).json({ success: false, error: "An unexpected error occurred. Please contact hello@firecrawl.com for help. Your exception ID is " + id });
});
Logger.info(`Worker ${process.pid} started`);
// const sq = getScrapeQueue();
// sq.on("waiting", j => ScrapeEvents.logJobEvent(j, "waiting"));
// sq.on("active", j => ScrapeEvents.logJobEvent(j, "active"));
// sq.on("completed", j => ScrapeEvents.logJobEvent(j, "completed"));
// sq.on("paused", j => ScrapeEvents.logJobEvent(j, "paused"));
// sq.on("resumed", j => ScrapeEvents.logJobEvent(j, "resumed"));
// sq.on("removed", j => ScrapeEvents.logJobEvent(j, "removed"));
console.log(`Worker ${process.pid} started`);
}

8
apps/api/src/lib/LLM-extraction/helpers.ts
View File

@ -6,7 +6,13 @@ export function numTokensFromString(message: string, model: string): number {
const encoder = encoding_for_model(model as TiktokenModel);
// Encode the message into tokens
const tokens = encoder.encode(message);
let tokens: Uint32Array;
try {
tokens = encoder.encode(message);
} catch (error) {
message = message.replace("<|endoftext|>", "");
tokens = encoder.encode(message);
}
// Free the encoder resources after use
encoder.free();

21
apps/api/src/lib/LLM-extraction/index.ts
View File

@ -4,16 +4,19 @@ const ajv = new Ajv(); // Initialize AJV for JSON schema validation
import { generateOpenAICompletions } from "./models";
import { Document, ExtractorOptions } from "../entities";
import { Logger } from "../logger";
// Generate completion using OpenAI
export async function generateCompletions(
documents: Document[],
extractionOptions: ExtractorOptions
extractionOptions: ExtractorOptions,
mode: "markdown" | "raw-html"
): Promise<Document[]> {
// const schema = zodToJsonSchema(options.schema)
const schema = extractionOptions.extractionSchema;
const prompt = extractionOptions.extractionPrompt;
const systemPrompt = extractionOptions.extractionPrompt;
const prompt = extractionOptions.userPrompt;
const switchVariable = "openAI"; // Placholder, want to think more about how we abstract the model provider
@ -22,28 +25,34 @@ export async function generateCompletions(
switch (switchVariable) {
case "openAI":
const llm = new OpenAI();
try{
try {
const completionResult = await generateOpenAICompletions({
client: llm,
document: document,
schema: schema,
prompt: prompt,
systemPrompt: systemPrompt,
mode: mode,
});
// Validate the JSON output against the schema using AJV
if (schema) {
const validate = ajv.compile(schema);
if (!validate(completionResult.llm_extraction)) {
//TODO: add Custom Error handling middleware that bubbles this up with proper Error code, etc.
throw new Error(
`JSON parsing error(s): ${validate.errors
?.map((err) => err.message)
.join(", ")}\n\nLLM extraction did not match the extraction schema you provided. This could be because of a model hallucination, or an Error on our side. Try adjusting your prompt, and if it doesn't work reach out to support.`
.join(
", "
)}\n\nLLM extraction did not match the extraction schema you provided. This could be because of a model hallucination, or an Error on our side. Try adjusting your prompt, and if it doesn't work reach out to support.`
);
}
}
return completionResult;
} catch (error) {
console.error(`Error generating completions: ${error}`);
throw new Error(`Error generating completions: ${error.message}`);
Logger.error(`Error generating completions: ${error}`);
throw error;
}
default:
throw new Error("Invalid client");

96
apps/api/src/lib/LLM-extraction/models.ts
View File

@ -13,52 +13,100 @@ const defaultPrompt =
"You are a professional web scraper. Extract the contents of the webpage";
function prepareOpenAIDoc(
document: Document
): [OpenAI.Chat.Completions.ChatCompletionContentPart[], number] {
document: Document,
mode: "markdown" | "raw-html"
): [OpenAI.Chat.Completions.ChatCompletionContentPart[], number] | null {
let markdown = document.markdown;
// Check if the markdown content exists in the document
if (!markdown) {
throw new Error(
"Markdown content is missing in the document. This is likely due to an error in the scraping process. Please try again or reach out to help@mendable.ai"
);
let extractionTarget = document.markdown;
if (mode === "raw-html") {
extractionTarget = document.rawHtml;
}
// Check if the markdown content exists in the document
if (!extractionTarget) {
return null;
// throw new Error(
// `${mode} content is missing in the document. This is likely due to an error in the scraping process. Please try again or reach out to help@mendable.ai`
// );
}
// count number of tokens
const numTokens = numTokensFromString(document.markdown, "gpt-4");
const numTokens = numTokensFromString(extractionTarget, "gpt-4");
if (numTokens > maxTokens) {
// trim the document to the maximum number of tokens, tokens != characters
markdown = markdown.slice(0, (maxTokens * modifier));
extractionTarget = extractionTarget.slice(0, maxTokens * modifier);
}
return [[{ type: "text", text: markdown }], numTokens];
return [[{ type: "text", text: extractionTarget }], numTokens];
}
export async function generateOpenAICompletions({
client,
model = "gpt-4o",
model = process.env.MODEL_NAME || "gpt-4o-mini",
document,
schema, //TODO - add zod dynamic type checking
prompt = defaultPrompt,
systemPrompt = defaultPrompt,
prompt,
temperature,
mode,
}: {
client: OpenAI;
model?: string;
document: Document;
schema: any; // This should be replaced with a proper Zod schema type when available
prompt?: string;
systemPrompt?: string;
temperature?: number;
mode: "markdown" | "raw-html";
}): Promise<Document> {
const openai = client as OpenAI;
const [content, numTokens] = prepareOpenAIDoc(document);
const preparedDoc = prepareOpenAIDoc(document, mode);
const completion = await openai.chat.completions.create({
if (preparedDoc === null) {
return {
...document,
warning:
"LLM extraction was not performed since the document's content is empty or missing.",
};
}
const [content, numTokens] = preparedDoc;
let completion;
let llmExtraction;
if (prompt && !schema) {
const jsonCompletion = await openai.chat.completions.create({
model,
messages: [
{
role: "system",
content: prompt,
content: systemPrompt,
},
{ role: "user", content },
{
role: "user",
content: `Transform the above content into structured json output based on the following user request: ${prompt}`,
},
],
response_format: { type: "json_object" },
temperature,
});
try {
llmExtraction = JSON.parse(
jsonCompletion.choices[0].message.content.trim()
);
} catch (e) {
throw new Error("Invalid JSON");
}
} else {
completion = await openai.chat.completions.create({
model,
messages: [
{
role: "system",
content: systemPrompt,
},
{ role: "user", content },
],
@ -72,20 +120,26 @@ export async function generateOpenAICompletions({
},
},
],
tool_choice: { "type": "function", "function": {"name": "extract_content"}},
tool_choice: { type: "function", function: { name: "extract_content" } },
temperature,
});
const c = completion.choices[0].message.tool_calls[0].function.arguments;
// Extract the LLM extraction content from the completion response
const llmExtraction = JSON.parse(c);
try {
llmExtraction = JSON.parse(c);
} catch (e) {
throw new Error("Invalid JSON");
}
}
// Return the document with the LLM extraction content added
return {
...document,
llm_extraction: llmExtraction,
warning: numTokens > maxTokens ? `Page was trimmed to fit the maximum token limit defined by the LLM model (Max: ${maxTokens} tokens, Attemped: ${numTokens} tokens). If results are not good, email us at help@mendable.ai so we can help you.` : undefined,
warning:
numTokens > maxTokens
? `Page was trimmed to fit the maximum token limit defined by the LLM model (Max: ${maxTokens} tokens, Attemped: ${numTokens} tokens). If results are not good, email us at help@mendable.ai so we can help you.`
: undefined,
};
}

40
apps/api/src/lib/__tests__/html-to-markdown.test.ts Normal file
View File

@ -0,0 +1,40 @@
import { parseMarkdown } from '../html-to-markdown';
describe('parseMarkdown', () => {
it('should correctly convert simple HTML to Markdown', async () => {
const html = '<p>Hello, world!</p>';
const expectedMarkdown = 'Hello, world!';
await expect(parseMarkdown(html)).resolves.toBe(expectedMarkdown);
});
it('should convert complex HTML with nested elements to Markdown', async () => {
const html = '<div><p>Hello <strong>bold</strong> world!</p><ul><li>List item</li></ul></div>';
const expectedMarkdown = 'Hello **bold** world!\n\n- List item';
await expect(parseMarkdown(html)).resolves.toBe(expectedMarkdown);
});
it('should return empty string when input is empty', async () => {
const html = '';
const expectedMarkdown = '';
await expect(parseMarkdown(html)).resolves.toBe(expectedMarkdown);
});
it('should handle null input gracefully', async () => {
const html = null;
const expectedMarkdown = '';
await expect(parseMarkdown(html)).resolves.toBe(expectedMarkdown);
});
it('should handle various types of invalid HTML gracefully', async () => {
const invalidHtmls = [
{ html: '<html><p>Unclosed tag', expected: 'Unclosed tag' },
{ html: '<div><span>Missing closing div', expected: 'Missing closing div' },
{ html: '<p><strong>Wrong nesting</em></strong></p>', expected: '**Wrong nesting**' },
{ html: '<a href="http://example.com">Link without closing tag', expected: '[Link without closing tag](http://example.com)' }
];
for (const { html, expected } of invalidHtmls) {
await expect(parseMarkdown(html)).resolves.toBe(expected);
}
});
});

134
apps/api/src/lib/__tests__/job-priority.test.ts Normal file
View File

@ -0,0 +1,134 @@
import {
getJobPriority,
addJobPriority,
deleteJobPriority,
} from "../job-priority";
import { redisConnection } from "../../services/queue-service";
import { PlanType } from "../../types";
jest.mock("../../services/queue-service", () => ({
redisConnection: {
sadd: jest.fn(),
srem: jest.fn(),
scard: jest.fn(),
expire: jest.fn(),
},
}));
describe("Job Priority Tests", () => {
afterEach(() => {
jest.clearAllMocks();
});
test("addJobPriority should add job_id to the set and set expiration", async () => {
const team_id = "team1";
const job_id = "job1";
await addJobPriority(team_id, job_id);
expect(redisConnection.sadd).toHaveBeenCalledWith(
`limit_team_id:${team_id}`,
job_id
);
expect(redisConnection.expire).toHaveBeenCalledWith(
`limit_team_id:${team_id}`,
60
);
});
test("deleteJobPriority should remove job_id from the set", async () => {
const team_id = "team1";
const job_id = "job1";
await deleteJobPriority(team_id, job_id);
expect(redisConnection.srem).toHaveBeenCalledWith(
`limit_team_id:${team_id}`,
job_id
);
});
test("getJobPriority should return correct priority based on plan and set length", async () => {
const team_id = "team1";
const plan: PlanType = "standard";
(redisConnection.scard as jest.Mock).mockResolvedValue(150);
const priority = await getJobPriority({ plan, team_id });
expect(priority).toBe(10);
(redisConnection.scard as jest.Mock).mockResolvedValue(250);
const priorityExceeded = await getJobPriority({ plan, team_id });
expect(priorityExceeded).toBe(20); // basePriority + Math.ceil((250 - 200) * 0.4)
});
test("getJobPriority should handle different plans correctly", async () => {
const team_id = "team1";
(redisConnection.scard as jest.Mock).mockResolvedValue(50);
let plan: PlanType = "hobby";
let priority = await getJobPriority({ plan, team_id });
expect(priority).toBe(10);
(redisConnection.scard as jest.Mock).mockResolvedValue(150);
plan = "hobby";
priority = await getJobPriority({ plan, team_id });
expect(priority).toBe(25); // basePriority + Math.ceil((150 - 50) * 0.3)
(redisConnection.scard as jest.Mock).mockResolvedValue(25);
plan = "free";
priority = await getJobPriority({ plan, team_id });
expect(priority).toBe(10);
(redisConnection.scard as jest.Mock).mockResolvedValue(60);
plan = "free";
priority = await getJobPriority({ plan, team_id });
expect(priority).toBe(28); // basePriority + Math.ceil((60 - 25) * 0.5)
});
test("addJobPriority should reset expiration time when adding new job", async () => {
const team_id = "team1";
const job_id1 = "job1";
const job_id2 = "job2";
await addJobPriority(team_id, job_id1);
expect(redisConnection.expire).toHaveBeenCalledWith(
`limit_team_id:${team_id}`,
60
);
// Clear the mock calls
(redisConnection.expire as jest.Mock).mockClear();
// Add another job
await addJobPriority(team_id, job_id2);
expect(redisConnection.expire).toHaveBeenCalledWith(
`limit_team_id:${team_id}`,
60
);
});
test("Set should expire after 60 seconds", async () => {
const team_id = "team1";
const job_id = "job1";
jest.useFakeTimers();
await addJobPriority(team_id, job_id);
expect(redisConnection.expire).toHaveBeenCalledWith(
`limit_team_id:${team_id}`,
60
);
// Fast-forward time by 59 seconds
jest.advanceTimersByTime(59000);
// The set should still exist
expect(redisConnection.scard).not.toHaveBeenCalled();
// Fast-forward time by 2 more seconds (total 61 seconds)
jest.advanceTimersByTime(2000);
// Check if the set has been removed (scard should return 0)
(redisConnection.scard as jest.Mock).mockResolvedValue(0);
const setSize = await redisConnection.scard(`limit_team_id:${team_id}`);
expect(setSize).toBe(0);
jest.useRealTimers();
});
});

48
apps/api/src/lib/concurrency-limit.ts Normal file
View File

@ -0,0 +1,48 @@
import { getRateLimiterPoints } from "../services/rate-limiter";
import { redisConnection } from "../services/queue-service";
import { RateLimiterMode } from "../types";
import { JobsOptions } from "bullmq";
const constructKey = (team_id: string) => "concurrency-limiter:" + team_id;
const constructQueueKey = (team_id: string) => "concurrency-limit-queue:" + team_id;
const stalledJobTimeoutMs = 2 * 60 * 1000;
export function getConcurrencyLimitMax(plan: string): number {
return getRateLimiterPoints(RateLimiterMode.Scrape, undefined, plan);
}
export async function cleanOldConcurrencyLimitEntries(team_id: string, now: number = Date.now()) {
await redisConnection.zremrangebyscore(constructKey(team_id), -Infinity, now);
}
export async function getConcurrencyLimitActiveJobs(team_id: string, now: number = Date.now()): Promise<string[]> {
return await redisConnection.zrangebyscore(constructKey(team_id), now, Infinity);
}
export async function pushConcurrencyLimitActiveJob(team_id: string, id: string, now: number = Date.now()) {
await redisConnection.zadd(constructKey(team_id), now + stalledJobTimeoutMs, id);
}
export async function removeConcurrencyLimitActiveJob(team_id: string, id: string) {
await redisConnection.zrem(constructKey(team_id), id);
}
export type ConcurrencyLimitedJob = {
id: string;
data: any;
opts: JobsOptions;
priority?: number;
}
export async function takeConcurrencyLimitedJob(team_id: string): Promise<ConcurrencyLimitedJob | null> {
const res = await redisConnection.zmpop(1, constructQueueKey(team_id), "MIN");
if (res === null || res === undefined) {
return null;
}
return JSON.parse(res[1][0][0]);
}
export async function pushConcurrencyLimitedJob(team_id: string, job: ConcurrencyLimitedJob) {
await redisConnection.zadd(constructQueueKey(team_id), job.priority ?? 1, JSON.stringify(job));
}

152
apps/api/src/lib/crawl-redis.ts Normal file
View File

@ -0,0 +1,152 @@
import { WebCrawler } from "../scraper/WebScraper/crawler";
import { redisConnection } from "../services/queue-service";
import { Logger } from "./logger";
export type StoredCrawl = {
originUrl?: string;
crawlerOptions: any;
pageOptions: any;
team_id: string;
plan: string;
robots?: string;
cancelled?: boolean;
createdAt: number;
};
export async function saveCrawl(id: string, crawl: StoredCrawl) {
await redisConnection.set("crawl:" + id, JSON.stringify(crawl));
await redisConnection.expire("crawl:" + id, 24 * 60 * 60, "NX");
}
export async function getCrawl(id: string): Promise<StoredCrawl | null> {
const x = await redisConnection.get("crawl:" + id);
if (x === null) {
return null;
}
return JSON.parse(x);
}
export async function getCrawlExpiry(id: string): Promise<Date> {
const d = new Date();
const ttl = await redisConnection.pttl("crawl:" + id);
d.setMilliseconds(d.getMilliseconds() + ttl);
d.setMilliseconds(0);
return d;
}
export async function addCrawlJob(id: string, job_id: string) {
await redisConnection.sadd("crawl:" + id + ":jobs", job_id);
await redisConnection.expire("crawl:" + id + ":jobs", 24 * 60 * 60, "NX");
}
export async function addCrawlJobs(id: string, job_ids: string[]) {
await redisConnection.sadd("crawl:" + id + ":jobs", ...job_ids);
await redisConnection.expire("crawl:" + id + ":jobs", 24 * 60 * 60, "NX");
}
export async function addCrawlJobDone(id: string, job_id: string) {
await redisConnection.sadd("crawl:" + id + ":jobs_done", job_id);
await redisConnection.lpush("crawl:" + id + ":jobs_done_ordered", job_id);
await redisConnection.expire("crawl:" + id + ":jobs_done", 24 * 60 * 60, "NX");
await redisConnection.expire("crawl:" + id + ":jobs_done_ordered", 24 * 60 * 60, "NX");
}
export async function getDoneJobsOrderedLength(id: string): Promise<number> {
return await redisConnection.llen("crawl:" + id + ":jobs_done_ordered");
}
export async function getDoneJobsOrdered(id: string, start = 0, end = -1): Promise<string[]> {
return await redisConnection.lrange("crawl:" + id + ":jobs_done_ordered", start, end);
}
export async function isCrawlFinished(id: string) {
return (await redisConnection.scard("crawl:" + id + ":jobs_done")) === (await redisConnection.scard("crawl:" + id + ":jobs"));
}
export async function isCrawlFinishedLocked(id: string) {
return (await redisConnection.exists("crawl:" + id + ":finish"));
}
export async function finishCrawl(id: string) {
if (await isCrawlFinished(id)) {
const set = await redisConnection.setnx("crawl:" + id + ":finish", "yes");
if (set === 1) {
await redisConnection.expire("crawl:" + id + ":finish", 24 * 60 * 60);
}
return set === 1
}
}
export async function getCrawlJobs(id: string): Promise<string[]> {
return await redisConnection.smembers("crawl:" + id + ":jobs");
}
export async function getThrottledJobs(teamId: string): Promise<string[]> {
return await redisConnection.zrangebyscore("concurrency-limiter:" + teamId + ":throttled", Date.now(), Infinity);
}
export async function lockURL(id: string, sc: StoredCrawl, url: string): Promise<boolean> {
if (typeof sc.crawlerOptions?.limit === "number") {
if (await redisConnection.scard("crawl:" + id + ":visited") >= sc.crawlerOptions.limit) {
return false;
}
}
try {
const urlO = new URL(url);
urlO.search = "";
urlO.hash = "";
url = urlO.href;
} catch (error) {
Logger.warn("Failed to normalize URL " + JSON.stringify(url) + ": " + error);
}
const res = (await redisConnection.sadd("crawl:" + id + ":visited", url)) !== 0
await redisConnection.expire("crawl:" + id + ":visited", 24 * 60 * 60, "NX");
return res;
}
/// NOTE: does not check limit. only use if limit is checked beforehand e.g. with sitemap
export async function lockURLs(id: string, urls: string[]): Promise<boolean> {
urls = urls.map(url => {
try {
const urlO = new URL(url);
urlO.search = "";
urlO.hash = "";
return urlO.href;
} catch (error) {
Logger.warn("Failed to normalize URL " + JSON.stringify(url) + ": " + error);
}
return url;
});
const res = (await redisConnection.sadd("crawl:" + id + ":visited", ...urls)) !== 0
await redisConnection.expire("crawl:" + id + ":visited", 24 * 60 * 60, "NX");
return res;
}
export function crawlToCrawler(id: string, sc: StoredCrawl): WebCrawler {
const crawler = new WebCrawler({
jobId: id,
initialUrl: sc.originUrl,
includes: sc.crawlerOptions?.includes ?? [],
excludes: sc.crawlerOptions?.excludes ?? [],
maxCrawledLinks: sc.crawlerOptions?.maxCrawledLinks ?? 1000,
maxCrawledDepth: sc.crawlerOptions?.maxDepth ?? 10,
limit: sc.crawlerOptions?.limit ?? 10000,
generateImgAltText: sc.crawlerOptions?.generateImgAltText ?? false,
allowBackwardCrawling: sc.crawlerOptions?.allowBackwardCrawling ?? false,
allowExternalContentLinks: sc.crawlerOptions?.allowExternalContentLinks ?? false,
});
if (sc.robots !== undefined) {
try {
crawler.importRobotsTxt(sc.robots);
} catch (_) {}
}
return crawler;
}

1
apps/api/src/lib/custom-error.ts
View File

@ -19,3 +19,4 @@ export class CustomError extends Error {
Object.setPrototypeOf(this, CustomError.prototype);
}
}

28
apps/api/src/lib/default-values.ts Normal file
View File

@ -0,0 +1,28 @@
export const defaultOrigin = "api";
export const defaultTimeout = 60000; // 60 seconds
export const defaultPageOptions = {
onlyMainContent: false,
includeHtml: false,
waitFor: 0,
screenshot: false,
fullPageScreenshot: false,
parsePDF: true
};
export const defaultCrawlerOptions = {
allowBackwardCrawling: false,
limit: 10000
}
export const defaultCrawlPageOptions = {
onlyMainContent: false,
includeHtml: false,
removeTags: [],
parsePDF: true
}
export const defaultExtractorOptions = {
mode: "markdown"
}

78
apps/api/src/lib/entities.ts
View File

@ -10,22 +10,63 @@ export interface Progress {
currentDocument?: Document;
}
export type Action = {
type: "wait",
milliseconds?: number,
selector?: string,
} | {
type: "click",
selector: string,
} | {
type: "screenshot",
fullPage?: boolean,
} | {
type: "write",
text: string,
} | {
type: "press",
key: string,
} | {
type: "scroll",
direction: "up" | "down"
} | {
type: "scrape",
}
export type PageOptions = {
includeMarkdown?: boolean;
includeExtract?: boolean;
onlyMainContent?: boolean;
includeHtml?: boolean;
includeRawHtml?: boolean;
fallback?: boolean;
fetchPageContent?: boolean;
waitFor?: number;
screenshot?: boolean;
fullPageScreenshot?: boolean;
headers?: Record<string, string>;
replaceAllPathsWithAbsolutePaths?: boolean;
parsePDF?: boolean;
removeTags?: string | string[];
onlyIncludeTags?: string | string[];
includeLinks?: boolean;
useFastMode?: boolean; // beta
disableJsDom?: boolean; // beta
atsv?: boolean; // anti-bot solver, beta
actions?: Action[]; // beta
geolocation?: {
country?: string;
};
skipTlsVerification?: boolean;
removeBase64Images?: boolean;
mobile?: boolean;
};
export type ExtractorOptions = {
mode: "markdown" | "llm-extraction";
mode: "markdown" | "llm-extraction" | "llm-extraction-from-markdown" | "llm-extraction-from-raw-html";
extractionPrompt?: string;
extractionSchema?: Record<string, any>;
userPrompt?: string;
}
export type SearchOptions = {
@ -39,8 +80,8 @@ export type SearchOptions = {
export type CrawlerOptions = {
returnOnlyUrls?: boolean;
includes?: string[];
excludes?: string[];
includes?: string | string[];
excludes?: string | string[];
maxCrawledLinks?: number;
maxDepth?: number;
limit?: number;
@ -49,9 +90,11 @@ export type CrawlerOptions = {
ignoreSitemap?: boolean;
mode?: "default" | "fast"; // have a mode of some sort
allowBackwardCrawling?: boolean;
allowExternalContentLinks?: boolean;
}
export type WebScraperOptions = {
jobId: string;
urls: string[];
mode: "single_urls" | "sitemap" | "crawl";
crawlerOptions?: CrawlerOptions;
@ -59,6 +102,8 @@ export type WebScraperOptions = {
extractorOptions?: ExtractorOptions;
concurrentRequests?: number;
bullJobId?: string;
priority?: number;
teamId?: string;
};
export interface DocumentUrl {
@ -71,6 +116,7 @@ export class Document {
content: string;
markdown?: string;
html?: string;
rawHtml?: string;
llm_extraction?: Record<string, any>;
createdAt?: Date;
updatedAt?: Date;
@ -82,8 +128,12 @@ export class Document {
childrenLinks?: string[];
provider?: string;
warning?: string;
actions?: {
screenshots: string[];
}
index?: number;
linksOnPage?: string[]; // Add this new field as a separate property
constructor(data: Partial<Document>) {
if (!data.content) {
@ -97,6 +147,7 @@ export class Document {
this.markdown = data.markdown || "";
this.childrenLinks = data.childrenLinks || undefined;
this.provider = data.provider || undefined;
this.linksOnPage = data.linksOnPage; // Assign linksOnPage if provided
}
}
@ -117,7 +168,26 @@ export class SearchResult {
}
}
export interface ScrapeActionContent {
url: string;
html: string;
}
export interface FireEngineResponse {
html: string;
screenshot: string;
screenshots?: string[];
pageStatusCode?: number;
pageError?: string;
scrapeActionContent?: ScrapeActionContent[];
}
export interface FireEngineOptions{
mobileProxy?: boolean;
method?: string;
engine?: string;
blockMedia?: boolean;
blockAds?: boolean;
disableJsDom?: boolean;
atsv?: boolean; // beta
}

90
apps/api/src/lib/html-to-markdown.ts
View File

@ -1,8 +1,68 @@
export function parseMarkdown(html: string) {
import koffi from 'koffi';
import { join } from 'path';
import "../services/sentry"
import * as Sentry from "@sentry/node";
import dotenv from 'dotenv';
import { Logger } from './logger';
dotenv.config();
// TODO: add a timeout to the Go parser
class GoMarkdownConverter {
private static instance: GoMarkdownConverter;
private convert: any;
private constructor() {
const goExecutablePath = join(process.cwd(), 'sharedLibs', 'go-html-to-md', 'html-to-markdown.so');
const lib = koffi.load(goExecutablePath);
this.convert = lib.func('ConvertHTMLToMarkdown', 'string', ['string']);
}
public static getInstance(): GoMarkdownConverter {
if (!GoMarkdownConverter.instance) {
GoMarkdownConverter.instance = new GoMarkdownConverter();
}
return GoMarkdownConverter.instance;
}
public async convertHTMLToMarkdown(html: string): Promise<string> {
return new Promise<string>((resolve, reject) => {
this.convert.async(html, (err: Error, res: string) => {
if (err) {
reject(err);
} else {
resolve(res);
}
});
});
}
}
export async function parseMarkdown(html: string): Promise<string> {
if (!html) {
return '';
}
try {
if (process.env.USE_GO_MARKDOWN_PARSER == "true") {
const converter = GoMarkdownConverter.getInstance();
let markdownContent = await converter.convertHTMLToMarkdown(html);
markdownContent = processMultiLineLinks(markdownContent);
markdownContent = removeSkipToContentLinks(markdownContent);
Logger.info(`HTML to Markdown conversion using Go parser successful`);
return markdownContent;
}
} catch (error) {
Sentry.captureException(error);
Logger.error(`Error converting HTML to Markdown with Go parser: ${error}`);
}
// Fallback to TurndownService if Go parser fails or is not enabled
var TurndownService = require("turndown");
var turndownPluginGfm = require('joplin-turndown-plugin-gfm')
var turndownPluginGfm = require('joplin-turndown-plugin-gfm');
const turndownService = new TurndownService();
turndownService.addRule("inlineLink", {
@ -21,9 +81,20 @@ export function parseMarkdown(html: string) {
});
var gfm = turndownPluginGfm.gfm;
turndownService.use(gfm);
let markdownContent = turndownService.turndown(html);
// multiple line links
try {
let markdownContent = await turndownService.turndown(html);
markdownContent = processMultiLineLinks(markdownContent);
markdownContent = removeSkipToContentLinks(markdownContent);
return markdownContent;
} catch (error) {
console.error("Error converting HTML to Markdown: ", error);
return ""; // Optionally return an empty string or handle the error as needed
}
}
function processMultiLineLinks(markdownContent: string): string {
let insideLinkContent = false;
let newMarkdownContent = "";
let linkOpenCount = 0;
@ -43,13 +114,14 @@ export function parseMarkdown(html: string) {
newMarkdownContent += char;
}
}
markdownContent = newMarkdownContent;
return newMarkdownContent;
}
function removeSkipToContentLinks(markdownContent: string): string {
// Remove [Skip to Content](#page) and [Skip to content](#skip)
markdownContent = markdownContent.replace(
const newMarkdownContent = markdownContent.replace(
/\[Skip to Content\]\(#[^\)]*\)/gi,
""
);
return markdownContent;
return newMarkdownContent;
}

99
apps/api/src/lib/job-priority.ts Normal file
View File

@ -0,0 +1,99 @@
import { redisConnection } from "../../src/services/queue-service";
import { PlanType } from "../../src/types";
import { Logger } from "./logger";
const SET_KEY_PREFIX = "limit_team_id:";
export async function addJobPriority(team_id, job_id) {
try {
const setKey = SET_KEY_PREFIX + team_id;
// Add scrape job id to the set
await redisConnection.sadd(setKey, job_id);
// This approach will reset the expiration time to 60 seconds every time a new job is added to the set.
await redisConnection.expire(setKey, 60);
} catch (e) {
Logger.error(`Add job priority (sadd) failed: ${team_id}, ${job_id}`);
}
}
export async function deleteJobPriority(team_id, job_id) {
try {
const setKey = SET_KEY_PREFIX + team_id;
// remove job_id from the set
await redisConnection.srem(setKey, job_id);
} catch (e) {
Logger.error(`Delete job priority (srem) failed: ${team_id}, ${job_id}`);
}
}
export async function getJobPriority({
plan,
team_id,
basePriority = 10,
}: {
plan: PlanType;
team_id: string;
basePriority?: number;
}): Promise<number> {
if (team_id === "d97c4ceb-290b-4957-8432-2b2a02727d95") {
return 50;
}
try {
const setKey = SET_KEY_PREFIX + team_id;
// Get the length of the set
const setLength = await redisConnection.scard(setKey);
// Determine the priority based on the plan and set length
let planModifier = 1;
let bucketLimit = 0;
switch (plan) {
case "free":
bucketLimit = 25;
planModifier = 0.5;
break;
case "hobby":
bucketLimit = 100;
planModifier = 0.3;
break;
case "standard":
case "standardnew":
bucketLimit = 200;
planModifier = 0.2;
break;
case "growth":
case "growthdouble":
bucketLimit = 400;
planModifier = 0.1;
break;
case "etier2c":
bucketLimit = 1000;
planModifier = 0.05;
break;
default:
bucketLimit = 25;
planModifier = 1;
break;
}
// if length set is smaller than set, just return base priority
if (setLength <= bucketLimit) {
return basePriority;
} else {
// If not, we keep base priority + planModifier
return Math.ceil(
basePriority + Math.ceil((setLength - bucketLimit) * planModifier)
);
}
} catch (e) {
Logger.error(
`Get job priority failed: ${team_id}, ${plan}, ${basePriority}`
);
return basePriority;
}
}

57
apps/api/src/lib/logger.ts Normal file
View File

@ -0,0 +1,57 @@
import { configDotenv } from "dotenv";
configDotenv();
enum LogLevel {
NONE = 'NONE', // No logs will be output.
ERROR = 'ERROR', // For logging error messages that indicate a failure in a specific operation.
WARN = 'WARN', // For logging potentially harmful situations that are not necessarily errors.
INFO = 'INFO', // For logging informational messages that highlight the progress of the application.
DEBUG = 'DEBUG', // For logging detailed information on the flow through the system, primarily used for debugging.
TRACE = 'TRACE' // For logging more detailed information than the DEBUG level.
}
export class Logger {
static colors = {
ERROR: '\x1b[31m%s\x1b[0m', // Red
WARN: '\x1b[33m%s\x1b[0m', // Yellow
INFO: '\x1b[34m%s\x1b[0m', // Blue
DEBUG: '\x1b[36m%s\x1b[0m', // Cyan
TRACE: '\x1b[35m%s\x1b[0m' // Magenta
};
static log (message: string, level: LogLevel) {
const logLevel: LogLevel = LogLevel[process.env.LOGGING_LEVEL as keyof typeof LogLevel] || LogLevel.TRACE;
const levels = [LogLevel.NONE, LogLevel.ERROR, LogLevel.WARN, LogLevel.INFO, LogLevel.DEBUG, LogLevel.TRACE];
const currentLevelIndex = levels.indexOf(logLevel);
const messageLevelIndex = levels.indexOf(level);
if (currentLevelIndex >= messageLevelIndex) {
const color = Logger.colors[level];
console[level.toLowerCase()](color, `[${new Date().toISOString()}]${level} - ${message}`);
// const useDbAuthentication = process.env.USE_DB_AUTHENTICATION === 'true';
// if (useDbAuthentication) {
// save to supabase? another place?
// supabase.from('logs').insert({ level: level, message: message, timestamp: new Date().toISOString(), success: boolean });
// }
}
}
static error(message: string | any) {
Logger.log(message, LogLevel.ERROR);
}
static warn(message: string) {
Logger.log(message, LogLevel.WARN);
}
static info(message: string) {
Logger.log(message, LogLevel.INFO);
}
static debug(message: string) {
Logger.log(message, LogLevel.DEBUG);
}
static trace(message: string) {
Logger.log(message, LogLevel.TRACE);
}
}

46
apps/api/src/lib/map-cosine.ts Normal file
View File

@ -0,0 +1,46 @@
import { Logger } from "./logger";
export function performCosineSimilarity(links: string[], searchQuery: string) {
try {
// Function to calculate cosine similarity
const cosineSimilarity = (vec1: number[], vec2: number[]): number => {
const dotProduct = vec1.reduce((sum, val, i) => sum + val * vec2[i], 0);
const magnitude1 = Math.sqrt(
vec1.reduce((sum, val) => sum + val * val, 0)
);
const magnitude2 = Math.sqrt(
vec2.reduce((sum, val) => sum + val * val, 0)
);
if (magnitude1 === 0 || magnitude2 === 0) return 0;
return dotProduct / (magnitude1 * magnitude2);
};
// Function to convert text to vector
const textToVector = (text: string): number[] => {
const words = searchQuery.toLowerCase().split(/\W+/);
return words.map((word) => {
const count = (text.toLowerCase().match(new RegExp(word, "g")) || [])
.length;
return count / text.length;
});
};
// Calculate similarity scores
const similarityScores = links.map((link) => {
const linkVector = textToVector(link);
const searchVector = textToVector(searchQuery);
return cosineSimilarity(linkVector, searchVector);
});
// Sort links based on similarity scores and print scores
const a = links
.map((link, index) => ({ link, score: similarityScores[index] }))
.sort((a, b) => b.score - a.score);
links = a.map((item) => item.link);
return links;
} catch (error) {
Logger.error(`Error performing cosine similarity: ${error}`);
return links;
}
}

87
apps/api/src/lib/scrape-events.ts Normal file
View File

@ -0,0 +1,87 @@
import { Job } from "bullmq";
import type { baseScrapers } from "../scraper/WebScraper/single_url";
import { supabase_service as supabase } from "../services/supabase";
import { Logger } from "./logger";
import { configDotenv } from "dotenv";
configDotenv();
export type ScrapeErrorEvent = {
type: "error",
message: string,
stack?: string,
}
export type ScrapeScrapeEvent = {
type: "scrape",
url: string,
worker?: string,
method: (typeof baseScrapers)[number],
result: null | {
success: boolean,
response_code?: number,
response_size?: number,
error?: string | object,
// proxy?: string,
time_taken: number,
},
}
export type ScrapeQueueEvent = {
type: "queue",
event: "waiting" | "active" | "completed" | "paused" | "resumed" | "removed" | "failed",
worker?: string,
}
export type ScrapeEvent = ScrapeErrorEvent | ScrapeScrapeEvent | ScrapeQueueEvent;
export class ScrapeEvents {
static async insert(jobId: string, content: ScrapeEvent) {
if (jobId === "TEST") return null;
const useDbAuthentication = process.env.USE_DB_AUTHENTICATION === 'true';
if (useDbAuthentication) {
try {
const result = await supabase.from("scrape_events").insert({
job_id: jobId,
type: content.type,
content: content,
// created_at
}).select().single();
return (result.data as any).id;
} catch (error) {
// Logger.error(`Error inserting scrape event: ${error}`);
return null;
}
}
return null;
}
static async updateScrapeResult(logId: number | null, result: ScrapeScrapeEvent["result"]) {
if (logId === null) return;
try {
const previousLog = (await supabase.from("scrape_events").select().eq("id", logId).single()).data as any;
await supabase.from("scrape_events").update({
content: {
...previousLog.content,
result,
}
}).eq("id", logId);
} catch (error) {
Logger.error(`Error updating scrape result: ${error}`);
}
}
static async logJobEvent(job: Job | any, event: ScrapeQueueEvent["event"]) {
try {
await this.insert(((job as any).id ? (job as any).id : job) as string, {
type: "queue",
event,
worker: process.env.FLY_MACHINE_ID,
});
} catch (error) {
Logger.error(`Error logging job event: ${error}`);
}
}
}

93
apps/api/src/lib/supabase-jobs.ts Normal file
View File

@ -0,0 +1,93 @@
import { supabase_service } from "../services/supabase";
import { Logger } from "./logger";
import * as Sentry from "@sentry/node";
/**
* Get a single firecrawl_job by ID
* @param jobId ID of Job
* @returns {any | null} Job
*/
export const supabaseGetJobById = async (jobId: string) => {
const { data, error } = await supabase_service
.from("firecrawl_jobs")
.select("*")
.eq("job_id", jobId)
.single();
if (error) {
return null;
}
if (!data) {
return null;
}
return data;
};
/**
* Get multiple firecrawl_jobs by ID. Use this if you're not requesting a lot (50+) of jobs at once.
* @param jobIds IDs of Jobs
* @returns {any[]} Jobs
*/
export const supabaseGetJobsById = async (jobIds: string[]) => {
const { data, error } = await supabase_service
.from("firecrawl_jobs")
.select()
.in("job_id", jobIds);
if (error) {
Logger.error(`Error in supabaseGetJobsById: ${error}`);
Sentry.captureException(error);
return [];
}
if (!data) {
return [];
}
return data;
};
/**
* Get multiple firecrawl_jobs by crawl ID. Use this if you need a lot of jobs at once.
* @param crawlId ID of crawl
* @returns {any[]} Jobs
*/
export const supabaseGetJobsByCrawlId = async (crawlId: string) => {
const { data, error } = await supabase_service
.from("firecrawl_jobs")
.select()
.eq("crawl_id", crawlId)
if (error) {
Logger.error(`Error in supabaseGetJobsByCrawlId: ${error}`);
Sentry.captureException(error);
return [];
}
if (!data) {
return [];
}
return data;
};
export const supabaseGetJobByIdOnlyData = async (jobId: string) => {
const { data, error } = await supabase_service
.from("firecrawl_jobs")
.select("docs, team_id")
.eq("job_id", jobId)
.single();
if (error) {
return null;
}
if (!data) {
return null;
}
return data;
};

1
apps/api/src/lib/timeout.ts Normal file
View File

@ -0,0 +1 @@
export const axiosTimeout = 3000;

2261
apps/api/src/lib/validate-country.ts Normal file
View File

File diff suppressed because it is too large Load Diff

159
apps/api/src/lib/validateUrl.test.ts Normal file
View File

@ -0,0 +1,159 @@
import { isSameDomain, removeDuplicateUrls } from "./validateUrl";
import { isSameSubdomain } from "./validateUrl";
describe("isSameDomain", () => {
it("should return true for a subdomain", () => {
const result = isSameDomain("http://sub.example.com", "http://example.com");
expect(result).toBe(true);
});
it("should return true for the same domain", () => {
const result = isSameDomain("http://example.com", "http://example.com");
expect(result).toBe(true);
});
it("should return false for different domains", () => {
const result = isSameDomain("http://example.com", "http://another.com");
expect(result).toBe(false);
});
it("should return true for a subdomain with different protocols", () => {
const result = isSameDomain("https://sub.example.com", "http://example.com");
expect(result).toBe(true);
});
it("should return false for invalid URLs", () => {
const result = isSameDomain("invalid-url", "http://example.com");
expect(result).toBe(false);
const result2 = isSameDomain("http://example.com", "invalid-url");
expect(result2).toBe(false);
});
it("should return true for a subdomain with www prefix", () => {
const result = isSameDomain("http://www.sub.example.com", "http://example.com");
expect(result).toBe(true);
});
it("should return true for the same domain with www prefix", () => {
const result = isSameDomain("http://docs.s.s.example.com", "http://example.com");
expect(result).toBe(true);
});
});
describe("isSameSubdomain", () => {
it("should return false for a subdomain", () => {
const result = isSameSubdomain("http://example.com", "http://docs.example.com");
expect(result).toBe(false);
});
it("should return true for the same subdomain", () => {
const result = isSameSubdomain("http://docs.example.com", "http://docs.example.com");
expect(result).toBe(true);
});
it("should return false for different subdomains", () => {
const result = isSameSubdomain("http://docs.example.com", "http://blog.example.com");
expect(result).toBe(false);
});
it("should return false for different domains", () => {
const result = isSameSubdomain("http://example.com", "http://another.com");
expect(result).toBe(false);
});
it("should return false for invalid URLs", () => {
const result = isSameSubdomain("invalid-url", "http://example.com");
expect(result).toBe(false);
const result2 = isSameSubdomain("http://example.com", "invalid-url");
expect(result2).toBe(false);
});
it("should return true for the same subdomain with different protocols", () => {
const result = isSameSubdomain("https://docs.example.com", "http://docs.example.com");
expect(result).toBe(true);
});
it("should return true for the same subdomain with www prefix", () => {
const result = isSameSubdomain("http://www.docs.example.com", "http://docs.example.com");
expect(result).toBe(true);
});
it("should return false for a subdomain with www prefix and different subdomain", () => {
const result = isSameSubdomain("http://www.docs.example.com", "http://blog.example.com");
expect(result).toBe(false);
});
});
describe("removeDuplicateUrls", () => {
it("should remove duplicate URLs with different protocols", () => {
const urls = [
"http://example.com",
"https://example.com",
"http://www.example.com",
"https://www.example.com"
];
const result = removeDuplicateUrls(urls);
expect(result).toEqual(["https://example.com"]);
});
it("should keep URLs with different paths", () => {
const urls = [
"https://example.com/page1",
"https://example.com/page2",
"https://example.com/page1?param=1",
"https://example.com/page1#section1"
];
const result = removeDuplicateUrls(urls);
expect(result).toEqual([
"https://example.com/page1",
"https://example.com/page2",
"https://example.com/page1?param=1",
"https://example.com/page1#section1"
]);
});
it("should prefer https over http", () => {
const urls = [
"http://example.com",
"https://example.com"
];
const result = removeDuplicateUrls(urls);
expect(result).toEqual(["https://example.com"]);
});
it("should prefer non-www over www", () => {
const urls = [
"https://www.example.com",
"https://example.com"
];
const result = removeDuplicateUrls(urls);
expect(result).toEqual(["https://example.com"]);
});
it("should handle empty input", () => {
const urls: string[] = [];
const result = removeDuplicateUrls(urls);
expect(result).toEqual([]);
});
it("should handle URLs with different cases", () => {
const urls = [
"https://EXAMPLE.com",
"https://example.com"
];
const result = removeDuplicateUrls(urls);
expect(result).toEqual(["https://EXAMPLE.com"]);
});
it("should handle URLs with trailing slashes", () => {
const urls = [
"https://example.com",
"https://example.com/"
];
const result = removeDuplicateUrls(urls);
expect(result).toEqual(["https://example.com"]);
});
});

170
apps/api/src/lib/validateUrl.ts Normal file
View File

@ -0,0 +1,170 @@
export const protocolIncluded = (url: string) => {
// if :// not in the start of the url assume http (maybe https?)
// regex checks if :// appears before any .
return /^([^.:]+:\/\/)/.test(url);
};
const getURLobj = (s: string) => {
// URL fails if we dont include the protocol ie google.com
let error = false;
let urlObj = {};
try {
urlObj = new URL(s);
} catch (err) {
error = true;
}
return { error, urlObj };
};
export const checkAndUpdateURL = (url: string) => {
if (!protocolIncluded(url)) {
url = `http://${url}`;
}
const { error, urlObj } = getURLobj(url);
if (error) {
throw new Error("Invalid URL");
}
const typedUrlObj = urlObj as URL;
if (typedUrlObj.protocol !== "http:" && typedUrlObj.protocol !== "https:") {
throw new Error("Invalid URL");
}
return { urlObj: typedUrlObj, url: url };
};
export const checkUrl = (url: string) => {
const { error, urlObj } = getURLobj(url);
if (error) {
throw new Error("Invalid URL");
}
const typedUrlObj = urlObj as URL;
if (typedUrlObj.protocol !== "http:" && typedUrlObj.protocol !== "https:") {
throw new Error("Invalid URL");
}
if ((url.split(".")[0].match(/:/g) || []).length !== 1) {
throw new Error("Invalid URL. Invalid protocol."); // for this one: http://http://example.com
}
return url;
};
/**
* Same domain check
* It checks if the domain of the url is the same as the base url
* It accounts true for subdomains and www.subdomains
* @param url
* @param baseUrl
* @returns
*/
export function isSameDomain(url: string, baseUrl: string) {
const { urlObj: urlObj1, error: error1 } = getURLobj(url);
const { urlObj: urlObj2, error: error2 } = getURLobj(baseUrl);
if (error1 || error2) {
return false;
}
const typedUrlObj1 = urlObj1 as URL;
const typedUrlObj2 = urlObj2 as URL;
const cleanHostname = (hostname: string) => {
return hostname.startsWith('www.') ? hostname.slice(4) : hostname;
};
const domain1 = cleanHostname(typedUrlObj1.hostname).split('.').slice(-2).join('.');
const domain2 = cleanHostname(typedUrlObj2.hostname).split('.').slice(-2).join('.');
return domain1 === domain2;
}
export function isSameSubdomain(url: string, baseUrl: string) {
const { urlObj: urlObj1, error: error1 } = getURLobj(url);
const { urlObj: urlObj2, error: error2 } = getURLobj(baseUrl);
if (error1 || error2) {
return false;
}
const typedUrlObj1 = urlObj1 as URL;
const typedUrlObj2 = urlObj2 as URL;
const cleanHostname = (hostname: string) => {
return hostname.startsWith('www.') ? hostname.slice(4) : hostname;
};
const domain1 = cleanHostname(typedUrlObj1.hostname).split('.').slice(-2).join('.');
const domain2 = cleanHostname(typedUrlObj2.hostname).split('.').slice(-2).join('.');
const subdomain1 = cleanHostname(typedUrlObj1.hostname).split('.').slice(0, -2).join('.');
const subdomain2 = cleanHostname(typedUrlObj2.hostname).split('.').slice(0, -2).join('.');
// Check if the domains are the same and the subdomains are the same
return domain1 === domain2 && subdomain1 === subdomain2;
}
export const checkAndUpdateURLForMap = (url: string) => {
if (!protocolIncluded(url)) {
url = `http://${url}`;
}
// remove last slash if present
if (url.endsWith("/")) {
url = url.slice(0, -1);
}
const { error, urlObj } = getURLobj(url);
if (error) {
throw new Error("Invalid URL");
}
const typedUrlObj = urlObj as URL;
if (typedUrlObj.protocol !== "http:" && typedUrlObj.protocol !== "https:") {
throw new Error("Invalid URL");
}
// remove any query params
url = url.split("?")[0].trim();
return { urlObj: typedUrlObj, url: url };
};
export function removeDuplicateUrls(urls: string[]): string[] {
const urlMap = new Map<string, string>();
for (const url of urls) {
const parsedUrl = new URL(url);
const protocol = parsedUrl.protocol;
const hostname = parsedUrl.hostname.replace(/^www\./, '');
const path = parsedUrl.pathname + parsedUrl.search + parsedUrl.hash;
const key = `${hostname}${path}`;
if (!urlMap.has(key)) {
urlMap.set(key, url);
} else {
const existingUrl = new URL(urlMap.get(key)!);
const existingProtocol = existingUrl.protocol;
if (protocol === 'https:' && existingProtocol === 'http:') {
urlMap.set(key, url);
} else if (protocol === existingProtocol && !parsedUrl.hostname.startsWith('www.') && existingUrl.hostname.startsWith('www.')) {
urlMap.set(key, url);
}
}
}
return [...new Set(Array.from(urlMap.values()))];
}

12
apps/api/src/lib/withAuth.ts
View File

@ -1,4 +1,8 @@
import { AuthResponse } from "../../src/types";
import { Logger } from "./logger";
import * as Sentry from "@sentry/node";
import { configDotenv } from "dotenv";
configDotenv();
let warningCount = 0;
@ -6,9 +10,10 @@ export function withAuth<T extends AuthResponse, U extends any[]>(
originalFunction: (...args: U) => Promise<T>
) {
return async function (...args: U): Promise<T> {
if (process.env.USE_DB_AUTHENTICATION === "false") {
const useDbAuthentication = process.env.USE_DB_AUTHENTICATION === 'true';
if (!useDbAuthentication) {
if (warningCount < 5) {
console.warn("WARNING - You're bypassing authentication");
Logger.warn("You're bypassing authentication");
warningCount++;
}
return { success: true } as T;
@ -16,7 +21,8 @@ export function withAuth<T extends AuthResponse, U extends any[]>(
try {
return await originalFunction(...args);
} catch (error) {
console.error("Error in withAuth function: ", error);
Sentry.captureException(error);
Logger.error(`Error in withAuth function: ${error}`);
return { success: false, error: error.message } as T;
}
}

125
apps/api/src/main/runWebScraper.ts
View File

@ -1,81 +1,102 @@
import { Job } from "bull";
import { CrawlResult, WebScraperOptions } from "../types";
import { Job } from "bullmq";
import {
CrawlResult,
WebScraperOptions,
RunWebScraperParams,
RunWebScraperResult,
} from "../types";
import { WebScraperDataProvider } from "../scraper/WebScraper";
import { DocumentUrl, Progress } from "../lib/entities";
import { billTeam } from "../services/billing/credit_billing";
import { Document } from "../lib/entities";
import { supabase_service } from "../services/supabase";
import { Logger } from "../lib/logger";
import { ScrapeEvents } from "../lib/scrape-events";
import { configDotenv } from "dotenv";
configDotenv();
export async function startWebScraperPipeline({
job,
token,
}: {
job: Job<WebScraperOptions>;
token: string;
}) {
let partialDocs: Document[] = [];
return (await runWebScraper({
url: job.data.url,
mode: job.data.mode,
crawlerOptions: job.data.crawlerOptions,
pageOptions: job.data.pageOptions,
extractorOptions: job.data.extractorOptions,
pageOptions: {
...job.data.pageOptions,
...(job.data.crawl_id ? ({
includeRawHtml: true,
}): {}),
},
inProgress: (progress) => {
Logger.debug(`🐂 Job in progress ${job.id}`);
if (progress.currentDocument) {
partialDocs.push(progress.currentDocument);
if (partialDocs.length > 50) {
partialDocs = partialDocs.slice(-50);
}
job.progress({ ...progress, partialDocs: partialDocs });
// job.updateProgress({ ...progress, partialDocs: partialDocs });
}
},
onSuccess: (result) => {
job.moveToCompleted(result);
onSuccess: (result, mode) => {
Logger.debug(`🐂 Job completed ${job.id}`);
saveJob(job, result, token, mode);
},
onError: (error) => {
job.moveToFailed(error);
Logger.error(`🐂 Job failed ${job.id}`);
ScrapeEvents.logJobEvent(job, "failed");
job.moveToFailed(error, token, false);
},
team_id: job.data.team_id,
bull_job_id: job.id.toString(),
priority: job.opts.priority,
is_scrape: job.data.is_scrape ?? false,
})) as { success: boolean; message: string; docs: Document[] };
}
export async function runWebScraper({
url,
mode,
crawlerOptions,
pageOptions,
extractorOptions,
inProgress,
onSuccess,
onError,
team_id,
bull_job_id,
}: {
url: string;
mode: "crawl" | "single_urls" | "sitemap";
crawlerOptions: any;
pageOptions?: any;
inProgress: (progress: any) => void;
onSuccess: (result: any) => void;
onError: (error: any) => void;
team_id: string;
bull_job_id: string;
}): Promise<{
success: boolean;
message: string;
docs: Document[] | DocumentUrl[];
}> {
priority,
is_scrape=false,
}: RunWebScraperParams): Promise<RunWebScraperResult> {
try {
const provider = new WebScraperDataProvider();
if (mode === "crawl") {
await provider.setOptions({
jobId: bull_job_id,
mode: mode,
urls: [url],
extractorOptions,
crawlerOptions: crawlerOptions,
pageOptions: pageOptions,
bullJobId: bull_job_id,
priority,
});
} else {
await provider.setOptions({
jobId: bull_job_id,
mode: mode,
urls: url.split(","),
extractorOptions,
crawlerOptions: crawlerOptions,
pageOptions: pageOptions,
priority,
teamId: team_id
});
}
const docs = (await provider.getDocuments(false, (progress: Progress) => {
@ -91,33 +112,67 @@ export async function runWebScraper({
}
// remove docs with empty content
const filteredDocs = crawlerOptions.returnOnlyUrls
const filteredDocs = crawlerOptions?.returnOnlyUrls
? docs.map((doc) => {
if (doc.metadata.sourceURL) {
return { url: doc.metadata.sourceURL };
}
})
: docs.filter((doc) => doc.content.trim().length > 0);
: docs;
const billingResult = await billTeam(team_id, filteredDocs.length);
if (!billingResult.success) {
// throw new Error("Failed to bill team, no subscription was found");
return {
success: false,
message: "Failed to bill team, no subscription was found",
docs: [],
};
if(is_scrape === false) {
let creditsToBeBilled = 1; // Assuming 1 credit per document
if (extractorOptions && (extractorOptions.mode === "llm-extraction" || extractorOptions.mode === "extract")) {
creditsToBeBilled = 5;
}
billTeam(team_id, undefined, creditsToBeBilled * filteredDocs.length).catch(error => {
Logger.error(`Failed to bill team ${team_id} for ${creditsToBeBilled * filteredDocs.length} credits: ${error}`);
// Optionally, you could notify an admin or add to a retry queue here
});
}
// This is where the returnvalue from the job is set
onSuccess(filteredDocs);
onSuccess(filteredDocs, mode);
// this return doesn't matter too much for the job completion result
return { success: true, message: "", docs: filteredDocs };
} catch (error) {
console.error("Error running web scraper", error);
onError(error);
return { success: false, message: error.message, docs: [] };
}
}
const saveJob = async (job: Job, result: any, token: string, mode: string) => {
try {
const useDbAuthentication = process.env.USE_DB_AUTHENTICATION === 'true';
if (useDbAuthentication) {
const { data, error } = await supabase_service
.from("firecrawl_jobs")
.update({ docs: result })
.eq("job_id", job.id);
if (error) throw new Error(error.message);
// try {
// if (mode === "crawl") {
// await job.moveToCompleted(null, token, false);
// } else {
// await job.moveToCompleted(result, token, false);
// }
// } catch (error) {
// // I think the job won't exist here anymore
// }
// } else {
// try {
// await job.moveToCompleted(result, token, false);
// } catch (error) {
// // I think the job won't exist here anymore
// }
}
ScrapeEvents.logJobEvent(job, "completed");
} catch (error) {
Logger.error(`🐂 Failed to update job status: ${error}`);
}
};

42
apps/api/src/routes/admin.ts Normal file
View File

@ -0,0 +1,42 @@
import express from "express";
import { redisHealthController } from "../controllers/v0/admin/redis-health";
import {
autoscalerController,
checkQueuesController,
cleanBefore24hCompleteJobsController,
queuesController,
} from "../controllers/v0/admin/queue";
import { acucCacheClearController } from "../controllers/v0/admin/acuc-cache-clear";
import { wrap } from "./v1";
export const adminRouter = express.Router();
adminRouter.get(
`/admin/${process.env.BULL_AUTH_KEY}/redis-health`,
redisHealthController
);
adminRouter.get(
`/admin/${process.env.BULL_AUTH_KEY}/clean-before-24h-complete-jobs`,
cleanBefore24hCompleteJobsController
);
adminRouter.get(
`/admin/${process.env.BULL_AUTH_KEY}/check-queues`,
checkQueuesController
);
adminRouter.get(
`/admin/${process.env.BULL_AUTH_KEY}/queues`,
queuesController
);
adminRouter.get(
`/admin/${process.env.BULL_AUTH_KEY}/autoscaler`,
autoscalerController
);
adminRouter.post(
`/admin/${process.env.BULL_AUTH_KEY}/acuc-cache-clear`,
wrap(acucCacheClearController),
);

21
apps/api/src/routes/v0.ts
View File

@ -1,12 +1,14 @@
import express from "express";
import { crawlController } from "../../src/controllers/crawl";
import { crawlStatusController } from "../../src/controllers/crawl-status";
import { scrapeController } from "../../src/controllers/scrape";
import { crawlPreviewController } from "../../src/controllers/crawlPreview";
import { crawlJobStatusPreviewController } from "../../src/controllers/status";
import { searchController } from "../../src/controllers/search";
import { crawlCancelController } from "../../src/controllers/crawl-cancel";
import { keyAuthController } from "../../src/controllers/keyAuth";
import { crawlController } from "../../src/controllers/v0/crawl";
import { crawlStatusController } from "../../src/controllers/v0/crawl-status";
import { scrapeController } from "../../src/controllers/v0/scrape";
import { crawlPreviewController } from "../../src/controllers/v0/crawlPreview";
import { crawlJobStatusPreviewController } from "../../src/controllers/v0/status";
import { searchController } from "../../src/controllers/v0/search";
import { crawlCancelController } from "../../src/controllers/v0/crawl-cancel";
import { keyAuthController } from "../../src/controllers/v0/keyAuth";
import { livenessController } from "../controllers/v0/liveness";
import { readinessController } from "../controllers/v0/readiness";
export const v0Router = express.Router();
@ -23,3 +25,6 @@ v0Router.get("/v0/keyAuth", keyAuthController);
// Search routes
v0Router.post("/v0/search", searchController);
// Health/Probe routes
v0Router.get("/v0/health/liveness", livenessController);
v0Router.get("/v0/health/readiness", readinessController);

Some files were not shown because too many files have changed in this diff Show More