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 remote-tracking branch 'origin/main' into f/rust-sdk

Browse Source
This commit is contained in:
rafaelsideguide 2024-08-14 17:30:43 -03:00
commit 697501cc8a
160 changed files with 11226 additions and 1308 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

28
.github/dependabot.yml vendored
View File

@ -5,11 +5,8 @@ updates:
directory: "/apps/playwright-service"
schedule:
interval: "weekly"
groups:
prod-deps:
dependency-type: "production"
dev-deps:
dependency-type: "development"
open-pull-requests-limit: 0 # Disable version updates
security-updates: "all"
commit-message:
prefix: "apps/playwright-service"
include: "scope"
@ -19,11 +16,8 @@ updates:
directory: "/apps/python-sdk"
schedule:
interval: "weekly"
groups:
prod-deps:
dependency-type: "production"
dev-deps:
dependency-type: "development"
open-pull-requests-limit: 0 # Disable version updates
security-updates: "all"
commit-message:
prefix: "apps/python-sdk"
include: "scope"
@ -33,11 +27,8 @@ updates:
directory: "/apps/api"
schedule:
interval: "weekly"
groups:
prod-deps:
dependency-type: "production"
dev-deps:
dependency-type: "development"
open-pull-requests-limit: 0 # Disable version updates
security-updates: "all"
commit-message:
prefix: "apps/api"
include: "scope"
@ -47,11 +38,8 @@ updates:
directory: "/apps/test-suite"
schedule:
interval: "weekly"
groups:
prod-deps:
dependency-type: "production"
dev-deps:
dependency-type: "development"
open-pull-requests-limit: 0 # Disable version updates
security-updates: "all"
commit-message:
prefix: "apps/test-suite"
include: "scope"

20
.github/workflows/check-queues.yml vendored Normal file
View File

@ -0,0 +1,20 @@
name: Check Queues
on:
schedule:
- cron: '*/5 * * * *'
env:
BULL_AUTH_KEY: ${{ secrets.BULL_AUTH_KEY }}
jobs:
clean-jobs:
runs-on: ubuntu-latest
steps:
- name: Send GET request to check queues
run: |
response=$(curl --write-out '%{http_code}' --silent --output /dev/null --max-time 180 https://api.firecrawl.dev/admin/${{ secrets.BULL_AUTH_KEY }}/check-queues)
if [ "$response" -ne 200 ]; then
echo "Failed to check queues. Response: $response"
exit 1
fi
echo "Successfully checked queues. Response: $response"

6
.github/workflows/fly-direct.yml vendored
View File

@ -29,9 +29,9 @@ jobs:
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
- run: flyctl deploy --remote-only -a firecrawl-scraper-js
working-directory: ./apps/api
env:
FLY_API_TOKEN: ${{ secrets.FLY_API_TOKEN }}
BULL_AUTH_KEY: ${{ secrets.BULL_AUTH_KEY }}

42
.github/workflows/fly.yml vendored
View File

@ -169,6 +169,41 @@ jobs:
run: npm run test
working-directory: ./apps/js-sdk/firecrawl
go-sdk-tests:
name: Go 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 Go
uses: actions/setup-go@v5
with:
go-version-file: "go.mod"
- 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 Go SDK
run: go mod tidy
working-directory: ./apps/go-sdk
- name: Run tests for Go SDK
run: go test -v ./... -timeout 180s
working-directory: ./apps/go-sdk/firecrawl
rust-sdk-tests:
name: Rust SDK Tests
needs: pre-deploy-e2e-tests
@ -210,12 +245,12 @@ jobs:
needs: [pre-deploy-test-suite, python-sdk-tests, js-sdk-tests, rust-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
- run: flyctl deploy --remote-only -a firecrawl-scraper-js
working-directory: ./apps/api
env:
FLY_API_TOKEN: ${{ secrets.FLY_API_TOKEN }}
BULL_AUTH_KEY: ${{ secrets.BULL_AUTH_KEY }}
build-and-publish-python-sdk:
name: Build and publish Python SDK
@ -297,7 +332,6 @@ jobs:
run: |
npm run build-and-publish
working-directory: ./apps/js-sdk/firecrawl
build-and-publish-rust-sdk:
name: Build and publish Rust SDK
runs-on: ubuntu-latest

1
.gitignore vendored
View File

@ -18,3 +18,4 @@ apps/test-suite/load-test-results/test-run-report.json
apps/playwright-service-ts/node_modules/
apps/playwright-service-ts/package-lock.json

6
.gitmodules vendored Normal file
View File

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

1
CONTRIBUTING.md
View File

@ -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

19
LICENSE
View File

@ -659,3 +659,22 @@ specific requirements.
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.

51
README.md
View File

@ -20,8 +20,14 @@ We provide an easy to use API with our hosted version. You can find the playgrou
- [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] [Langchain JS Integration 🦜🔗](https://js.langchain.com/docs/integrations/document_loaders/web_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)
- [x] [Dify Integration](https://dify.ai/blog/dify-ai-blog-integrated-with-firecrawl)
- [x] [Langflow Integration](https://docs.langflow.org/)
- [x] [Crew.ai Integration](https://docs.crewai.com/)
- [x] [Flowise AI Integration](https://docs.flowiseai.com/integrations/langchain/document-loaders/firecrawl)
- [x] [PraisonAI Integration](https://docs.praison.ai/firecrawl/)
- [x] [Zapier Integration](https://zapier.com/apps/firecrawl/integrations)
- [ ] 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).
@ -212,7 +218,6 @@ curl -X POST https://api.firecrawl.dev/v0/scrape \
}
}
}
```
## Using Python SDK
@ -302,34 +307,29 @@ To scrape a single URL with error handling, use the `scrapeUrl` method. It takes
```js
try {
const url = 'https://example.com';
const url = "https://example.com";
const scrapedData = await app.scrapeUrl(url);
console.log(scrapedData);
} catch (error) {
console.error(
'Error occurred while scraping:',
error.message
);
console.error("Error occurred while scraping:", error.message);
}
```
### 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 crawlUrl = "https://example.com";
const params = {
crawlerOptions: {
excludes: ['blog/'],
excludes: ["blog/"],
includes: [], // leave empty for all pages
limit: 1000,
},
pageOptions: {
onlyMainContent: true
}
onlyMainContent: true,
},
};
const waitUntilDone = true;
const timeout = 5;
@ -339,10 +339,8 @@ const crawlResult = await app.crawlUrl(
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.
@ -352,8 +350,6 @@ 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:
@ -393,17 +389,28 @@ console.log(scrapeResult.data["llm_extraction"]);
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.
```js
const query = 'what is mendable?';
const query = "what is mendable?";
const searchResults = await app.search(query, {
pageOptions: {
fetchPageContent: true // Fetch the page content for each search result
}
fetchPageContent: true, // Fetch the page content for each search result
},
});
```
## Contributing
We love contributions! Please read our [contributing guide](CONTRIBUTING.md) before submitting a pull request.
*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._
## 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.

164
SELF_HOST.md
View File

@ -1,36 +1,77 @@
## Self-hosting Firecrawl
# 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._
#### Contributor?
Refer to [CONTRIBUTING.md](https://github.com/mendableai/firecrawl/blob/main/CONTRIBUTING.md) for instructions on how to run it locally.
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.
## Getting Started
If you're contributing, note that the process is similar to other open-source repos, i.e., fork Firecrawl, make changes, run tests, PR.
First, clone this repository and copy the example env file from the API folder `.env.example` to `.env`.
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)!
### Steps
## Why?
1. Clone the repository:
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:
```bash
git clone https://github.com/mendableai/firecrawl.git
cd firecrawl
cp ./apps/api/.env.example ./.env
- **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 wont set up authentication, or any optional sub services (pdf parsing, JS blocking support, AI features)
`.env:`
```
2. For running the simplest version of FireCrawl, edit the `USE_DB_AUTHENTICATION` in `.env` to not use the database authentication:
```plaintext
USE_DB_AUTHENTICATION=false
```
3. Update the Redis URL in the .env file to align with the Docker configuration:
```plaintext
# ===== 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= #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
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
```
4. #### Option: Running with TypeScript Playwright Service
3. *(Optional) Running with TypeScript Playwright Service*
* Update the `docker-compose.yml` file to change the Playwright service:
@ -49,16 +90,91 @@ First, clone this repository and copy the example env file from the API folder `
```
* Don't forget to set the proxy server in your `.env` file as needed.
5. Build and run the Docker containers:
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`.
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/v0/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.

50
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.
@ -16,18 +17,29 @@ 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.)
# 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=@
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'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 have a serper key you'd like to use as a search api
SERPER_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 +54,8 @@ 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 +69,14 @@ 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

1
apps/api/.env.local
View File

@ -5,6 +5,7 @@ SUPABASE_ANON_TOKEN=
SUPABASE_URL=
SUPABASE_SERVICE_TOKEN=
REDIS_URL=
REDIS_RATE_LIMIT_URL=
SCRAPING_BEE_API_KEY=
OPENAI_API_KEY=
ANTHROPIC_API_KEY=

2
apps/api/.gitignore vendored
View File

@ -4,3 +4,5 @@
*.csv
dump.rdb
/mongo-data
/.next/

3
apps/api/Dockerfile
View File

@ -31,6 +31,3 @@ COPY --from=build /app /app
# 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" ]

6
apps/api/fly.staging.toml
View File

@ -6,13 +6,13 @@
app = 'staging-firecrawl-scraper-js'
primary_region = 'mia'
kill_signal = 'SIGINT'
kill_timeout = '5s'
kill_timeout = '30s'
[build]
[processes]
app = 'npm run start:production'
worker = 'npm run worker:production'
app = 'node dist/src/index.js'
worker = 'node dist/src/services/queue-worker.js'
[http_service]
internal_port = 8080

12
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 = 75
[[http_service.checks]]
grace_period = "20s"

378
apps/api/openapi.json
View File

@ -41,33 +41,20 @@
"pageOptions": {
"type": "object",
"properties": {
"onlyMainContent": {
"type": "boolean",
"description": "Only return the main content of the page excluding headers, navs, footers, etc.",
"default": false
"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 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
},
"screenshot": {
"includeRawHtml": {
"type": "boolean",
"description": "Include a screenshot of the top of the page that you are scraping.",
"description": "Include the raw HTML content of the page. Will output a rawHtml key in the response.",
"default": false
},
"waitFor": {
"type": "integer",
"description": "Wait x amount of milliseconds for the page to load to fetch content",
"default": 0
},
"removeTags": {
"type": "array",
"items": {
"type": "string"
},
"description": "Tags, classes and ids to remove from the page. Use comma separated values. Example: 'script, .ad, #footer'"
},
"onlyIncludeTags": {
"type": "array",
"items": {
@ -75,34 +62,58 @@
},
"description": "Only include tags, classes and ids from the page in the final output. 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."
"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 LLM-based extraction of structured information from the page content",
"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": ["llm-extraction", "llm-extraction-from-raw-html"],
"description": "The extraction mode to use. llm-extraction: Extracts information from the cleaned and parsed content. llm-extraction-from-raw-html: Extracts information directly from the raw HTML."
"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"
"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",
"description": "The schema for the data to be extracted, required only for LLM extraction modes.",
"required": [
"company_mission",
"supports_sso",
@ -134,13 +145,52 @@
}
},
"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."
}
}
}
}
}
}
}
}
@ -216,7 +266,12 @@
},
"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
}
}
@ -224,25 +279,32 @@
"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": {
@ -254,6 +316,21 @@
"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
}
}
}
@ -275,13 +352,52 @@
}
},
"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."
}
}
}
}
}
}
}
}
@ -323,7 +439,12 @@
},
"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
}
}
@ -355,13 +476,52 @@
}
},
"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."
}
}
}
}
}
}
}
}
@ -403,14 +563,6 @@
"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"
@ -427,7 +579,7 @@
"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."
}
}
}
@ -435,13 +587,52 @@
}
},
"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."
}
}
}
}
}
}
}
}
@ -485,13 +676,52 @@
}
},
"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."
}
}
}
}
}
}
}
}
@ -523,7 +753,12 @@
"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 `includeHtml` is true"
},
"rawHtml": {
"type": "string",
"nullable": true,
"description": "Raw HTML content of the page if `includeRawHtml` is true"
},
"metadata": {
"type": "object",
@ -583,7 +818,12 @@
"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 `includeHtml` is true"
},
"rawHtml": {
"type": "string",
"nullable": true,
"description": "Raw HTML content of the page if `includeRawHtml` is true"
},
"index": {
"type": "integer",

7
apps/api/package.json
View File

@ -19,12 +19,14 @@
"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",
"deploy:fly": "flyctl deploy",
"deploy:fly:staging": "fly deploy -c fly.staging.toml"
},
"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",
@ -62,6 +64,7 @@
"axios": "^1.3.4",
"bottleneck": "^2.19.5",
"bull": "^4.15.0",
"cacheable-lookup": "^6.1.0",
"cheerio": "^1.0.0-rc.12",
"cohere": "^1.1.1",
"cors": "^2.8.5",
@ -72,7 +75,7 @@
"form-data": "^4.0.0",
"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": "^2.3.0",
"keyword-extractor": "^0.0.28",
@ -91,7 +94,7 @@
"promptable": "^0.0.10",
"puppeteer": "^22.12.1",
"rate-limiter-flexible": "2.4.2",
"redis": "^4.6.7",
"redlock": "5.0.0-beta.2",
"resend": "^3.4.0",
"robots-parser": "^3.0.1",
"scrapingbee": "^1.7.4",

41
apps/api/pnpm-lock.yaml
View File

@ -59,6 +59,9 @@ importers:
bull:
specifier: ^4.15.0
version: 4.15.0
cacheable-lookup:
specifier: ^6.1.0
version: 6.1.0
cheerio:
specifier: ^1.0.0-rc.12
version: 1.0.0-rc.12
@ -90,7 +93,7 @@ importers:
specifier: ^1.1.5
version: 1.1.5
ioredis:
specifier: ^5.3.2
specifier: ^5.4.1
version: 5.4.1
joplin-turndown-plugin-gfm:
specifier: ^1.0.12
@ -146,9 +149,9 @@ importers:
rate-limiter-flexible:
specifier: 2.4.2
version: 2.4.2
redis:
specifier: ^4.6.7
version: 4.6.14
redlock:
specifier: 5.0.0-beta.2
version: 5.0.0-beta.2
resend:
specifier: ^3.4.0
version: 3.4.0
@ -192,6 +195,9 @@ importers:
'@flydotio/dockerfile':
specifier: ^0.4.10
version: 0.4.11
'@jest/globals':
specifier: ^29.7.0
version: 29.7.0
'@tsconfig/recommended':
specifier: ^1.0.3
version: 1.0.6
@ -1940,6 +1946,10 @@ packages:
resolution: {integrity: sha512-/Nf7TyzTx6S3yRJObOAV7956r8cr2+Oj8AC5dt8wSP3BQAoeX58NoHyCU8P8zGkNXStjTSi6fzO6F0pBdcYbEg==}
engines: {node: '>= 0.8'}
cacheable-lookup@6.1.0:
resolution: {integrity: sha512-KJ/Dmo1lDDhmW2XDPMo+9oiy/CeqosPguPCrgcVzKyZrL6pM1gU2GmPY/xo6OQPTUaA/c0kwHuywB4E6nmT9ww==}
engines: {node: '>=10.6.0'}
call-bind@1.0.7:
resolution: {integrity: sha512-GHTSNSYICQ7scH7sZ+M2rFopRoLh8t2bLSW6BbgrtLsahOIB5iyAVJf9GjWK3cYTDaMj4XdBpM1cA6pIS0Kv2w==}
engines: {node: '>= 0.4'}
@ -3526,6 +3536,9 @@ packages:
resolution: {integrity: sha512-dBpDMdxv9Irdq66304OLfEmQ9tbNRFnFTuZiLo+bD+r332bBmMJ8GBLXklIXXgxd3+v9+KUnZaUR5PJMa75Gsg==}
engines: {node: '>= 0.4.0'}
node-abort-controller@3.1.1:
resolution: {integrity: sha512-AGK2yQKIjRuqnc6VkX2Xj5d+QW8xZ87pa1UK6yA6ouUyuxfHuMP6umE5QK7UmTeOAymo+Zx1Fxiuw9rVx8taHQ==}
node-domexception@1.0.0:
resolution: {integrity: sha512-/jKZoMpw0F8GRwl4/eLROPA3cfcXtLApP0QzLmUT/HuPCZWyB7IY9ZrMeKw2O/nFIqPQB3PVM9aYm0F312AXDQ==}
engines: {node: '>=10.5.0'}
@ -3949,6 +3962,10 @@ packages:
redis@4.6.14:
resolution: {integrity: sha512-GrNg/e33HtsQwNXL7kJT+iNFPSwE1IPmd7wzV3j4f2z0EYxZfZE7FVTmUysgAtqQQtg5NXF5SNLR9OdO/UHOfw==}
redlock@5.0.0-beta.2:
resolution: {integrity: sha512-2RDWXg5jgRptDrB1w9O/JgSZC0j7y4SlaXnor93H/UJm/QyDiFgBKNtrh0TI6oCXqYSaSoXxFh6Sd3VtYfhRXw==}
engines: {node: '>=12'}
regenerator-runtime@0.14.1:
resolution: {integrity: sha512-dYnhHh0nJoMfnkZs6GmmhFknAGRrLznOu5nc9ML+EJxGvrx6H7teuevqVqCuPcPK//3eDrrjQhehXVx9cnkGdw==}
@ -4372,8 +4389,8 @@ packages:
engines: {node: '>=14.17'}
hasBin: true
typescript@5.5.3:
resolution: {integrity: sha512-/hreyEujaB0w76zKo6717l3L0o/qEUtRgdvUBvlkhoWeOVMjMuHNHk0BRBzikzuGDqNmPQbg5ifMEqsHLiIUcQ==}
typescript@5.5.4:
resolution: {integrity: sha512-Mtq29sKDAEYP7aljRgtPOpTvOfbwRWlS6dPRzwjdE+C0R4brX/GUyhHSecbHMFLNBLcJIPt9nl9yG5TZ1weH+Q==}
engines: {node: '>=14.17'}
hasBin: true
@ -6920,6 +6937,8 @@ snapshots:
bytes@3.1.2: {}
cacheable-lookup@6.1.0: {}
call-bind@1.0.7:
dependencies:
es-define-property: 1.0.0
@ -8596,6 +8615,8 @@ snapshots:
netmask@2.0.2: {}
node-abort-controller@3.1.1: {}
node-domexception@1.0.0: {}
node-ensure@0.0.0: {}
@ -8930,7 +8951,7 @@ snapshots:
csv-parse: 5.5.6
gpt3-tokenizer: 1.1.5
openai: 3.3.0
typescript: 5.5.3
typescript: 5.5.4
uuid: 9.0.1
zod: 3.23.8
transitivePeerDependencies:
@ -9099,6 +9120,10 @@ snapshots:
'@redis/search': 1.1.6(@redis/client@1.5.16)
'@redis/time-series': 1.0.5(@redis/client@1.5.16)
redlock@5.0.0-beta.2:
dependencies:
node-abort-controller: 3.1.1
regenerator-runtime@0.14.1: {}
require-directory@2.1.1: {}
@ -9522,7 +9547,7 @@ snapshots:
typescript@5.4.5: {}
typescript@5.5.3: {}
typescript@5.5.4: {}
typesense@1.8.2(@babel/runtime@7.24.6):
dependencies:

1
apps/api/src/__tests__/e2e_full_withAuth/index.test.ts
View File

@ -858,7 +858,6 @@ describe("E2E Tests for API Routes", () => {
await new Promise((resolve) => setTimeout(resolve, 1000)); // Wait for 1 second before checking again
}
}
console.log(crawlData)
expect(crawlData.length).toBeGreaterThan(0);
expect(crawlData).toEqual(expect.arrayContaining([
expect.objectContaining({ url: expect.stringContaining("https://firecrawl.dev/?ref=mendable+banner") }),

87
apps/api/src/__tests__/e2e_withAuth/index.test.ts
View File

@ -311,7 +311,10 @@ describe("E2E Tests for API Routes", () => {
}
}
const completedResponse = response;
await new Promise((resolve) => setTimeout(resolve, 1000)); // wait for data to be saved on the database
const completedResponse = await request(TEST_URL)
.get(`/v0/crawl/status/${crawlResponse.body.jobId}`)
.set("Authorization", `Bearer ${process.env.TEST_API_KEY}`);
const urls = completedResponse.body.data.map(
(item: any) => item.metadata?.sourceURL
@ -331,7 +334,7 @@ describe("E2E Tests for API Routes", () => {
expect(completedResponse.body.data[0].content).toContain("Mendable");
expect(completedResponse.body.data[0].metadata.pageStatusCode).toBe(200);
expect(completedResponse.body.data[0].metadata.pageError).toBeUndefined();
}, 60000); // 60 seconds
}, 180000); // 180 seconds
it.concurrent("should return a successful response with a valid API key and valid excludes option", async () => {
const crawlResponse: FirecrawlCrawlResponse = await request(TEST_URL)
@ -363,7 +366,10 @@ describe("E2E Tests for API Routes", () => {
}
}
const completedResponse: FirecrawlCrawlStatusResponse = response;
await new Promise((resolve) => setTimeout(resolve, 1000)); // wait for data to be saved on the database
const completedResponse: FirecrawlCrawlStatusResponse = await request(TEST_URL)
.get(`/v0/crawl/status/${crawlResponse.body.jobId}`)
.set("Authorization", `Bearer ${process.env.TEST_API_KEY}`);
const urls = completedResponse.body.data.map(
(item: any) => item.metadata?.sourceURL
@ -481,7 +487,7 @@ describe("E2E Tests for API Routes", () => {
expect(response.body).toHaveProperty("success");
expect(response.body.success).toBe(true);
expect(response.body).toHaveProperty("data");
}, 30000); // 30 seconds timeout
}, 60000); // 60 seconds timeout
});
describe("GET /v0/crawl/status/:jobId", () => {
@ -513,7 +519,6 @@ describe("E2E Tests for API Routes", () => {
expect(crawlResponse.statusCode).toBe(200);
let isCompleted = false;
let completedResponse;
while (!isCompleted) {
const response = await request(TEST_URL)
@ -524,11 +529,16 @@ describe("E2E Tests for API Routes", () => {
if (response.body.status === "completed") {
isCompleted = true;
completedResponse = response;
} else {
await new Promise((r) => setTimeout(r, 1000)); // Wait for 1 second before checking again
}
}
await new Promise((resolve) => setTimeout(resolve, 1000)); // wait for data to be saved on the database
const completedResponse = await request(TEST_URL)
.get(`/v0/crawl/status/${crawlResponse.body.jobId}`)
.set("Authorization", `Bearer ${process.env.TEST_API_KEY}`);
expect(completedResponse.body).toHaveProperty("status");
expect(completedResponse.body.status).toBe("completed");
expect(completedResponse.body).toHaveProperty("data");
@ -619,7 +629,13 @@ describe("E2E Tests for API Routes", () => {
expect(completedResponse.body).toHaveProperty("status");
expect(completedResponse.body.status).toBe("failed");
expect(completedResponse.body).toHaveProperty("data");
expect(completedResponse.body.data).toBeNull();
let isNullOrEmptyArray = false;
if (completedResponse.body.data === null || completedResponse.body.data.length === 0) {
isNullOrEmptyArray = true;
}
expect(isNullOrEmptyArray).toBe(true);
expect(completedResponse.body.data).toEqual(expect.arrayContaining([]));
expect(completedResponse.body).toHaveProperty("partial_data");
expect(completedResponse.body.partial_data[0]).toHaveProperty("content");
expect(completedResponse.body.partial_data[0]).toHaveProperty("markdown");
@ -679,61 +695,4 @@ describe("E2E Tests for API Routes", () => {
expect(typeof llmExtraction.is_open_source).toBe("boolean");
}, 60000); // 60 secs
});
describe("POST /v0/crawl with fast mode", () => {
it.concurrent("should complete the crawl under 20 seconds", async () => {
const startTime = Date.now();
const crawlResponse = await request(TEST_URL)
.post("/v0/crawl")
.set("Authorization", `Bearer ${process.env.TEST_API_KEY}`)
.set("Content-Type", "application/json")
.send({
url: "https://flutterbricks.com",
crawlerOptions: {
mode: "fast"
}
});
expect(crawlResponse.statusCode).toBe(200);
const jobId = crawlResponse.body.jobId;
let statusResponse;
let isFinished = false;
while (!isFinished) {
statusResponse = await request(TEST_URL)
.get(`/v0/crawl/status/${jobId}`)
.set("Authorization", `Bearer ${process.env.TEST_API_KEY}`);
expect(statusResponse.statusCode).toBe(200);
isFinished = statusResponse.body.status === "completed";
if (!isFinished) {
await new Promise((resolve) => setTimeout(resolve, 1000)); // Wait for 1 second before checking again
}
}
// const endTime = Date.now();
// const timeElapsed = (endTime - startTime) / 1000; // Convert to seconds
// console.log(`Time elapsed: ${timeElapsed} seconds`);
expect(statusResponse.body.status).toBe("completed");
expect(statusResponse.body).toHaveProperty("data");
expect(statusResponse.body.data[0]).toHaveProperty("content");
expect(statusResponse.body.data[0]).toHaveProperty("markdown");
expect(statusResponse.body.data[0]).toHaveProperty("metadata");
expect(statusResponse.body.data[0].metadata.pageStatusCode).toBe(200);
expect(statusResponse.body.data[0].metadata.pageError).toBeUndefined();
const results = statusResponse.body.data;
// results.forEach((result, i) => {
// console.log(result.metadata.sourceURL);
// });
expect(results.length).toBeGreaterThanOrEqual(10);
expect(results.length).toBeLessThanOrEqual(15);
}, 20000);
});
});

87
apps/api/src/controllers/admin/queue.ts Normal file
View File

@ -0,0 +1,87 @@
import { Request, Response } from "express";
import { Job } from "bull";
import { Logger } from "../../lib/logger";
import { getWebScraperQueue } from "../../services/queue-service";
import { checkAlerts } from "../../services/alerts";
export async function cleanBefore24hCompleteJobsController(
req: Request,
res: Response
) {
Logger.info("🐂 Cleaning jobs older than 24h");
try {
const webScraperQueue = getWebScraperQueue();
const batchSize = 10;
const numberOfBatches = 9; // Adjust based on your needs
const completedJobsPromises: Promise<Job[]>[] = [];
for (let i = 0; i < numberOfBatches; i++) {
completedJobsPromises.push(
webScraperQueue.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 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) {
Logger.error(error);
return res.status(500).json({ error: error.message });
}
}

85
apps/api/src/controllers/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 });
}
}

231
apps/api/src/controllers/auth.ts
View File

@ -1,25 +1,77 @@
import { parseApi } from "../../src/lib/parseApi";
import { getRateLimiter, } from "../../src/services/rate-limiter";
import { AuthResponse, NotificationType, RateLimiterMode } from "../../src/types";
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 { 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 "../../src/services/redlock";
import { getValue } from "../../src/services/redis";
import { setValue } from "../../src/services/redis";
import { validate } from "uuid";
export async function authenticateUser(req, res, mode?: RateLimiterMode): Promise<AuthResponse> {
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> {
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);
Logger.error(`Error setting trace attributes: ${error.message}`);
}
}
async function getKeyAndPriceId(normalizedApi: string): Promise<{
success: boolean;
teamId?: string;
priceId?: string;
error?: string;
status?: number;
}> {
const { data, error } = await supabase_service.rpc("get_key_and_price_id_2", {
api_key: normalizedApi,
});
if (error) {
Logger.error(`RPC ERROR (get_key_and_price_id_2): ${error.message}`);
return {
success: false,
error:
"The server seems overloaded. Please contact hello@firecrawl.com if you aren't sending too many requests at once.",
status: 500,
};
}
if (!data || data.length === 0) {
Logger.warn(`Error fetching api key: ${error.message} or data is empty`);
// TODO: change this error code ?
return {
success: false,
error: "Unauthorized: Invalid token",
status: 401,
};
} else {
return {
success: true,
teamId: data[0].team_id,
priceId: data[0].price_id,
};
}
}
export async function supaAuthenticateUser(
req,
@ -50,20 +102,83 @@ export async function supaAuthenticateUser(
const iptoken = incomingIP + token;
let rateLimiter: RateLimiterRedis;
let subscriptionData: { team_id: string, plan: string } | null = null;
let subscriptionData: { team_id: string; plan: string } | null = null;
let normalizedApi: string;
let team_id: string;
let cacheKey = "";
let redLockKey = "";
const lockTTL = 15000; // 10 seconds
let teamId: string | null = null;
let priceId: string | null = null;
if (token == "this_is_just_a_preview_token") {
rateLimiter = getRateLimiter(RateLimiterMode.Preview, token);
team_id = "preview";
teamId = "preview";
} else {
normalizedApi = parseApi(token);
if (!normalizedApiIsUuid(normalizedApi)) {
return {
success: false,
error: "Unauthorized: Invalid token",
status: 401,
};
}
const { data, error } = await supabase_service.rpc(
'get_key_and_price_id_2', { api_key: normalizedApi }
cacheKey = `api_key:${normalizedApi}`;
try {
const teamIdPriceId = await getValue(cacheKey);
if (teamIdPriceId) {
const { team_id, price_id } = JSON.parse(teamIdPriceId);
teamId = team_id;
priceId = price_id;
} else {
const {
success,
teamId: tId,
priceId: pId,
error,
status,
} = await getKeyAndPriceId(normalizedApi);
if (!success) {
return { success, error, status };
}
teamId = tId;
priceId = pId;
await setValue(
cacheKey,
JSON.stringify({ team_id: teamId, price_id: priceId }),
10
);
}
} catch (error) {
Logger.error(`Error with auth function: ${error.message}`);
// const {
// success,
// teamId: tId,
// priceId: pId,
// error: e,
// status,
// } = await getKeyAndPriceId(normalizedApi);
// if (!success) {
// return { success, error: e, status };
// }
// teamId = tId;
// priceId = pId;
// const {
// success,
// teamId: tId,
// priceId: pId,
// error: e,
// status,
// } = await getKeyAndPriceId(normalizedApi);
// if (!success) {
// return { success, error: e, status };
// }
// teamId = tId;
// priceId = pId;
}
// 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 $$
@ -81,38 +196,34 @@ export async function supaAuthenticateUser(
// end;
// $$ 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) {
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);
const plan = getPlanByPriceId(priceId);
// HyperDX Logging
setTrace(team_id, normalizedApi);
setTrace(teamId, normalizedApi);
subscriptionData = {
team_id: team_id,
plan: plan
}
team_id: teamId,
plan: 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
);
break;
case RateLimiterMode.Search:
rateLimiter = getRateLimiter(RateLimiterMode.Search, token, subscriptionData.plan);
rateLimiter = getRateLimiter(
RateLimiterMode.Search,
token,
subscriptionData.plan
);
break;
case RateLimiterMode.CrawlStatus:
rateLimiter = getRateLimiter(RateLimiterMode.CrawlStatus, token);
@ -130,12 +241,13 @@ 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);
@ -143,7 +255,17 @@ 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());
// Cache longer for 429s
if (teamId && priceId && mode !== RateLimiterMode.Preview) {
await setValue(
cacheKey,
JSON.stringify({ team_id: teamId, price_id: priceId }),
60 // 10 seconds, cache for everything
);
}
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}`,
@ -153,7 +275,9 @@ export async function supaAuthenticateUser(
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.Search)
) {
return { success: true, team_id: "preview" };
// check the origin of the request and make sure its from firecrawl.dev
@ -178,6 +302,7 @@ export async function supaAuthenticateUser(
.eq("key", normalizedApi);
if (error || !data || data.length === 0) {
Logger.warn(`Error fetching api key: ${error.message} or data is empty`);
return {
success: false,
error: "Unauthorized: Invalid token",
@ -188,24 +313,30 @@ export async function supaAuthenticateUser(
subscriptionData = data[0];
}
return { success: true, team_id: subscriptionData.team_id, plan: subscriptionData.plan ?? ""};
return {
success: true,
team_id: subscriptionData.team_id,
plan: subscriptionData.plan ?? "",
};
}
function getPlanByPriceId(price_id: string) {
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 'standardnew';
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:
return "growth";
default:
return 'free';
return "free";
}
}

17
apps/api/src/controllers/crawl-cancel.ts
View File

@ -5,9 +5,12 @@ 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";
import { Logger } from "../../src/lib/logger";
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,
@ -22,6 +25,7 @@ export async function crawlCancelController(req: Request, res: Response) {
}
// check if the job belongs to the team
if (useDbAuthentication) {
const { data, error: supaError } = await supabase_service
.from("bulljobs_teams")
.select("*")
@ -34,29 +38,34 @@ export async function crawlCancelController(req: Request, res: Response) {
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...");
Logger.info("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 getWebScraperQueue().client.del(job.lockKey());
await job.takeLock();
await job.discard();
await job.moveToFailed(Error("Job cancelled by user"), true);
} catch (error) {
console.error(error);
Logger.error(error);
}
const newJobState = await job.getState();
res.json({
status: newJobState === "failed" ? "cancelled" : "Cancelling...",
status: "cancelled"
});
} catch (error) {
console.error(error);
Logger.error(error);
return res.status(500).json({ error: error.message });
}
}

30
apps/api/src/controllers/crawl-status.ts
View File

@ -3,6 +3,8 @@ import { authenticateUser } from "./auth";
import { RateLimiterMode } from "../../src/types";
import { addWebScraperJob } from "../../src/services/queue-jobs";
import { getWebScraperQueue } from "../../src/services/queue-service";
import { supabaseGetJobById } from "../../src/lib/supabase-jobs";
import { Logger } from "../../src/lib/logger";
export async function crawlStatusController(req: Request, res: Response) {
try {
@ -20,18 +22,30 @@ export async function crawlStatusController(req: Request, res: Response) {
}
const { current, current_url, total, current_step, partialDocs } = await job.progress();
let data = job.returnvalue;
if (process.env.USE_DB_AUTHENTICATION === "true") {
const supabaseData = await supabaseGetJobById(req.params.jobId);
if (supabaseData) {
data = supabaseData.docs;
}
}
const jobStatus = await job.getState();
res.json({
status: await job.getState(),
status: jobStatus,
// progress: job.progress(),
current: current,
current_url: current_url,
current_step: current_step,
total: total,
data: job.returnvalue,
partial_data: partialDocs ?? [],
current,
current_url,
current_step,
total,
data: data ? data : null,
partial_data: jobStatus == 'completed' ? [] : partialDocs,
});
} catch (error) {
console.error(error);
Logger.error(error);
return res.status(500).json({ error: error.message });
}
}

11
apps/api/src/controllers/crawl.ts
View File

@ -10,6 +10,8 @@ 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";
export async function crawlController(req: Request, res: Response) {
try {
@ -30,7 +32,7 @@ export async function crawlController(req: Request, res: Response) {
try {
createIdempotencyKey(req);
} catch (error) {
console.error(error);
Logger.error(error);
return res.status(500).json({ error: error.message });
}
}
@ -60,10 +62,11 @@ export async function crawlController(req: Request, res: Response) {
const crawlerOptions = { ...defaultCrawlerOptions, ...req.body.crawlerOptions };
const pageOptions = { ...defaultCrawlPageOptions, ...req.body.pageOptions };
if (mode === "single_urls" && !url.includes(",")) {
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 },
@ -83,7 +86,7 @@ export async function crawlController(req: Request, res: Response) {
documents: docs,
});
} catch (error) {
console.error(error);
Logger.error(error);
return res.status(500).json({ error: error.message });
}
}
@ -101,7 +104,7 @@ export async function crawlController(req: Request, res: Response) {
res.json({ jobId: job.id });
} catch (error) {
console.error(error);
Logger.error(error);
return res.status(500).json({ error: error.message });
}
}

3
apps/api/src/controllers/crawlPreview.ts
View File

@ -3,6 +3,7 @@ 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 { Logger } from "../../src/lib/logger";
export async function crawlPreviewController(req: Request, res: Response) {
try {
@ -39,7 +40,7 @@ export async function crawlPreviewController(req: Request, res: Response) {
res.json({ jobId: job.id });
} catch (error) {
console.error(error);
Logger.error(error);
return res.status(500).json({ error: error.message });
}
}

6
apps/api/src/controllers/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/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" });
}

89
apps/api/src/controllers/scrape.ts
View File

@ -9,8 +9,11 @@ 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 { v4 as uuidv4 } from "uuid";
import { Logger } from '../lib/logger';
export async function scrapeHelper(
jobId: string,
req: Request,
team_id: string,
crawlerOptions: any,
@ -35,6 +38,7 @@ export async function scrapeHelper(
const a = new WebScraperDataProvider();
await a.setOptions({
jobId,
mode: "single_urls",
urls: [url],
crawlerOptions: {
@ -73,28 +77,6 @@ export async function scrapeHelper(
});
}
let creditsToBeBilled = filteredDocs.length;
const creditsPerLLMExtract = 50;
if (extractorOptions.mode === "llm-extraction" || extractorOptions.mode === "llm-extraction-from-raw-html" || extractorOptions.mode === "llm-extraction-from-markdown") {
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],
@ -104,6 +86,7 @@ export async function scrapeHelper(
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 } = await authenticateUser(
req,
@ -113,27 +96,40 @@ export async function scrapeController(req: Request, res: Response) {
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 };
if (extractorOptions.mode === "llm-extraction") {
pageOptions.onlyMainContent = true;
}
const origin = req.body.origin ?? defaultOrigin;
const timeout = req.body.timeout ?? defaultTimeout;
let timeout = req.body.timeout ?? defaultTimeout;
if (extractorOptions.mode.includes("llm-extraction")) {
pageOptions.onlyMainContent = true;
timeout = req.body.timeout ?? 90000;
}
const checkCredits = async () => {
try {
const { success: creditsCheckSuccess, message: creditsCheckMessage } =
await checkTeamCredits(team_id, 1);
const { success: creditsCheckSuccess, message: creditsCheckMessage } = await checkTeamCredits(team_id, 1);
if (!creditsCheckSuccess) {
earlyReturn = true;
return res.status(402).json({ error: "Insufficient credits" });
}
} catch (error) {
console.error(error);
return res.status(500).json({ error: "Internal server error" });
Logger.error(error);
earlyReturn = true;
return res.status(500).json({ error: "Error checking team credits. Please contact hello@firecrawl.com for help." });
}
};
await checkCredits();
const jobId = uuidv4();
const startTime = new Date().getTime();
const result = await scrapeHelper(
jobId,
req,
team_id,
crawlerOptions,
@ -146,7 +142,35 @@ export async function scrapeController(req: Request, res: Response) {
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; // Assuming 1 credit per document
const creditsPerLLMExtract = 50;
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;
}
const billingResult = await billTeam(
team_id,
creditsToBeBilled
);
if (!billingResult.success) {
return res.status(402).json({
success: false,
error: "Failed to bill team. Insufficient credits or subscription not found.",
});
}
}
logJob({
job_id: jobId,
success: result.success,
message: result.error,
num_docs: 1,
@ -161,9 +185,12 @@ export async function scrapeController(req: Request, res: Response) {
extractor_options: extractorOptions,
num_tokens: numTokens,
});
return res.status(result.returnCode).json(result);
} catch (error) {
console.error(error);
Logger.error(error);
return res.status(500).json({ error: error.message });
}
}

17
apps/api/src/controllers/search.ts
View File

@ -7,8 +7,11 @@ 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";
export async function searchHelper(
jobId: string,
req: Request,
team_id: string,
crawlerOptions: any,
@ -75,8 +78,9 @@ export async function searchHelper(
const a = new WebScraperDataProvider();
await a.setOptions({
jobId,
mode: "single_urls",
urls: res.map((r) => r.url).slice(0, searchOptions.limit ?? 7),
urls: res.map((r) => r.url).slice(0, Math.min(searchOptions.limit ?? 5, 5)),
crawlerOptions: {
...crawlerOptions,
},
@ -146,7 +150,10 @@ export async function searchController(req: Request, res: Response) {
};
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 } =
@ -155,11 +162,12 @@ export async function searchController(req: Request, res: Response) {
return res.status(402).json({ error: "Insufficient credits" });
}
} catch (error) {
console.error(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,
crawlerOptions,
@ -169,6 +177,7 @@ export async function searchController(req: Request, res: Response) {
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,
@ -183,7 +192,7 @@ export async function searchController(req: Request, res: Response) {
});
return res.status(result.returnCode).json(result);
} catch (error) {
console.error(error);
Logger.error(error);
return res.status(500).json({ error: error.message });
}
}

32
apps/api/src/controllers/status.ts
View File

@ -1,5 +1,7 @@
import { Request, Response } from "express";
import { getWebScraperQueue } from "../../src/services/queue-service";
import { supabaseGetJobById } from "../../src/lib/supabase-jobs";
import { Logger } from "../../src/lib/logger";
export async function crawlJobStatusPreviewController(req: Request, res: Response) {
try {
@ -9,18 +11,32 @@ export async function crawlJobStatusPreviewController(req: Request, res: Respons
}
const { current, current_url, total, current_step, partialDocs } = await job.progress();
let data = job.returnvalue;
if (process.env.USE_DB_AUTHENTICATION === "true") {
const supabaseData = await supabaseGetJobById(req.params.jobId);
if (supabaseData) {
data = supabaseData.docs;
}
}
let jobStatus = await job.getState();
if (jobStatus === 'waiting' || jobStatus === 'stuck') {
jobStatus = 'active';
}
res.json({
status: await job.getState(),
status: jobStatus,
// progress: job.progress(),
current: current,
current_url: current_url,
current_step: current_step,
total: total,
data: job.returnvalue,
partial_data: partialDocs ?? [],
current,
current_url,
current_step,
total,
data: data ? data : null,
partial_data: jobStatus == 'completed' ? [] : partialDocs,
});
} catch (error) {
console.error(error);
Logger.error(error);
return res.status(500).json({ error: error.message });
}
}

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: {},

121
apps/api/src/index.ts
View File

@ -3,22 +3,34 @@ 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 { v0Router } from "./routes/v0";
import { initSDK } from "@hyperdx/node-opentelemetry";
import cluster from "cluster";
import os from "os";
import { Job } from "bull";
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';
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`);
const cacheable = new CacheableLookup({
// this is important to avoid querying local hostnames see https://github.com/szmarczak/cacheable-lookup readme
lookup:false
});
cacheable.install(http.globalAgent);
cacheable.install(https.globalAgent)
if (cluster.isMaster) {
console.log(`Master ${process.pid} is running`);
Logger.info(`Master ${process.pid} is running`);
// Fork workers.
for (let i = 0; i < numCPUs; i++) {
@ -26,9 +38,11 @@ if (cluster.isMaster) {
}
cluster.on("exit", (worker, code, signal) => {
console.log(`Worker ${worker.process.pid} exited`);
console.log("Starting a new worker");
if (code !== null) {
Logger.info(`Worker ${worker.process.pid} exited`);
Logger.info("Starting a new worker");
cluster.fork();
}
});
} else {
const app = express();
@ -64,10 +78,10 @@ if (cluster.isMaster) {
// register router
app.use(v0Router);
app.use(adminRouter);
const DEFAULT_PORT = process.env.PORT ?? 3002;
const HOST = process.env.HOST ?? "localhost";
redisClient.connect();
// HyperDX OpenTelemetry
if (process.env.ENV === "production") {
@ -76,14 +90,9 @@ if (cluster.isMaster) {
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;
@ -93,26 +102,6 @@ if (cluster.isMaster) {
startServer();
}
// Use this as a "health check" that way we dont destroy the server
app.get(`/admin/${process.env.BULL_AUTH_KEY}/queues`, async (req, res) => {
try {
const webScraperQueue = getWebScraperQueue();
const [webScraperActive] = await Promise.all([
webScraperQueue.getActiveCount(),
]);
const noActiveJobs = webScraperActive === 0;
// 200 if no active jobs, 503 if there are active jobs
return res.status(noActiveJobs ? 200 : 500).json({
webScraperActive,
noActiveJobs,
});
} catch (error) {
console.error(error);
return res.status(500).json({ error: error.message });
}
});
app.get(`/serverHealthCheck`, async (req, res) => {
try {
const webScraperQueue = getWebScraperQueue();
@ -126,7 +115,7 @@ if (cluster.isMaster) {
waitingJobs,
});
} catch (error) {
console.error(error);
Logger.error(error);
return res.status(500).json({ error: error.message });
}
});
@ -171,13 +160,13 @@ if (cluster.isMaster) {
});
if (!response.ok) {
console.error("Failed to send Slack notification");
Logger.error("Failed to send Slack notification");
}
}
}, timeout);
}
} catch (error) {
console.error(error);
Logger.debug(error);
}
};
@ -185,52 +174,20 @@ if (cluster.isMaster) {
}
});
app.get(
`/admin/${process.env.BULL_AUTH_KEY}/clean-before-24h-complete-jobs`,
async (req, res) => {
try {
const webScraperQueue = getWebScraperQueue();
const batchSize = 10;
const numberOfBatches = 9; // Adjust based on your needs
const completedJobsPromises: Promise<Job[]>[] = [];
for (let i = 0; i < numberOfBatches; i++) {
completedJobsPromises.push(webScraperQueue.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) {
console.error(`Failed to remove job with ID ${job.id}:`, jobError);
}
}
return res.status(200).send(`Removed ${count} completed jobs.`);
} catch (error) {
console.error("Failed to clean last 24h complete jobs:", error);
return res.status(500).send("Failed to clean jobs");
}
}
);
app.get("/is-production", (req, res) => {
res.send({ isProduction: global.isProduction });
});
console.log(`Worker ${process.pid} started`);
Logger.info(`Worker ${process.pid} started`);
}
const wsq = getWebScraperQueue();
wsq.on("waiting", j => ScrapeEvents.logJobEvent(j, "waiting"));
wsq.on("active", j => ScrapeEvents.logJobEvent(j, "active"));
wsq.on("completed", j => ScrapeEvents.logJobEvent(j, "completed"));
wsq.on("paused", j => ScrapeEvents.logJobEvent(j, "paused"));
wsq.on("resumed", j => ScrapeEvents.logJobEvent(j, "resumed"));
wsq.on("removed", j => ScrapeEvents.logJobEvent(j, "removed"));

3
apps/api/src/lib/LLM-extraction/index.ts
View File

@ -4,6 +4,7 @@ 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(
@ -44,7 +45,7 @@ export async function generateCompletions(
return completionResult;
} catch (error) {
console.error(`Error generating completions: ${error}`);
Logger.error(`Error generating completions: ${error}`);
throw new Error(`Error generating completions: ${error.message}`);
}
default:

2
apps/api/src/lib/LLM-extraction/models.ts
View File

@ -48,7 +48,7 @@ function prepareOpenAIDoc(
export async function generateOpenAICompletions({
client,
model = "gpt-4o",
model = process.env.MODEL_NAME || "gpt-4o",
document,
schema, //TODO - add zod dynamic type checking
prompt = defaultPrompt,

3
apps/api/src/lib/default-values.ts
View File

@ -1,12 +1,13 @@
export const defaultOrigin = "api";
export const defaultTimeout = 30000; // 30 seconds
export const defaultTimeout = 45000; // 45 seconds
export const defaultPageOptions = {
onlyMainContent: false,
includeHtml: false,
waitFor: 0,
screenshot: false,
fullPageScreenshot: false,
parsePDF: true
};

17
apps/api/src/lib/entities.ts
View File

@ -18,6 +18,7 @@ export type PageOptions = {
fetchPageContent?: boolean;
waitFor?: number;
screenshot?: boolean;
fullPageScreenshot?: boolean;
headers?: Record<string, string>;
replaceAllPathsWithAbsolutePaths?: boolean;
parsePDF?: boolean;
@ -42,8 +43,8 @@ export type SearchOptions = {
export type CrawlerOptions = {
returnOnlyUrls?: boolean;
includes?: string[];
excludes?: string[];
includes?: string | string[];
excludes?: string | string[];
maxCrawledLinks?: number;
maxDepth?: number;
limit?: number;
@ -56,6 +57,7 @@ export type CrawlerOptions = {
}
export type WebScraperOptions = {
jobId: string;
urls: string[];
mode: "single_urls" | "sitemap" | "crawl";
crawlerOptions?: CrawlerOptions;
@ -89,6 +91,7 @@ export class Document {
warning?: string;
index?: number;
linksOnPage?: string[]; // Add this new field as a separate property
constructor(data: Partial<Document>) {
if (!data.content) {
@ -102,6 +105,7 @@ 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
}
}
@ -129,3 +133,12 @@ export interface FireEngineResponse {
pageError?: string;
}
export interface FireEngineOptions{
mobileProxy?: boolean;
method?: string;
engine?: string;
blockMedia?: boolean;
blockAds?: boolean;
disableJsDom?: boolean;
}

53
apps/api/src/lib/logger.ts Normal file
View File

@ -0,0 +1,53 @@
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.INFO;
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}`);
// if (process.env.USE_DB_AUTH) {
// 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);
}
}

84
apps/api/src/lib/scrape-events.ts Normal file
View File

@ -0,0 +1,84 @@
import { Job, JobId } from "bull";
import type { baseScrapers } from "../scraper/WebScraper/single_url";
import { supabase_service as supabase } from "../services/supabase";
import { Logger } from "./logger";
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;
if (process.env.USE_DB_AUTHENTICATION) {
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 | JobId, 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}`);
}
}
}

19
apps/api/src/lib/supabase-jobs.ts Normal file
View File

@ -0,0 +1,19 @@
import { supabase_service } from "../services/supabase";
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;
}

5
apps/api/src/lib/withAuth.ts
View File

@ -1,4 +1,5 @@
import { AuthResponse } from "../../src/types";
import { Logger } from "./logger";
let warningCount = 0;
@ -8,7 +9,7 @@ export function withAuth<T extends AuthResponse, U extends any[]>(
return async function (...args: U): Promise<T> {
if (process.env.USE_DB_AUTHENTICATION === "false") {
if (warningCount < 5) {
console.warn("WARNING - You're bypassing authentication");
Logger.warn("You're bypassing authentication");
warningCount++;
}
return { success: true } as T;
@ -16,7 +17,7 @@ export function withAuth<T extends AuthResponse, U extends any[]>(
try {
return await originalFunction(...args);
} catch (error) {
console.error("Error in withAuth function: ", error);
Logger.error(`Error in withAuth function: ${error}`);
return { success: false, error: error.message } as T;
}
}

46
apps/api/src/main/runWebScraper.ts
View File

@ -1,9 +1,17 @@
import { Job } from "bull";
import { CrawlResult, WebScraperOptions, RunWebScraperParams, RunWebScraperResult } from "../types";
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";
export async function startWebScraperPipeline({
job,
@ -17,6 +25,7 @@ export async function startWebScraperPipeline({
crawlerOptions: job.data.crawlerOptions,
pageOptions: job.data.pageOptions,
inProgress: (progress) => {
Logger.debug(`🐂 Job in progress ${job.id}`);
if (progress.currentDocument) {
partialDocs.push(progress.currentDocument);
if (partialDocs.length > 50) {
@ -26,9 +35,12 @@ export async function startWebScraperPipeline({
}
},
onSuccess: (result) => {
job.moveToCompleted(result);
Logger.debug(`🐂 Job completed ${job.id}`);
saveJob(job, result);
},
onError: (error) => {
Logger.error(`🐂 Job failed ${job.id}`);
ScrapeEvents.logJobEvent(job, "failed");
job.moveToFailed(error);
},
team_id: job.data.team_id,
@ -50,6 +62,7 @@ export async function runWebScraper({
const provider = new WebScraperDataProvider();
if (mode === "crawl") {
await provider.setOptions({
jobId: bull_job_id,
mode: mode,
urls: [url],
crawlerOptions: crawlerOptions,
@ -58,6 +71,7 @@ export async function runWebScraper({
});
} else {
await provider.setOptions({
jobId: bull_job_id,
mode: mode,
urls: url.split(","),
crawlerOptions: crawlerOptions,
@ -102,8 +116,34 @@ export async function runWebScraper({
// 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) => {
try {
if (process.env.USE_DB_AUTHENTICATION === "true") {
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 {
await job.moveToCompleted(null, false, false);
} catch (error) {
// I think the job won't exist here anymore
}
} else {
try {
await job.moveToCompleted(result, false, 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}`);
}
};

29
apps/api/src/routes/admin.ts Normal file
View File

@ -0,0 +1,29 @@
import express from "express";
import { redisHealthController } from "../controllers/admin/redis-health";
import {
checkQueuesController,
cleanBefore24hCompleteJobsController,
queuesController,
} from "../controllers/admin/queue";
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
);

5
apps/api/src/routes/v0.ts
View File

@ -7,6 +7,8 @@ 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 { livenessController } from "../controllers/liveness";
import { readinessController } from "../controllers/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);

6
apps/api/src/scraper/WebScraper/__tests__/crawler.test.ts
View File

@ -42,6 +42,7 @@ describe('WebCrawler', () => {
crawler = new WebCrawler({
jobId: "TEST",
initialUrl: initialUrl,
includes: [],
excludes: [],
@ -76,6 +77,7 @@ describe('WebCrawler', () => {
crawler = new WebCrawler({
jobId: "TEST",
initialUrl: initialUrl,
includes: [],
excludes: [],
@ -104,6 +106,7 @@ describe('WebCrawler', () => {
crawler = new WebCrawler({
jobId: "TEST",
initialUrl: initialUrl,
includes: [],
excludes: [],
@ -133,6 +136,7 @@ describe('WebCrawler', () => {
crawler = new WebCrawler({
jobId: "TEST",
initialUrl: initialUrl,
includes: [],
excludes: [],
@ -161,6 +165,7 @@ describe('WebCrawler', () => {
// Setup the crawler with the specific test case options
const crawler = new WebCrawler({
jobId: "TEST",
initialUrl: initialUrl,
includes: [],
excludes: [],
@ -194,6 +199,7 @@ describe('WebCrawler', () => {
const limit = 2; // Set a limit for the number of links
crawler = new WebCrawler({
jobId: "TEST",
initialUrl: initialUrl,
includes: [],
excludes: [],

15
apps/api/src/scraper/WebScraper/__tests__/dns.test.ts Normal file
View File

@ -0,0 +1,15 @@
import CacheableLookup from 'cacheable-lookup';
import https from 'node:https';
import axios from "axios";
describe("DNS", () => {
it("cached dns", async () => {
const cachedDns = new CacheableLookup();
cachedDns.install(https.globalAgent);
jest.spyOn(cachedDns, "lookupAsync");
const res = await axios.get("https://example.com");
expect(res.status).toBe(200);
expect(cachedDns.lookupAsync).toHaveBeenCalled();
});
});

23
apps/api/src/scraper/WebScraper/__tests__/single_url.test.ts
View File

@ -1,3 +1,7 @@
import { scrapSingleUrl } from '../single_url';
import { PageOptions } from '../../../lib/entities';
jest.mock('../single_url', () => {
const originalModule = jest.requireActual('../single_url');
originalModule.fetchHtmlContent = jest.fn().mockResolvedValue('<html><head><title>Test</title></head><body><h1>Roast</h1></body></html>');
@ -5,20 +9,29 @@ jest.mock('../single_url', () => {
return originalModule;
});
import { scrapSingleUrl } from '../single_url';
import { PageOptions } from '../../../lib/entities';
describe('scrapSingleUrl', () => {
it('should handle includeHtml option correctly', async () => {
const url = 'https://roastmywebsite.ai';
const pageOptionsWithHtml: PageOptions = { includeHtml: true };
const pageOptionsWithoutHtml: PageOptions = { includeHtml: false };
const resultWithHtml = await scrapSingleUrl(url, pageOptionsWithHtml);
const resultWithoutHtml = await scrapSingleUrl(url, pageOptionsWithoutHtml);
const resultWithHtml = await scrapSingleUrl("TEST", url, pageOptionsWithHtml);
const resultWithoutHtml = await scrapSingleUrl("TEST", url, pageOptionsWithoutHtml);
expect(resultWithHtml.html).toBeDefined();
expect(resultWithoutHtml.html).toBeUndefined();
}, 10000);
});
it('should return a list of links on the firecrawl.ai page', async () => {
const url = 'https://example.com';
const pageOptions: PageOptions = { includeHtml: true };
const result = await scrapSingleUrl("TEST", url, pageOptions);
// Check if the result contains a list of links
expect(result.linksOnPage).toBeDefined();
expect(Array.isArray(result.linksOnPage)).toBe(true);
expect(result.linksOnPage.length).toBeGreaterThan(0);
expect(result.linksOnPage).toContain('https://www.iana.org/domains/example')
}, 10000);

44
apps/api/src/scraper/WebScraper/crawler.ts
View File

@ -8,8 +8,10 @@ import { scrapSingleUrl } from "./single_url";
import robotsParser from "robots-parser";
import { getURLDepth } from "./utils/maxDepthUtils";
import { axiosTimeout } from "../../../src/lib/timeout";
import { Logger } from "../../../src/lib/logger";
export class WebCrawler {
private jobId: string;
private initialUrl: string;
private baseUrl: string;
private includes: string[];
@ -26,6 +28,7 @@ export class WebCrawler {
private allowExternalContentLinks: boolean;
constructor({
jobId,
initialUrl,
includes,
excludes,
@ -36,6 +39,7 @@ export class WebCrawler {
allowBackwardCrawling = false,
allowExternalContentLinks = false
}: {
jobId: string;
initialUrl: string;
includes?: string[];
excludes?: string[];
@ -46,6 +50,7 @@ export class WebCrawler {
allowBackwardCrawling?: boolean;
allowExternalContentLinks?: boolean;
}) {
this.jobId = jobId;
this.initialUrl = initialUrl;
this.baseUrl = new URL(initialUrl).origin;
this.includes = includes ?? [];
@ -64,7 +69,7 @@ export class WebCrawler {
private filterLinks(sitemapLinks: string[], limit: number, maxDepth: number): string[] {
return sitemapLinks
.filter((link) => {
const url = new URL(link);
const url = new URL(link.trim(), this.baseUrl);
const path = url.pathname;
const depth = getURLDepth(url.toString());
@ -116,7 +121,7 @@ export class WebCrawler {
const isAllowed = this.robots.isAllowed(link, "FireCrawlAgent") ?? true;
// Check if the link is disallowed by robots.txt
if (!isAllowed) {
console.log(`Link disallowed by robots.txt: ${link}`);
Logger.debug(`Link disallowed by robots.txt: ${link}`);
return false;
}
@ -133,15 +138,19 @@ export class WebCrawler {
limit: number = 10000,
maxDepth: number = 10
): Promise<{ url: string, html: string }[]> {
Logger.debug(`Crawler starting with ${this.initialUrl}`);
// Fetch and parse robots.txt
try {
const response = await axios.get(this.robotsTxtUrl, { timeout: axiosTimeout });
this.robots = robotsParser(this.robotsTxtUrl, response.data);
Logger.debug(`Crawler robots.txt fetched with ${this.robotsTxtUrl}`);
} catch (error) {
console.log(`Failed to fetch robots.txt from ${this.robotsTxtUrl}`);
Logger.debug(`Failed to fetch robots.txt from ${this.robotsTxtUrl}`);
}
if (!crawlerOptions?.ignoreSitemap){
Logger.debug(`Fetching sitemap links from ${this.initialUrl}`);
const sitemapLinks = await this.tryFetchSitemapLinks(this.initialUrl);
if (sitemapLinks.length > 0) {
let filteredLinks = this.filterLinks(sitemapLinks, limit, maxDepth);
@ -175,6 +184,7 @@ export class WebCrawler {
inProgress?: (progress: Progress) => void,
): Promise<{ url: string, html: string }[]> {
const queue = async.queue(async (task: string, callback) => {
Logger.debug(`Crawling ${task}`);
if (this.crawledUrls.size >= Math.min(this.maxCrawledLinks, this.limit)) {
if (callback && typeof callback === "function") {
callback();
@ -216,16 +226,18 @@ export class WebCrawler {
}
}, concurrencyLimit);
Logger.debug(`🐂 Pushing ${urls.length} URLs to the queue`);
queue.push(
urls.filter(
(url) =>
!this.visited.has(url) && this.robots.isAllowed(url, "FireCrawlAgent")
),
(err) => {
if (err) console.error(err);
if (err) Logger.error(`🐂 Error pushing URLs to the queue: ${err}`);
}
);
await queue.drain();
Logger.debug(`🐂 Crawled ${this.crawledUrls.size} URLs, Queue drained.`);
return Array.from(this.crawledUrls.entries()).map(([url, html]) => ({ url, html }));
}
@ -253,7 +265,7 @@ export class WebCrawler {
// If it is the first link, fetch with single url
if (this.visited.size === 1) {
const page = await scrapSingleUrl(url, { ...pageOptions, includeHtml: true });
const page = await scrapSingleUrl(this.jobId, url, { ...pageOptions, includeHtml: true });
content = page.html ?? "";
pageStatusCode = page.metadata?.pageStatusCode;
pageError = page.metadata?.pageError || undefined;
@ -282,7 +294,6 @@ export class WebCrawler {
const urlObj = new URL(fullUrl);
const path = urlObj.pathname;
if (this.isInternalLink(fullUrl)) { // INTERNAL LINKS
if (this.isInternalLink(fullUrl) &&
this.noSections(fullUrl) &&
@ -383,7 +394,7 @@ export class WebCrawler {
return linkDomain === baseDomain;
}
private isFile(url: string): boolean {
public isFile(url: string): boolean {
const fileExtensions = [
".png",
".jpg",
@ -393,6 +404,7 @@ export class WebCrawler {
".js",
".ico",
".svg",
".tiff",
// ".pdf",
".zip",
".exe",
@ -408,9 +420,10 @@ export class WebCrawler {
".woff",
".ttf",
".woff2",
".webp"
".webp",
".inc"
];
return fileExtensions.some((ext) => url.endsWith(ext));
return fileExtensions.some((ext) => url.toLowerCase().endsWith(ext));
}
private isSocialMediaOrEmail(url: string): boolean {
@ -448,10 +461,14 @@ export class WebCrawler {
try {
const response = await axios.get(sitemapUrl, { timeout: axiosTimeout });
if (response.status === 200) {
sitemapLinks = await getLinksFromSitemap(sitemapUrl);
sitemapLinks = await getLinksFromSitemap({ sitemapUrl });
}
} catch (error) {
console.error(`Failed to fetch sitemap from ${sitemapUrl}: ${error}`);
Logger.debug(`Failed to fetch sitemap with axios from ${sitemapUrl}: ${error}`);
const response = await getLinksFromSitemap({ sitemapUrl, mode: 'fire-engine' });
if (response) {
sitemapLinks = response;
}
}
if (sitemapLinks.length === 0) {
@ -459,10 +476,11 @@ export class WebCrawler {
try {
const response = await axios.get(baseUrlSitemap, { timeout: axiosTimeout });
if (response.status === 200) {
sitemapLinks = await getLinksFromSitemap(baseUrlSitemap);
sitemapLinks = await getLinksFromSitemap({ sitemapUrl: baseUrlSitemap, mode: 'fire-engine' });
}
} catch (error) {
console.error(`Failed to fetch sitemap from ${baseUrlSitemap}: ${error}`);
Logger.debug(`Failed to fetch sitemap from ${baseUrlSitemap}: ${error}`);
sitemapLinks = await getLinksFromSitemap({ sitemapUrl: baseUrlSitemap, mode: 'fire-engine' });
}
}

8
apps/api/src/scraper/WebScraper/custom/handleCustomScraping.ts
View File

@ -1,10 +1,12 @@
import { Logger } from "../../../lib/logger";
export async function handleCustomScraping(
text: string,
url: string
): Promise<{ scraper: string; url: string; waitAfterLoad?: number, pageOptions?: { scrollXPaths?: string[] } } | null> {
// Check for Readme Docs special case
if (text.includes('<meta name="readme-deploy"')) {
console.log(
Logger.debug(
`Special use case detected for ${url}, using Fire Engine with wait time 1000ms`
);
return {
@ -19,7 +21,7 @@ export async function handleCustomScraping(
// Check for Vanta security portals
if (text.includes('<link href="https://static.vanta.com')) {
console.log(
Logger.debug(
`Vanta link detected for ${url}, using Fire Engine with wait time 3000ms`
);
return {
@ -34,7 +36,7 @@ export async function handleCustomScraping(
const googleDriveMetaMatch = text.match(googleDriveMetaPattern);
if (googleDriveMetaMatch) {
const url = googleDriveMetaMatch[1];
console.log(`Google Drive PDF link detected: ${url}`);
Logger.debug(`Google Drive PDF link detected: ${url}`);
const fileIdMatch = url.match(/https:\/\/drive\.google\.com\/file\/d\/([^\/]+)\/view/);
if (fileIdMatch) {

215
apps/api/src/scraper/WebScraper/index.ts
View File

@ -19,13 +19,16 @@ import { generateCompletions } from "../../lib/LLM-extraction";
import { getWebScraperQueue } from "../../../src/services/queue-service";
import { fetchAndProcessDocx } from "./utils/docxProcessor";
import { getAdjustedMaxDepth, getURLDepth } from "./utils/maxDepthUtils";
import { Logger } from "../../lib/logger";
import { ScrapeEvents } from "../../lib/scrape-events";
export class WebScraperDataProvider {
private jobId: string;
private bullJobId: string;
private urls: string[] = [""];
private mode: "single_urls" | "sitemap" | "crawl" = "single_urls";
private includes: string[];
private excludes: string[];
private includes: string | string[];
private excludes: string | string[];
private maxCrawledLinks: number;
private maxCrawledDepth: number = 10;
private returnOnlyUrls: boolean;
@ -65,6 +68,7 @@ export class WebScraperDataProvider {
batchUrls.map(async (url, index) => {
const existingHTML = allHtmls ? allHtmls[i + index] : "";
const result = await scrapSingleUrl(
this.jobId,
url,
this.pageOptions,
this.extractorOptions,
@ -89,14 +93,14 @@ export class WebScraperDataProvider {
const job = await getWebScraperQueue().getJob(this.bullJobId);
const jobStatus = await job.getState();
if (jobStatus === "failed") {
console.error(
Logger.info(
"Job has failed or has been cancelled by the user. Stopping the job..."
);
return [] as Document[];
}
}
} catch (error) {
console.error(error);
Logger.error(error.message);
return [] as Document[];
}
}
@ -164,11 +168,29 @@ export class WebScraperDataProvider {
private async handleCrawlMode(
inProgress?: (progress: Progress) => void
): Promise<Document[]> {
let includes: string[];
if (Array.isArray(this.includes)) {
if (this.includes[0] != "") {
includes = this.includes;
}
} else {
includes = this.includes.split(',');
}
let excludes: string[];
if (Array.isArray(this.excludes)) {
if (this.excludes[0] != "") {
excludes = this.excludes;
}
} else {
excludes = this.excludes.split(',');
}
const crawler = new WebCrawler({
jobId: this.jobId,
initialUrl: this.urls[0],
includes: this.includes,
excludes: this.excludes,
includes,
excludes,
maxCrawledLinks: this.maxCrawledLinks,
maxCrawledDepth: getAdjustedMaxDepth(this.urls[0], this.maxCrawledDepth),
limit: this.limit,
@ -218,14 +240,13 @@ export class WebScraperDataProvider {
private async handleSitemapMode(
inProgress?: (progress: Progress) => void
): Promise<Document[]> {
let links = await getLinksFromSitemap(this.urls[0]);
let links = await getLinksFromSitemap({ sitemapUrl: this.urls[0] });
links = await this.cleanIrrelevantPath(links);
if (this.returnOnlyUrls) {
return this.returnOnlyUrlsResponse(links, inProgress);
}
let documents = await this.processLinks(links, inProgress);
return this.cacheAndFinalizeDocuments(documents, links);
}
@ -253,35 +274,60 @@ export class WebScraperDataProvider {
inProgress?: (progress: Progress) => void,
allHtmls?: string[]
): Promise<Document[]> {
const pdfLinks = links.filter(link => link.endsWith(".pdf"));
const docLinks = links.filter(link => link.endsWith(".doc") || link.endsWith(".docx"));
const pdfDocuments = await this.fetchPdfDocuments(pdfLinks);
const docxDocuments = await this.fetchDocxDocuments(docLinks);
links = links.filter(link => !pdfLinks.includes(link) && !docLinks.includes(link));
let documents = await this.convertUrlsToDocuments(
links,
inProgress,
allHtmls
const pdfLinks = links.filter((link) => link.endsWith(".pdf"));
const docLinks = links.filter(
(link) => link.endsWith(".doc") || link.endsWith(".docx")
);
const [pdfDocuments, docxDocuments] = await Promise.all([
this.fetchPdfDocuments(pdfLinks),
this.fetchDocxDocuments(docLinks),
]);
links = links.filter(
(link) => !pdfLinks.includes(link) && !docLinks.includes(link)
);
let [documents, sitemapData] = await Promise.all([
this.convertUrlsToDocuments(links, inProgress, allHtmls),
this.mode === "single_urls" && links.length > 0
? this.getSitemapDataForSingleUrl(this.urls[0], links[0], 1500).catch(
(error) => {
Logger.debug(`Failed to fetch sitemap data: ${error}`);
return null;
}
)
: Promise.resolve(null),
]);
if (this.mode === "single_urls" && documents.length > 0) {
documents[0].metadata.sitemap = sitemapData ?? undefined;
} else {
documents = await this.getSitemapData(this.urls[0], documents);
}
documents = this.applyPathReplacements(documents);
// documents = await this.applyImgAltText(documents);
if (
(this.extractorOptions.mode === "llm-extraction" || this.extractorOptions.mode === "llm-extraction-from-markdown") &&
(this.extractorOptions.mode === "llm-extraction" ||
this.extractorOptions.mode === "llm-extraction-from-markdown") &&
this.mode === "single_urls"
) {
documents = await generateCompletions(documents, this.extractorOptions, "markdown");
documents = await generateCompletions(
documents,
this.extractorOptions,
"markdown"
);
}
if (
(this.extractorOptions.mode === "llm-extraction-from-raw-html") &&
this.extractorOptions.mode === "llm-extraction-from-raw-html" &&
this.mode === "single_urls"
) {
documents = await generateCompletions(documents, this.extractorOptions, "raw-html");
documents = await generateCompletions(
documents,
this.extractorOptions,
"raw-html"
);
}
return documents.concat(pdfDocuments).concat(docxDocuments);
}
@ -289,7 +335,28 @@ export class WebScraperDataProvider {
private async fetchPdfDocuments(pdfLinks: string[]): Promise<Document[]> {
return Promise.all(
pdfLinks.map(async (pdfLink) => {
const { content, pageStatusCode, pageError } = await fetchAndProcessPdf(pdfLink, this.pageOptions.parsePDF);
const timer = Date.now();
const logInsertPromise = ScrapeEvents.insert(this.jobId, {
type: "scrape",
url: pdfLink,
worker: process.env.FLY_MACHINE_ID,
method: "pdf-scrape",
result: null,
});
const { content, pageStatusCode, pageError } = await fetchAndProcessPdf(
pdfLink,
this.pageOptions.parsePDF
);
const insertedLogId = await logInsertPromise;
ScrapeEvents.updateScrapeResult(insertedLogId, {
response_size: content.length,
success: !(pageStatusCode && pageStatusCode >= 400) && !!content && (content.trim().length >= 100),
error: pageError,
response_code: pageStatusCode,
time_taken: Date.now() - timer,
});
return {
content: content,
metadata: { sourceURL: pdfLink, pageStatusCode, pageError },
@ -300,11 +367,32 @@ export class WebScraperDataProvider {
}
private async fetchDocxDocuments(docxLinks: string[]): Promise<Document[]> {
return Promise.all(
docxLinks.map(async (p) => {
const { content, pageStatusCode, pageError } = await fetchAndProcessDocx(p);
docxLinks.map(async (docxLink) => {
const timer = Date.now();
const logInsertPromise = ScrapeEvents.insert(this.jobId, {
type: "scrape",
url: docxLink,
worker: process.env.FLY_MACHINE_ID,
method: "docx-scrape",
result: null,
});
const { content, pageStatusCode, pageError } = await fetchAndProcessDocx(
docxLink
);
const insertedLogId = await logInsertPromise;
ScrapeEvents.updateScrapeResult(insertedLogId, {
response_size: content.length,
success: !(pageStatusCode && pageStatusCode >= 400) && !!content && (content.trim().length >= 100),
error: pageError,
response_code: pageStatusCode,
time_taken: Date.now() - timer,
});
return {
content,
metadata: { sourceURL: p, pageStatusCode, pageError },
metadata: { sourceURL: docxLink, pageStatusCode, pageError },
provider: "web-scraper",
};
})
@ -328,7 +416,7 @@ export class WebScraperDataProvider {
documents: Document[],
links: string[]
): Promise<Document[]> {
await this.setCachedDocuments(documents, links);
// await this.setCachedDocuments(documents, links);
documents = this.removeChildLinks(documents);
return documents.splice(0, this.limit);
}
@ -375,6 +463,10 @@ export class WebScraperDataProvider {
const url = new URL(document.metadata.sourceURL);
const path = url.pathname;
if (!Array.isArray(this.excludes)) {
this.excludes = this.excludes.split(',');
}
if (this.excludes.length > 0 && this.excludes[0] !== "") {
// Check if the link should be excluded
if (
@ -386,6 +478,10 @@ export class WebScraperDataProvider {
}
}
if (!Array.isArray(this.includes)) {
this.includes = this.includes.split(',');
}
if (this.includes.length > 0 && this.includes[0] !== "") {
// Check if the link matches the include patterns, if any are specified
if (this.includes.length > 0) {
@ -424,7 +520,7 @@ export class WebScraperDataProvider {
...document,
childrenLinks: childrenLinks || [],
}),
60 * 60 * 24 * 10
60 * 60
); // 10 days
}
}
@ -433,7 +529,7 @@ export class WebScraperDataProvider {
let documents: Document[] = [];
for (const url of urls) {
const normalizedUrl = this.normalizeUrl(url);
console.log(
Logger.debug(
"Getting cached document for web-scraper-cache:" + normalizedUrl
);
const cachedDocumentString = await getValue(
@ -472,6 +568,7 @@ export class WebScraperDataProvider {
throw new Error("Urls are required");
}
this.jobId = options.jobId;
this.bullJobId = options.bullJobId;
this.urls = options.urls;
this.mode = options.mode;
@ -489,16 +586,28 @@ export class WebScraperDataProvider {
includeHtml: false,
replaceAllPathsWithAbsolutePaths: false,
parsePDF: true,
removeTags: []
removeTags: [],
};
this.extractorOptions = options.extractorOptions ?? {mode: "markdown"}
this.replaceAllPathsWithAbsolutePaths = options.crawlerOptions?.replaceAllPathsWithAbsolutePaths ?? options.pageOptions?.replaceAllPathsWithAbsolutePaths ?? false;
//! @nicolas, for some reason this was being injected and breaking everything. Don't have time to find source of the issue so adding this check
this.excludes = this.excludes.filter((item) => item !== "");
this.extractorOptions = options.extractorOptions ?? { mode: "markdown" };
this.replaceAllPathsWithAbsolutePaths =
options.crawlerOptions?.replaceAllPathsWithAbsolutePaths ??
options.pageOptions?.replaceAllPathsWithAbsolutePaths ??
false;
if (typeof options.crawlerOptions?.excludes === 'string') {
this.excludes = options.crawlerOptions?.excludes.split(',').filter((item) => item.trim() !== "");
}
if (typeof options.crawlerOptions?.includes === 'string') {
this.includes = options.crawlerOptions?.includes.split(',').filter((item) => item.trim() !== "");
}
this.crawlerMode = options.crawlerOptions?.mode ?? "default";
this.ignoreSitemap = options.crawlerOptions?.ignoreSitemap ?? false;
this.allowBackwardCrawling = options.crawlerOptions?.allowBackwardCrawling ?? false;
this.allowExternalContentLinks = options.crawlerOptions?.allowExternalContentLinks ?? false;
this.allowBackwardCrawling =
options.crawlerOptions?.allowBackwardCrawling ?? false;
this.allowExternalContentLinks =
options.crawlerOptions?.allowExternalContentLinks ?? false;
// make sure all urls start with https://
this.urls = this.urls.map((url) => {
@ -537,6 +646,34 @@ export class WebScraperDataProvider {
}
return documents;
}
private async getSitemapDataForSingleUrl(
baseUrl: string,
url: string,
timeout?: number
) {
const sitemapData = await fetchSitemapData(baseUrl, timeout);
if (sitemapData) {
const docInSitemapData = sitemapData.find(
(data) => this.normalizeUrl(data.loc) === this.normalizeUrl(url)
);
if (docInSitemapData) {
let sitemapDocData: Partial<SitemapEntry> = {};
if (docInSitemapData.changefreq) {
sitemapDocData.changefreq = docInSitemapData.changefreq;
}
if (docInSitemapData.priority) {
sitemapDocData.priority = Number(docInSitemapData.priority);
}
if (docInSitemapData.lastmod) {
sitemapDocData.lastmod = docInSitemapData.lastmod;
}
if (Object.keys(sitemapDocData).length !== 0) {
return sitemapDocData;
}
}
}
return null;
}
generatesImgAltText = async (documents: Document[]): Promise<Document[]> => {
await Promise.all(
documents.map(async (document) => {

9
apps/api/src/scraper/WebScraper/scrapers/fetch.ts
View File

@ -2,6 +2,7 @@ import axios from "axios";
import { logScrape } from "../../../services/logging/scrape_log";
import { fetchAndProcessPdf } from "../utils/pdfProcessor";
import { universalTimeout } from "../global";
import { Logger } from "../../../lib/logger";
/**
* Scrapes a URL with Axios
@ -34,9 +35,7 @@ export async function scrapWithFetch(
});
if (response.status !== 200) {
console.error(
`[Axios] Error fetching url: ${url} with status: ${response.status}`
);
Logger.debug(`⛏️ Axios: Failed to fetch url: ${url} with status: ${response.status}`);
logParams.error_message = response.statusText;
logParams.response_code = response.status;
return {
@ -63,10 +62,10 @@ export async function scrapWithFetch(
} catch (error) {
if (error.code === "ECONNABORTED") {
logParams.error_message = "Request timed out";
console.log(`[Axios] Request timed out for ${url}`);
Logger.debug(`⛏️ Axios: Request timed out for ${url}`);
} else {
logParams.error_message = error.message || error;
console.error(`[Axios] Error fetching url: ${url} -> ${error}`);
Logger.debug(`⛏️ Axios: Failed to fetch url: ${url} | Error: ${error}`);
}
return { content: "", pageStatusCode: null, pageError: logParams.error_message };
} finally {

44
apps/api/src/scraper/WebScraper/scrapers/fireEngine.ts
View File

@ -1,15 +1,17 @@
import axios from "axios";
import { FireEngineResponse } from "../../../lib/entities";
import { FireEngineOptions, FireEngineResponse } from "../../../lib/entities";
import { logScrape } from "../../../services/logging/scrape_log";
import { generateRequestParams } from "../single_url";
import { fetchAndProcessPdf } from "../utils/pdfProcessor";
import { universalTimeout } from "../global";
import { Logger } from "../../../lib/logger";
/**
* Scrapes a URL with Fire-Engine
* @param url The URL to scrape
* @param waitFor The time to wait for the page to load
* @param screenshot Whether to take a screenshot
* @param fullPageScreenshot Whether to take a full page screenshot
* @param pageOptions The options for the page
* @param headers The headers to send with the request
* @param options The options for the request
@ -19,14 +21,18 @@ export async function scrapWithFireEngine({
url,
waitFor = 0,
screenshot = false,
fullPageScreenshot = false,
pageOptions = { parsePDF: true },
fireEngineOptions = {},
headers,
options,
}: {
url: string;
waitFor?: number;
screenshot?: boolean;
fullPageScreenshot?: boolean;
pageOptions?: { scrollXPaths?: string[]; parsePDF?: boolean };
fireEngineOptions?: FireEngineOptions;
headers?: Record<string, string>;
options?: any;
}): Promise<FireEngineResponse> {
@ -44,19 +50,35 @@ export async function scrapWithFireEngine({
try {
const reqParams = await generateRequestParams(url);
const waitParam = reqParams["params"]?.wait ?? waitFor;
const engineParam = reqParams["params"]?.engine ?? reqParams["params"]?.fireEngineOptions?.engine ?? fireEngineOptions?.engine ?? "playwright";
const screenshotParam = reqParams["params"]?.screenshot ?? screenshot;
console.log(
`[Fire-Engine] Scraping ${url} with wait: ${waitParam} and screenshot: ${screenshotParam}`
const fullPageScreenshotParam = reqParams["params"]?.fullPageScreenshot ?? fullPageScreenshot;
const fireEngineOptionsParam : FireEngineOptions = reqParams["params"]?.fireEngineOptions ?? fireEngineOptions;
let endpoint = "/scrape";
if(options?.endpoint === "request") {
endpoint = "/request";
}
let engine = engineParam; // do we want fireEngineOptions as first choice?
Logger.info(
`⛏️ Fire-Engine (${engine}): Scraping ${url} | params: { wait: ${waitParam}, screenshot: ${screenshotParam}, fullPageScreenshot: ${fullPageScreenshot}, method: ${fireEngineOptionsParam?.method ?? "null"} }`
);
const response = await axios.post(
process.env.FIRE_ENGINE_BETA_URL + "/scrape",
process.env.FIRE_ENGINE_BETA_URL + endpoint,
{
url: url,
wait: waitParam,
screenshot: screenshotParam,
fullPageScreenshot: fullPageScreenshotParam,
headers: headers,
pageOptions: pageOptions,
...fireEngineOptionsParam,
},
{
headers: {
@ -67,11 +89,17 @@ export async function scrapWithFireEngine({
);
if (response.status !== 200) {
console.error(
`[Fire-Engine] Error fetching url: ${url} with status: ${response.status}`
Logger.debug(
`⛏️ Fire-Engine (${engine}): Failed to fetch url: ${url} \t status: ${response.status}`
);
logParams.error_message = response.data?.pageError;
logParams.response_code = response.data?.pageStatusCode;
if(response.data && response.data?.pageStatusCode !== 200) {
Logger.debug(`⛏️ Fire-Engine (${engine}): Failed to fetch url: ${url} \t status: ${response.status}`);
}
return {
html: "",
screenshot: "",
@ -107,10 +135,10 @@ export async function scrapWithFireEngine({
}
} catch (error) {
if (error.code === "ECONNABORTED") {
console.log(`[Fire-Engine] Request timed out for ${url}`);
Logger.debug(`⛏️ Fire-Engine: Request timed out for ${url}`);
logParams.error_message = "Request timed out";
} else {
console.error(`[Fire-Engine][c] Error fetching url: ${url} -> ${error}`);
Logger.debug(`⛏️ Fire-Engine: Failed to fetch url: ${url} | Error: ${error}`);
logParams.error_message = error.message || error;
}
return { html: "", screenshot: "", pageStatusCode: null, pageError: logParams.error_message };

13
apps/api/src/scraper/WebScraper/scrapers/playwright.ts
View File

@ -3,6 +3,7 @@ import { logScrape } from "../../../services/logging/scrape_log";
import { generateRequestParams } from "../single_url";
import { fetchAndProcessPdf } from "../utils/pdfProcessor";
import { universalTimeout } from "../global";
import { Logger } from "../../../lib/logger";
/**
* Scrapes a URL with Playwright
@ -51,8 +52,8 @@ export async function scrapWithPlaywright(
);
if (response.status !== 200) {
console.error(
`[Playwright] Error fetching url: ${url} with status: ${response.status}`
Logger.debug(
`⛏️ Playwright: Failed to fetch url: ${url} | status: ${response.status}, error: ${response.data?.pageError}`
);
logParams.error_message = response.data?.pageError;
logParams.response_code = response.data?.pageStatusCode;
@ -86,8 +87,8 @@ export async function scrapWithPlaywright(
};
} catch (jsonError) {
logParams.error_message = jsonError.message || jsonError;
console.error(
`[Playwright] Error parsing JSON response for url: ${url} -> ${jsonError}`
Logger.debug(
`⛏️ Playwright: Error parsing JSON response for url: ${url} | Error: ${jsonError}`
);
return { content: "", pageStatusCode: null, pageError: logParams.error_message };
}
@ -95,10 +96,10 @@ export async function scrapWithPlaywright(
} catch (error) {
if (error.code === "ECONNABORTED") {
logParams.error_message = "Request timed out";
console.log(`[Playwright] Request timed out for ${url}`);
Logger.debug(`⛏️ Playwright: Request timed out for ${url}`);
} else {
logParams.error_message = error.message || error;
console.error(`[Playwright] Error fetching url: ${url} -> ${error}`);
Logger.debug(`⛏️ Playwright: Failed to fetch url: ${url} | Error: ${error}`);
}
return { content: "", pageStatusCode: null, pageError: logParams.error_message };
} finally {

7
apps/api/src/scraper/WebScraper/scrapers/scrapingBee.ts
View File

@ -3,6 +3,7 @@ import { generateRequestParams } from "../single_url";
import { fetchAndProcessPdf } from "../utils/pdfProcessor";
import { universalTimeout } from "../global";
import { ScrapingBeeClient } from "scrapingbee";
import { Logger } from "../../../lib/logger";
/**
* Scrapes a URL with ScrapingBee
@ -56,8 +57,8 @@ export async function scrapWithScrapingBee(
text = decoder.decode(response.data);
logParams.success = true;
} catch (decodeError) {
console.error(
`[ScrapingBee][c] Error decoding response data for url: ${url} -> ${decodeError}`
Logger.debug(
`⛏️ ScrapingBee: Error decoding response data for url: ${url} | Error: ${decodeError}`
);
logParams.error_message = decodeError.message || decodeError;
}
@ -72,7 +73,7 @@ export async function scrapWithScrapingBee(
};
}
} catch (error) {
console.error(`[ScrapingBee][c] Error fetching url: ${url} -> ${error}`);
Logger.debug(`⛏️ ScrapingBee: Error fetching url: ${url} | Error: ${error}`);
logParams.error_message = error.message || error;
logParams.response_code = error.response?.status;
return {

102
apps/api/src/scraper/WebScraper/single_url.ts
View File

@ -16,16 +16,21 @@ import { scrapWithFetch } from "./scrapers/fetch";
import { scrapWithFireEngine } from "./scrapers/fireEngine";
import { scrapWithPlaywright } from "./scrapers/playwright";
import { scrapWithScrapingBee } from "./scrapers/scrapingBee";
import { extractLinks } from "./utils/utils";
import { Logger } from "../../lib/logger";
import { ScrapeEvents } from "../../lib/scrape-events";
import { clientSideError } from "../../strings";
dotenv.config();
const baseScrapers = [
export const baseScrapers = [
"fire-engine",
"fire-engine;chrome-cdp",
"scrapingBee",
"playwright",
process.env.USE_DB_AUTHENTICATION ? undefined : "playwright",
"scrapingBeeLoad",
"fetch",
] as const;
].filter(Boolean);
export async function generateRequestParams(
url: string,
@ -46,7 +51,7 @@ export async function generateRequestParams(
return defaultParams;
}
} catch (error) {
console.error(`Error generating URL key: ${error}`);
Logger.error(`Error generating URL key: ${error}`);
return defaultParams;
}
}
@ -70,6 +75,8 @@ function getScrapingFallbackOrder(
return !!process.env.SCRAPING_BEE_API_KEY;
case "fire-engine":
return !!process.env.FIRE_ENGINE_BETA_URL;
case "fire-engine;chrome-cdp":
return !!process.env.FIRE_ENGINE_BETA_URL;
case "playwright":
return !!process.env.PLAYWRIGHT_MICROSERVICE_URL;
default:
@ -78,21 +85,22 @@ function getScrapingFallbackOrder(
});
let defaultOrder = [
!process.env.USE_DB_AUTHENTICATION ? undefined : "fire-engine",
!process.env.USE_DB_AUTHENTICATION ? undefined : "fire-engine;chrome-cdp",
"scrapingBee",
"fire-engine",
"playwright",
process.env.USE_DB_AUTHENTICATION ? undefined : "playwright",
"scrapingBeeLoad",
"fetch",
];
].filter(Boolean);
if (isWaitPresent || isScreenshotPresent || isHeadersPresent) {
defaultOrder = [
"fire-engine",
"playwright",
process.env.USE_DB_AUTHENTICATION ? undefined : "playwright",
...defaultOrder.filter(
(scraper) => scraper !== "fire-engine" && scraper !== "playwright"
),
];
].filter(Boolean);
}
const filteredDefaultOrder = defaultOrder.filter(
@ -109,7 +117,10 @@ function getScrapingFallbackOrder(
return scrapersInOrder as (typeof baseScrapers)[number][];
}
export async function scrapSingleUrl(
jobId: string,
urlToScrap: string,
pageOptions: PageOptions = {
onlyMainContent: true,
@ -117,6 +128,7 @@ export async function scrapSingleUrl(
includeRawHtml: false,
waitFor: 0,
screenshot: false,
fullPageScreenshot: false,
headers: undefined,
},
extractorOptions: ExtractorOptions = {
@ -136,16 +148,36 @@ export async function scrapSingleUrl(
metadata: { pageStatusCode?: number; pageError?: string | null };
} = { text: "", screenshot: "", metadata: {} };
let screenshot = "";
const timer = Date.now();
const logInsertPromise = ScrapeEvents.insert(jobId, {
type: "scrape",
url,
worker: process.env.FLY_MACHINE_ID,
method,
result: null,
});
switch (method) {
case "fire-engine":
case "fire-engine;chrome-cdp":
let engine: "playwright" | "chrome-cdp" | "tlsclient" = "playwright";
if(method === "fire-engine;chrome-cdp"){
engine = "chrome-cdp";
}
if (process.env.FIRE_ENGINE_BETA_URL) {
console.log(`Scraping ${url} with Fire Engine`);
const response = await scrapWithFireEngine({
url,
waitFor: pageOptions.waitFor,
screenshot: pageOptions.screenshot,
fullPageScreenshot: pageOptions.fullPageScreenshot,
pageOptions: pageOptions,
headers: pageOptions.headers,
fireEngineOptions: {
engine: engine,
}
});
scraperResponse.text = response.html;
scraperResponse.screenshot = response.screenshot;
@ -234,11 +266,21 @@ export async function scrapSingleUrl(
scraperResponse.text = customScrapedContent.html;
screenshot = customScrapedContent.screenshot;
}
//* TODO: add an optional to return markdown or structured/extracted content
let cleanedHtml = removeUnwantedElements(scraperResponse.text, pageOptions);
const text = await parseMarkdown(cleanedHtml);
const insertedLogId = await logInsertPromise;
ScrapeEvents.updateScrapeResult(insertedLogId, {
response_size: scraperResponse.text.length,
success: !(scraperResponse.metadata.pageStatusCode && scraperResponse.metadata.pageStatusCode >= 400) && !!text && (text.trim().length >= 100),
error: scraperResponse.metadata.pageError,
response_code: scraperResponse.metadata.pageStatusCode,
time_taken: Date.now() - timer,
});
return {
text: await parseMarkdown(cleanedHtml),
text,
html: cleanedHtml,
rawHtml: scraperResponse.text,
screenshot: scraperResponse.screenshot,
@ -260,19 +302,19 @@ export async function scrapSingleUrl(
try {
urlKey = new URL(urlToScrap).hostname.replace(/^www\./, "");
} catch (error) {
console.error(`Invalid URL key, trying: ${urlToScrap}`);
Logger.error(`Invalid URL key, trying: ${urlToScrap}`);
}
const defaultScraper = urlSpecificParams[urlKey]?.defaultScraper ?? "";
const scrapersInOrder = getScrapingFallbackOrder(
defaultScraper,
pageOptions && pageOptions.waitFor && pageOptions.waitFor > 0,
pageOptions && pageOptions.screenshot && pageOptions.screenshot === true,
pageOptions && (pageOptions.screenshot || pageOptions.fullPageScreenshot) && (pageOptions.screenshot === true || pageOptions.fullPageScreenshot === true),
pageOptions && pageOptions.headers && pageOptions.headers !== undefined
);
for (const scraper of scrapersInOrder) {
// If exists text coming from crawler, use it
if (existingHtml && existingHtml.trim().length >= 100) {
if (existingHtml && existingHtml.trim().length >= 100 && !existingHtml.includes(clientSideError)) {
let cleanedHtml = removeUnwantedElements(existingHtml, pageOptions);
text = await parseMarkdown(cleanedHtml);
html = cleanedHtml;
@ -294,12 +336,18 @@ export async function scrapSingleUrl(
pageError = undefined;
}
if (text && text.trim().length >= 100) break;
if (pageStatusCode && pageStatusCode == 404) break;
const nextScraperIndex = scrapersInOrder.indexOf(scraper) + 1;
if (nextScraperIndex < scrapersInOrder.length) {
console.info(`Falling back to ${scrapersInOrder[nextScraperIndex]}`);
if (text && text.trim().length >= 100) {
Logger.debug(`⛏️ ${scraper}: Successfully scraped ${urlToScrap} with text length >= 100, breaking`);
break;
}
if (pageStatusCode && pageStatusCode == 404) {
Logger.debug(`⛏️ ${scraper}: Successfully scraped ${urlToScrap} with status code 404, breaking`);
break;
}
// const nextScraperIndex = scrapersInOrder.indexOf(scraper) + 1;
// if (nextScraperIndex < scrapersInOrder.length) {
// Logger.debug(`⛏️ ${scraper} Failed to fetch URL: ${urlToScrap} with status: ${pageStatusCode}, error: ${pageError} | Falling back to ${scrapersInOrder[nextScraperIndex]}`);
// }
}
if (!text) {
@ -309,6 +357,10 @@ export async function scrapSingleUrl(
const soup = cheerio.load(rawHtml);
const metadata = extractMetadata(soup, urlToScrap);
let linksOnPage: string[] | undefined;
linksOnPage = extractLinks(rawHtml, urlToScrap);
let document: Document;
if (screenshot && screenshot.length > 0) {
document = {
@ -320,6 +372,7 @@ export async function scrapSingleUrl(
extractorOptions.mode === "llm-extraction-from-raw-html"
? rawHtml
: undefined,
linksOnPage,
metadata: {
...metadata,
screenshot: screenshot,
@ -344,16 +397,23 @@ export async function scrapSingleUrl(
pageStatusCode: pageStatusCode,
pageError: pageError,
},
linksOnPage,
};
}
return document;
} catch (error) {
console.error(`Error: ${error} - Failed to fetch URL: ${urlToScrap}`);
Logger.debug(`⛏️ Error: ${error.message} - Failed to fetch URL: ${urlToScrap}`);
ScrapeEvents.insert(jobId, {
type: "error",
message: typeof error === "string" ? error : typeof error.message === "string" ? error.message : JSON.stringify(error),
stack: error.stack,
});
return {
content: "",
markdown: "",
html: "",
linksOnPage: [],
metadata: {
sourceURL: urlToScrap,
pageStatusCode: pageStatusCode,

29
apps/api/src/scraper/WebScraper/sitemap.ts
View File

@ -1,18 +1,33 @@
import axios from "axios";
import { axiosTimeout } from "../../lib/timeout";
import { parseStringPromise } from "xml2js";
import { scrapWithFireEngine } from "./scrapers/fireEngine";
import { WebCrawler } from "./crawler";
import { Logger } from "../../lib/logger";
export async function getLinksFromSitemap(
{
sitemapUrl,
allUrls = [],
mode = 'axios'
}: {
sitemapUrl: string,
allUrls: string[] = []
allUrls?: string[],
mode?: 'axios' | 'fire-engine'
}
): Promise<string[]> {
try {
let content: string;
try {
if (mode === 'axios' || process.env.FIRE_ENGINE_BETA_URL === '') {
const response = await axios.get(sitemapUrl, { timeout: axiosTimeout });
content = response.data;
} else if (mode === 'fire-engine') {
const response = await scrapWithFireEngine({ url: sitemapUrl, fireEngineOptions: { engine:"tlsclient", disableJsDom: true, mobileProxy: true } });
content = response.html;
}
} catch (error) {
console.error(`Request failed for ${sitemapUrl}: ${error}`);
Logger.error(`Request failed for ${sitemapUrl}: ${error.message}`);
return allUrls;
}
@ -23,27 +38,27 @@ export async function getLinksFromSitemap(
if (root && root.sitemap) {
for (const sitemap of root.sitemap) {
if (sitemap.loc && sitemap.loc.length > 0) {
await getLinksFromSitemap(sitemap.loc[0], allUrls);
await getLinksFromSitemap({ sitemapUrl: sitemap.loc[0], allUrls, mode });
}
}
} else if (root && root.url) {
for (const url of root.url) {
if (url.loc && url.loc.length > 0) {
if (url.loc && url.loc.length > 0 && !WebCrawler.prototype.isFile(url.loc[0])) {
allUrls.push(url.loc[0]);
}
}
}
} catch (error) {
console.error(`Error processing ${sitemapUrl}: ${error}`);
Logger.debug(`Error processing sitemapUrl: ${sitemapUrl} | Error: ${error.message}`);
}
return allUrls;
}
export const fetchSitemapData = async (url: string): Promise<SitemapEntry[] | null> => {
export const fetchSitemapData = async (url: string, timeout?: number): Promise<SitemapEntry[] | null> => {
const sitemapUrl = url.endsWith("/sitemap.xml") ? url : `${url}/sitemap.xml`;
try {
const response = await axios.get(sitemapUrl, { timeout: axiosTimeout });
const response = await axios.get(sitemapUrl, { timeout: timeout || axiosTimeout });
if (response.status === 200) {
const xml = response.data;
const parsedXml = await parseStringPromise(xml);

3
apps/api/src/scraper/WebScraper/utils/__tests__/socialBlockList.test.ts
View File

@ -1,3 +1,4 @@
import { Logger } from '../../../../lib/logger';
import { isUrlBlocked } from '../blocklist';
describe('isUrlBlocked', () => {
@ -19,7 +20,7 @@ describe('isUrlBlocked', () => {
blockedUrls.forEach(url => {
if (!isUrlBlocked(url)) {
console.log(`URL not blocked: ${url}`);
Logger.debug(`URL not blocked: ${url}`);
}
expect(isUrlBlocked(url)).toBe(true);
});

4
apps/api/src/scraper/WebScraper/utils/blocklist.ts
View File

@ -1,3 +1,5 @@
import { Logger } from "../../../lib/logger";
const socialMediaBlocklist = [
'facebook.com',
'x.com',
@ -59,7 +61,7 @@ export function isUrlBlocked(url: string): boolean {
return isBlocked;
} catch (e) {
// If an error occurs (e.g., invalid URL), return false
console.error(`Error processing URL: ${url}`, e);
Logger.error(`Error parsing the following URL: ${url}`);
return false;
}
}

87
apps/api/src/scraper/WebScraper/utils/custom/website_params.ts
View File

@ -1,28 +1,15 @@
export const urlSpecificParams = {
"platform.openai.com": {
defaultScraper: "fire-engine",
params:{
wait_browser: "networkidle2",
block_resources: false,
wait: 3000,
fireEngineOptions:{
engine: "chrome-cdp"
},
headers: {
"User-Agent":
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/124.0.0.0 Safari/537.36",
"sec-fetch-site": "same-origin",
"sec-fetch-mode": "cors",
"sec-fetch-dest": "empty",
referer: "https://www.google.com/",
"accept-language": "en-US,en;q=0.9",
"accept-encoding": "gzip, deflate, br",
accept:
"text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9",
},
cookies: {
__cf_bm:
"mC1On8P2GWT3A5UeSYH6z_MP94xcTAdZ5jfNi9IT2U0-1714327136-1.0.1.1-ILAP5pSX_Oo9PPo2iHEYCYX.p9a0yRBNLr58GHyrzYNDJ537xYpG50MXxUYVdfrD.h3FV5O7oMlRKGA0scbxaQ",
},
},
"support.greenpay.me":{
defaultScraper: "playwright",
defaultScraper: "fire-engine",
params: {
wait_browser: "networkidle2",
block_resources: false,
@ -43,7 +30,7 @@ export const urlSpecificParams = {
},
},
"docs.pdw.co":{
defaultScraper: "playwright",
defaultScraper: "fire-engine",
params: {
wait_browser: "networkidle2",
block_resources: false,
@ -83,7 +70,7 @@ export const urlSpecificParams = {
},
},
"developers.notion.com":{
defaultScraper: "playwright",
defaultScraper: "fire-engine",
params: {
wait_browser: "networkidle2",
block_resources: false,
@ -103,7 +90,7 @@ export const urlSpecificParams = {
},
},
"docs2.hubitat.com":{
defaultScraper: "playwright",
defaultScraper: "fire-engine",
params: {
wait_browser: "networkidle2",
block_resources: false,
@ -153,7 +140,7 @@ export const urlSpecificParams = {
},
},
"help.salesforce.com":{
defaultScraper: "playwright",
defaultScraper: "fire-engine",
params: {
wait_browser: "networkidle2",
block_resources: false,
@ -175,6 +162,7 @@ export const urlSpecificParams = {
"firecrawl.dev":{
defaultScraper: "fire-engine",
params: {
engine: "playwright",
headers: {
"User-Agent":
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/124.0.0.0 Safari/537.36",
@ -192,4 +180,59 @@ export const urlSpecificParams = {
"ir.veeva.com":{
defaultScraper: "fire-engine",
},
"eonhealth.com":{
defaultScraper: "fire-engine",
params:{
fireEngineOptions:{
mobileProxy: true,
method: "get",
engine: "request",
},
},
},
"notion.com":{
defaultScraper: "fire-engine",
params: {
wait_browser: "networkidle2",
block_resources: false,
wait: 2000,
engine: "playwright",
}
},
"mendable.ai":{
defaultScraper: "fire-engine",
params:{
fireEngineOptions:{
mobileProxy: true,
method: "get",
engine: "chrome-cdp",
},
},
},
"developer.apple.com":{
defaultScraper: "fire-engine",
params:{
engine: "playwright",
wait: 2000,
fireEngineOptions: {
blockMedia: false,
}
},
},
"amazon.com":{
defaultScraper: "fire-engine",
params:{
fireEngineOptions:{
engine: "chrome-cdp",
},
},
},
"digikey.com":{
defaultScraper: "fire-engine",
params:{
fireEngineOptions:{
engine: "tlsclient",
},
},
}
};

44
apps/api/src/scraper/WebScraper/utils/docxProcessor.ts
View File

@ -4,15 +4,36 @@ import { createWriteStream } from "node:fs";
import path from "path";
import os from "os";
import mammoth from "mammoth";
import { Logger } from "../../../lib/logger";
export async function fetchAndProcessDocx(url: string): Promise<{ content: string; pageStatusCode: number; pageError: string }> {
const { tempFilePath, pageStatusCode, pageError } = await downloadDocx(url);
const content = await processDocxToText(tempFilePath);
let tempFilePath = '';
let pageStatusCode = 200;
let pageError = '';
let content = '';
try {
const downloadResult = await downloadDocx(url);
tempFilePath = downloadResult.tempFilePath;
pageStatusCode = downloadResult.pageStatusCode;
pageError = downloadResult.pageError;
content = await processDocxToText(tempFilePath);
} catch (error) {
Logger.error(`Failed to fetch and process DOCX: ${error.message}`);
pageStatusCode = 500;
pageError = error.message;
content = '';
} finally {
if (tempFilePath) {
fs.unlinkSync(tempFilePath); // Clean up the temporary file
}
}
return { content, pageStatusCode, pageError };
}
async function downloadDocx(url: string): Promise<{ tempFilePath: string; pageStatusCode: number; pageError: string }> {
try {
const response = await axios({
url,
method: "GET",
@ -26,16 +47,33 @@ async function downloadDocx(url: string): Promise<{ tempFilePath: string; pageSt
return new Promise((resolve, reject) => {
writer.on("finish", () => resolve({ tempFilePath, pageStatusCode: response.status, pageError: response.statusText != "OK" ? response.statusText : undefined }));
writer.on("error", reject);
writer.on("error", () => {
Logger.error('Failed to write DOCX file to disk');
reject(new Error('Failed to write DOCX file to disk'));
});
});
} catch (error) {
Logger.error(`Failed to download DOCX: ${error.message}`);
return { tempFilePath: "", pageStatusCode: 500, pageError: error.message };
}
}
export async function processDocxToText(filePath: string): Promise<string> {
try {
const content = await extractTextFromDocx(filePath);
return content;
} catch (error) {
Logger.error(`Failed to process DOCX to text: ${error.message}`);
return "";
}
}
async function extractTextFromDocx(filePath: string): Promise<string> {
try {
const result = await mammoth.extractRawText({ path: filePath });
return result.value;
} catch (error) {
Logger.error(`Failed to extract text from DOCX: ${error.message}`);
return "";
}
}

3
apps/api/src/scraper/WebScraper/utils/imageDescription.ts
View File

@ -1,5 +1,6 @@
import Anthropic from '@anthropic-ai/sdk';
import axios from 'axios';
import { Logger } from '../../../lib/logger';
export async function getImageDescription(
imageUrl: string,
@ -82,7 +83,7 @@ export async function getImageDescription(
}
}
} catch (error) {
console.error("Error generating image alt text:", error?.message);
Logger.error(`Error generating image alt text: ${error}`);
return "";
}
}

4
apps/api/src/scraper/WebScraper/utils/metadata.ts
View File

@ -1,4 +1,6 @@
import { CheerioAPI } from "cheerio";
import { Logger } from "../../../lib/logger";
interface Metadata {
title?: string;
description?: string;
@ -105,7 +107,7 @@ export function extractMetadata(soup: CheerioAPI, url: string): Metadata {
dctermsCreated = soup('meta[name="dcterms.created"]').attr("content") || null;
} catch (error) {
console.error("Error extracting metadata:", error);
Logger.error(`Error extracting metadata: ${error}`);
}
return {

35
apps/api/src/scraper/WebScraper/utils/pdfProcessor.ts
View File

@ -7,14 +7,20 @@ import pdf from "pdf-parse";
import path from "path";
import os from "os";
import { axiosTimeout } from "../../../lib/timeout";
import { Logger } from "../../../lib/logger";
dotenv.config();
export async function fetchAndProcessPdf(url: string, parsePDF: boolean): Promise<{ content: string, pageStatusCode?: number, pageError?: string }> {
try {
const { tempFilePath, pageStatusCode, pageError } = await downloadPdf(url);
const content = await processPdfToText(tempFilePath, parsePDF);
fs.unlinkSync(tempFilePath); // Clean up the temporary file
return { content, pageStatusCode, pageError };
} catch (error) {
Logger.error(`Failed to fetch and process PDF: ${error.message}`);
return { content: "", pageStatusCode: 500, pageError: error.message };
}
}
async function downloadPdf(url: string): Promise<{ tempFilePath: string, pageStatusCode?: number, pageError?: string }> {
@ -39,6 +45,7 @@ export async function processPdfToText(filePath: string, parsePDF: boolean): Pro
let content = "";
if (process.env.LLAMAPARSE_API_KEY && parsePDF) {
Logger.debug("Processing pdf document w/ LlamaIndex");
const apiKey = process.env.LLAMAPARSE_API_KEY;
const headers = {
Authorization: `Bearer ${apiKey}`,
@ -69,7 +76,6 @@ export async function processPdfToText(filePath: string, parsePDF: boolean): Pro
let attempt = 0;
const maxAttempts = 10; // Maximum number of attempts
let resultAvailable = false;
while (attempt < maxAttempts && !resultAvailable) {
try {
resultResponse = await axios.get(resultUrl, { headers, timeout: (axiosTimeout * 2) });
@ -81,31 +87,54 @@ export async function processPdfToText(filePath: string, parsePDF: boolean): Pro
await new Promise((resolve) => setTimeout(resolve, 500)); // Wait for 0.5 seconds
}
} catch (error) {
console.error("Error fetching result w/ LlamaIndex");
Logger.debug("Error fetching result w/ LlamaIndex");
attempt++;
if (attempt >= maxAttempts) {
Logger.error("Max attempts reached, unable to fetch result.");
break; // Exit the loop if max attempts are reached
}
await new Promise((resolve) => setTimeout(resolve, 500)); // Wait for 0.5 seconds before retrying
// You may want to handle specific errors differently
}
}
if (!resultAvailable) {
try {
content = await processPdf(filePath);
} catch (error) {
Logger.error(`Failed to process PDF: ${error}`);
content = "";
}
}
content = resultResponse.data[resultType];
} catch (error) {
console.error("Error processing pdf document w/ LlamaIndex(2)");
Logger.debug("Error processing pdf document w/ LlamaIndex(2)");
content = await processPdf(filePath);
}
} else if (parsePDF) {
try {
content = await processPdf(filePath);
} catch (error) {
Logger.error(`Failed to process PDF: ${error}`);
content = "";
}
} else {
try {
content = fs.readFileSync(filePath, "utf-8");
} catch (error) {
Logger.error(`Failed to read PDF file: ${error}`);
content = "";
}
}
return content;
}
async function processPdf(file: string) {
try {
const fileContent = fs.readFileSync(file);
const data = await pdf(fileContent);
return data.text;
} catch (error) {
throw error;
}
}

12
apps/api/src/scraper/WebScraper/utils/removeUnwantedElements.ts
View File

@ -8,7 +8,11 @@ export const removeUnwantedElements = (
) => {
const soup = cheerio.load(html);
if (pageOptions.onlyIncludeTags) {
if (
pageOptions.onlyIncludeTags &&
pageOptions.onlyIncludeTags.length > 0 &&
pageOptions.onlyIncludeTags[0] !== ''
) {
if (typeof pageOptions.onlyIncludeTags === "string") {
pageOptions.onlyIncludeTags = [pageOptions.onlyIncludeTags];
}
@ -26,7 +30,11 @@ export const removeUnwantedElements = (
soup("script, style, iframe, noscript, meta, head").remove();
if (pageOptions.removeTags) {
if (
pageOptions.removeTags &&
pageOptions.removeTags.length > 0 &&
pageOptions.removeTags[0] !== ''
) {
if (typeof pageOptions.removeTags === "string") {
pageOptions.removeTags = [pageOptions.removeTags];
}

13
apps/api/src/scraper/WebScraper/utils/replacePaths.ts
View File

@ -1,3 +1,4 @@
import { Logger } from "../../../lib/logger";
import { Document } from "../../../lib/entities";
export const replacePathsWithAbsolutePaths = (documents: Document[]): Document[] => {
@ -6,13 +7,13 @@ export const replacePathsWithAbsolutePaths = (documents: Document[]): Document[]
const baseUrl = new URL(document.metadata.sourceURL).origin;
const paths =
document.content.match(
/(!?\[.*?\])\(((?:[^()]+|\((?:[^()]+|\([^()]*\))*\))*)\)|href="([^"]+)"/g
/!?\[.*?\]\(.*?\)|href=".+?"/g
) || [];
paths.forEach((path: string) => {
try {
const isImage = path.startsWith("!");
let matchedUrl = path.match(/\(([^)]+)\)/) || path.match(/href="([^"]+)"/);
let matchedUrl = path.match(/\((.*?)\)/) || path.match(/href="([^"]+)"/);
let url = matchedUrl[1];
if (!url.startsWith("data:") && !url.startsWith("http")) {
@ -39,7 +40,7 @@ export const replacePathsWithAbsolutePaths = (documents: Document[]): Document[]
return documents;
} catch (error) {
console.error("Error replacing paths with absolute paths", error);
Logger.debug(`Error replacing paths with absolute paths: ${error}`);
return documents;
}
};
@ -50,11 +51,11 @@ export const replaceImgPathsWithAbsolutePaths = (documents: Document[]): Documen
const baseUrl = new URL(document.metadata.sourceURL).origin;
const images =
document.content.match(
/!\[.*?\]\(((?:[^()]+|\((?:[^()]+|\([^()]*\))*\))*)\)/g
/!\[.*?\]\(.*?\)/g
) || [];
images.forEach((image: string) => {
let imageUrl = image.match(/\(([^)]+)\)/)[1];
let imageUrl = image.match(/\((.*?)\)/)[1];
let altText = image.match(/\[(.*?)\]/)[1];
if (!imageUrl.startsWith("data:image")) {
@ -78,7 +79,7 @@ export const replaceImgPathsWithAbsolutePaths = (documents: Document[]): Documen
return documents;
} catch (error) {
console.error("Error replacing img paths with absolute paths", error);
Logger.error(`Error replacing img paths with absolute paths: ${error}`);
return documents;
}
};

39
apps/api/src/scraper/WebScraper/utils/utils.ts
View File

@ -1,4 +1,7 @@
import axios from "axios";
import * as cheerio from "cheerio";
import { Logger } from "../../../lib/logger";
export async function attemptScrapWithRequests(
urlToScrap: string
@ -7,13 +10,13 @@ export async function attemptScrapWithRequests(
const response = await axios.get(urlToScrap, { timeout: 15000 });
if (!response.data) {
console.log("Failed normal requests as well");
Logger.debug("Failed normal requests as well");
return null;
}
return response.data;
} catch (error) {
console.error(`Error in attemptScrapWithRequests: ${error}`);
Logger.debug(`Error in attemptScrapWithRequests: ${error}`);
return null;
}
}
@ -21,3 +24,35 @@ export async function attemptScrapWithRequests(
export function sanitizeText(text: string): string {
return text.replace("\u0000", "");
}
export function extractLinks(html: string, baseUrl: string): string[] {
const $ = cheerio.load(html);
const links: string[] = [];
// Parse the base URL to get the origin
const urlObject = new URL(baseUrl);
const origin = urlObject.origin;
$('a').each((_, element) => {
const href = $(element).attr('href');
if (href) {
if (href.startsWith('http://') || href.startsWith('https://')) {
// Absolute URL, add as is
links.push(href);
} else if (href.startsWith('/')) {
// Relative URL starting with '/', append to origin
links.push(`${origin}${href}`);
} else if (!href.startsWith('#') && !href.startsWith('mailto:')) {
// Relative URL not starting with '/', append to base URL
links.push(`${baseUrl}/${href}`);
} else if (href.startsWith('mailto:')) {
// mailto: links, add as is
links.push(href);
}
// Fragment-only links (#) are ignored
}
});
// Remove duplicates and return
return [...new Set(links)];
}

5
apps/api/src/search/googlesearch.ts
View File

@ -2,6 +2,7 @@ import axios from 'axios';
import * as cheerio from 'cheerio';
import * as querystring from 'querystring';
import { SearchResult } from '../../src/lib/entities';
import { Logger } from '../../src/lib/logger';
const _useragent_list = [
'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:66.0) Gecko/20100101 Firefox/66.0',
@ -96,7 +97,7 @@ export async function google_search(term: string, advanced = false, num_results
await new Promise(resolve => setTimeout(resolve, sleep_interval * 1000));
} catch (error) {
if (error.message === 'Too many requests') {
console.warn('Too many requests, breaking the loop');
Logger.warn('Too many requests, breaking the loop');
break;
}
throw error;
@ -107,7 +108,7 @@ export async function google_search(term: string, advanced = false, num_results
}
}
if (attempts >= maxAttempts) {
console.warn('Max attempts reached, breaking the loop');
Logger.warn('Max attempts reached, breaking the loop');
}
return results
}

3
apps/api/src/search/index.ts
View File

@ -1,3 +1,4 @@
import { Logger } from "../../src/lib/logger";
import { SearchResult } from "../../src/lib/entities";
import { google_search } from "./googlesearch";
import { serper_search } from "./serper";
@ -47,7 +48,7 @@ export async function search({
timeout
);
} catch (error) {
console.error("Error in search function: ", error);
Logger.error(`Error in search function: ${error}`);
return []
}
// if process.env.SERPER_API_KEY is set, use serper

63
apps/api/src/services/alerts/index.ts Normal file
View File

@ -0,0 +1,63 @@
import { Logger } from "../../../src/lib/logger";
import { getWebScraperQueue } from "../queue-service";
import { sendSlackWebhook } from "./slack";
export async function checkAlerts() {
try {
if (
process.env.SLACK_WEBHOOK_URL &&
process.env.ENV === "production" &&
process.env.ALERT_NUM_ACTIVE_JOBS &&
process.env.ALERT_NUM_WAITING_JOBS
) {
Logger.info("Initializing alerts");
const checkActiveJobs = async () => {
try {
const webScraperQueue = getWebScraperQueue();
const activeJobs = await webScraperQueue.getActiveCount();
if (activeJobs > Number(process.env.ALERT_NUM_ACTIVE_JOBS)) {
Logger.warn(
`Alert: Number of active jobs is over ${process.env.ALERT_NUM_ACTIVE_JOBS}. Current active jobs: ${activeJobs}.`
);
sendSlackWebhook(
`Alert: Number of active jobs is over ${process.env.ALERT_NUM_ACTIVE_JOBS}. Current active jobs: ${activeJobs}`,
true
);
} else {
Logger.info(
`Number of active jobs is under ${process.env.ALERT_NUM_ACTIVE_JOBS}. Current active jobs: ${activeJobs}`
);
}
} catch (error) {
Logger.error(`Failed to check active jobs: ${error}`);
}
};
const checkWaitingQueue = async () => {
const webScraperQueue = getWebScraperQueue();
const waitingJobs = await webScraperQueue.getWaitingCount();
const paused = await webScraperQueue.getPausedCount();
if (waitingJobs !== paused && waitingJobs > Number(process.env.ALERT_NUM_WAITING_JOBS)) {
Logger.warn(
`Alert: Number of waiting jobs is over ${process.env.ALERT_NUM_WAITING_JOBS}. Current waiting jobs: ${waitingJobs}.`
);
sendSlackWebhook(
`Alert: Number of waiting jobs is over ${process.env.ALERT_NUM_WAITING_JOBS}. Current waiting jobs: ${waitingJobs}. Scale up the number of workers with fly scale count worker=20`,
true
);
}
};
const checkAll = async () => {
await checkActiveJobs();
await checkWaitingQueue();
};
await checkAll();
// setInterval(checkAll, 10000); // Run every
}
} catch (error) {
Logger.error(`Failed to initialize alerts: ${error}`);
}
}

24
apps/api/src/services/alerts/slack.ts Normal file
View File

@ -0,0 +1,24 @@
import axios from "axios";
import { Logger } from "../../../src/lib/logger";
export async function sendSlackWebhook(
message: string,
alertEveryone: boolean = false
) {
const webhookUrl = process.env.SLACK_WEBHOOK_URL;
const messagePrefix = alertEveryone ? "<!channel> " : "";
const payload = {
text: `${messagePrefix} ${message}`,
};
try {
const response = await axios.post(webhookUrl, payload, {
headers: {
"Content-Type": "application/json",
},
});
Logger.log("Webhook sent successfully:", response.data);
} catch (error) {
Logger.debug(`Error sending webhook: ${error}`);
}
}

63
apps/api/src/services/billing/credit_billing.ts
View File

@ -2,9 +2,14 @@ import { NotificationType } from "../../types";
import { withAuth } from "../../lib/withAuth";
import { sendNotification } from "../notification/email_notification";
import { supabase_service } from "../supabase";
import { Logger } from "../../lib/logger";
import { getValue, setValue } from "../redis";
import { redlock } from "../redlock";
const FREE_CREDITS = 500;
export async function billTeam(team_id: string, credits: number) {
return withAuth(supaBillTeam)(team_id, credits);
}
@ -12,27 +17,27 @@ export async function supaBillTeam(team_id: string, credits: number) {
if (team_id === "preview") {
return { success: true, message: "Preview team, no credits used" };
}
console.log(`Billing team ${team_id} for ${credits} credits`);
Logger.info(`Billing team ${team_id} for ${credits} credits`);
// When the API is used, you can log the credit usage in the credit_usage table:
// team_id: The ID of the team using the API.
// subscription_id: The ID of the team's active subscription.
// credits_used: The number of credits consumed by the API call.
// created_at: The timestamp of the API usage.
// 1. get the subscription
const { data: subscription } = await supabase_service
// 1. get the subscription and check for available coupons concurrently
const [{ data: subscription }, { data: coupons }] = await Promise.all([
supabase_service
.from("subscriptions")
.select("*")
.eq("team_id", team_id)
.eq("status", "active")
.single();
// 2. Check for available coupons
const { data: coupons } = await supabase_service
.single(),
supabase_service
.from("coupons")
.select("id, credits")
.eq("team_id", team_id)
.eq("status", "active");
.eq("status", "active"),
]);
let couponCredits = 0;
if (coupons && coupons.length > 0) {
@ -169,21 +174,21 @@ export async function supaCheckTeamCredits(team_id: string, credits: number) {
return { success: true, message: "Preview team, no credits used" };
}
// Retrieve the team's active subscription
const { data: subscription, error: subscriptionError } =
await supabase_service
// Retrieve the team's active subscription and check for available coupons concurrently
const [{ data: subscription, error: subscriptionError }, { data: coupons }] =
await Promise.all([
supabase_service
.from("subscriptions")
.select("id, price_id, current_period_start, current_period_end")
.eq("team_id", team_id)
.eq("status", "active")
.single();
// Check for available coupons
const { data: coupons } = await supabase_service
.single(),
supabase_service
.from("coupons")
.select("credits")
.eq("team_id", team_id)
.eq("status", "active");
.eq("status", "active"),
]);
let couponCredits = 0;
if (coupons && coupons.length > 0) {
@ -218,7 +223,7 @@ export async function supaCheckTeamCredits(team_id: string, credits: number) {
0
);
console.log("totalCreditsUsed", totalCreditsUsed);
Logger.info(`totalCreditsUsed: ${totalCreditsUsed}`);
const end = new Date();
end.setDate(end.getDate() + 30);
@ -238,7 +243,6 @@ export async function supaCheckTeamCredits(team_id: string, credits: number) {
// 5. Compare the total credits used with the credits allowed by the plan.
if (totalCreditsUsed + credits > FREE_CREDITS) {
// Send email notification for insufficient credits
await sendNotification(
team_id,
NotificationType.LIMIT_REACHED,
@ -254,7 +258,19 @@ export async function supaCheckTeamCredits(team_id: string, credits: number) {
}
let totalCreditsUsed = 0;
const cacheKey = `credit_usage_${subscription.id}_${subscription.current_period_start}_${subscription.current_period_end}_lc`;
const redLockKey = `lock_${cacheKey}`;
const lockTTL = 10000; // 10 seconds
try {
const lock = await redlock.acquire([redLockKey], lockTTL);
try {
const cachedCreditUsage = await getValue(cacheKey);
if (cachedCreditUsage) {
totalCreditsUsed = parseInt(cachedCreditUsage);
} else {
const { data: creditUsages, error: creditUsageError } =
await supabase_service.rpc("get_credit_usage_2", {
sub_id: subscription.id,
@ -263,19 +279,24 @@ export async function supaCheckTeamCredits(team_id: string, credits: number) {
});
if (creditUsageError) {
console.error("Error calculating credit usage:", creditUsageError);
Logger.error(`Error calculating credit usage: ${creditUsageError}`);
}
if (creditUsages && creditUsages.length > 0) {
totalCreditsUsed = creditUsages[0].total_credits_used;
await setValue(cacheKey, totalCreditsUsed.toString(), 1800); // Cache for 30 minutes
// Logger.info(`Cache set for credit usage: ${totalCreditsUsed}`);
}
}
} finally {
await lock.release();
}
} catch (error) {
console.error("Error calculating credit usage:", error);
Logger.error(`Error acquiring lock or calculating credit usage: ${error}`);
}
// Adjust total credits used by subtracting coupon value
const adjustedCreditsUsed = Math.max(0, totalCreditsUsed - couponCredits);
// Get the price details
const { data: price, error: priceError } = await supabase_service
.from("prices")

3
apps/api/src/services/idempotency/create.ts
View File

@ -1,5 +1,6 @@
import { Request } from "express";
import { supabase_service } from "../supabase";
import { Logger } from "../../../src/lib/logger";
export async function createIdempotencyKey(
req: Request,
@ -14,7 +15,7 @@ export async function createIdempotencyKey(
.insert({ key: idempotencyKey });
if (error) {
console.error("Failed to create idempotency key:", error);
Logger.error(`Failed to create idempotency key: ${error}`);
throw error;
}

5
apps/api/src/services/idempotency/validate.ts
View File

@ -1,6 +1,7 @@
import { Request } from "express";
import { supabase_service } from "../supabase";
import { validate as isUuid } from 'uuid';
import { Logger } from "../../../src/lib/logger";
export async function validateIdempotencyKey(
req: Request,
@ -13,7 +14,7 @@ export async function validateIdempotencyKey(
// Ensure idempotencyKey is treated as a string
const key = Array.isArray(idempotencyKey) ? idempotencyKey[0] : idempotencyKey;
if (!isUuid(key)) {
console.error("Invalid idempotency key provided in the request headers.");
Logger.debug("Invalid idempotency key provided in the request headers.");
return false;
}
@ -23,7 +24,7 @@ export async function validateIdempotencyKey(
.eq("key", idempotencyKey);
if (error) {
console.error(error);
Logger.error(`Error validating idempotency key: ${error}`);
}
if (!data || data.length === 0) {

5
apps/api/src/services/logging/crawl_log.ts
View File

@ -1,7 +1,9 @@
import { supabase_service } from "../supabase";
import { Logger } from "../../../src/lib/logger";
import "dotenv/config";
export async function logCrawl(job_id: string, team_id: string) {
if (process.env.USE_DB_AUTHENTICATION === 'true') {
try {
const { data, error } = await supabase_service
.from("bulljobs_teams")
@ -12,6 +14,7 @@ export async function logCrawl(job_id: string, team_id: string) {
},
]);
} catch (error) {
console.error("Error logging crawl job:\n", error);
Logger.error(`Error logging crawl job to supabase:\n${error}`);
}
}
}

11
apps/api/src/services/logging/log_job.ts
View File

@ -3,11 +3,11 @@ import { supabase_service } from "../supabase";
import { FirecrawlJob } from "../../types";
import { posthog } from "../posthog";
import "dotenv/config";
import { Logger } from "../../lib/logger";
export async function logJob(job: FirecrawlJob) {
try {
// Only log jobs in production
if (process.env.ENV !== "production") {
if (process.env.USE_DB_AUTHENTICATION === "false") {
return;
}
@ -25,6 +25,7 @@ export async function logJob(job: FirecrawlJob) {
.from("firecrawl_jobs")
.insert([
{
job_id: job.job_id ? job.job_id : null,
success: job.success,
message: job.message,
num_docs: job.num_docs,
@ -38,6 +39,7 @@ export async function logJob(job: FirecrawlJob) {
origin: job.origin,
extractor_options: job.extractor_options,
num_tokens: job.num_tokens,
retry: !!job.retry,
},
]);
@ -61,14 +63,15 @@ export async function logJob(job: FirecrawlJob) {
origin: job.origin,
extractor_options: job.extractor_options,
num_tokens: job.num_tokens,
retry: job.retry,
},
};
posthog.capture(phLog);
}
if (error) {
console.error("Error logging job:\n", error);
Logger.error(`Error logging job: ${error.message}`);
}
} catch (error) {
console.error("Error logging job:\n", error);
Logger.error(`Error logging job: ${error.message}`);
}
}

11
apps/api/src/services/logging/scrape_log.ts
View File

@ -2,11 +2,16 @@ import "dotenv/config";
import { ScrapeLog } from "../../types";
import { supabase_service } from "../supabase";
import { PageOptions } from "../../lib/entities";
import { Logger } from "../../lib/logger";
export async function logScrape(
scrapeLog: ScrapeLog,
pageOptions?: PageOptions
) {
if (process.env.USE_DB_AUTHENTICATION === "false") {
Logger.debug("Skipping logging scrape to Supabase");
return;
}
try {
// Only log jobs in production
// if (process.env.ENV !== "production") {
@ -32,16 +37,16 @@ export async function logScrape(
retried: scrapeLog.retried,
error_message: scrapeLog.error_message,
date_added: new Date().toISOString(),
html: scrapeLog.html,
html: "Removed to save db space",
ipv4_support: scrapeLog.ipv4_support,
ipv6_support: scrapeLog.ipv6_support,
},
]);
if (error) {
console.error("Error logging proxy:\n", error);
Logger.error(`Error logging proxy:\n${JSON.stringify(error)}`);
}
} catch (error) {
console.error("Error logging proxy:\n", error);
Logger.error(`Error logging proxy:\n${JSON.stringify(error)}`);
}
}

7
apps/api/src/services/logtail.ts
View File

@ -1,19 +1,20 @@
import { Logtail } from "@logtail/node";
import "dotenv/config";
import { Logger } from "../lib/logger";
// A mock Logtail class to handle cases where LOGTAIL_KEY is not provided
class MockLogtail {
info(message: string, context?: Record<string, any>): void {
console.log(message, context);
Logger.debug(`${message} - ${context}`);
}
error(message: string, context: Record<string, any> = {}): void {
console.error(message, context);
Logger.error(`${message} - ${context}`);
}
}
// Using the actual Logtail class if LOGTAIL_KEY exists, otherwise using the mock class
// Additionally, print a warning to the terminal if LOGTAIL_KEY is not provided
export const logtail = process.env.LOGTAIL_KEY ? new Logtail(process.env.LOGTAIL_KEY) : (() => {
console.warn("LOGTAIL_KEY is not provided - your events will not be logged. Using MockLogtail as a fallback. see logtail.ts for more.");
Logger.warn("LOGTAIL_KEY is not provided - your events will not be logged. Using MockLogtail as a fallback. see logtail.ts for more.");
return new MockLogtail();
})();

38
apps/api/src/services/notification/email_notification.ts
View File

@ -2,6 +2,7 @@ import { supabase_service } from "../supabase";
import { withAuth } from "../../lib/withAuth";
import { Resend } from "resend";
import { NotificationType } from "../../types";
import { Logger } from "../../../src/lib/logger";
const emailTemplates: Record<
NotificationType,
@ -52,11 +53,11 @@ async function sendEmailNotification(
});
if (error) {
console.error("Error sending email: ", error);
Logger.debug(`Error sending email: ${error}`);
return { success: false };
}
} catch (error) {
console.error("Error sending email (2): ", error);
Logger.debug(`Error sending email (2): ${error}`);
return { success: false };
}
}
@ -70,7 +71,28 @@ export async function sendNotificationInternal(
if (team_id === "preview") {
return { success: true };
}
const fifteenDaysAgo = new Date();
fifteenDaysAgo.setDate(fifteenDaysAgo.getDate() - 15);
const { data, error } = await supabase_service
.from("user_notifications")
.select("*")
.eq("team_id", team_id)
.eq("notification_type", notificationType)
.gte("sent_date", fifteenDaysAgo.toISOString());
if (error) {
Logger.debug(`Error fetching notifications: ${error}`);
return { success: false };
}
if (data.length !== 0) {
// Logger.debug(`Notification already sent for team_id: ${team_id} and notificationType: ${notificationType} in the last 15 days`);
return { success: false };
}
const { data: recentData, error: recentError } = await supabase_service
.from("user_notifications")
.select("*")
.eq("team_id", team_id)
@ -78,14 +100,16 @@ export async function sendNotificationInternal(
.gte("sent_date", startDateString)
.lte("sent_date", endDateString);
if (error) {
console.error("Error fetching notifications: ", error);
if (recentError) {
Logger.debug(`Error fetching recent notifications: ${recentError}`);
return { success: false };
}
if (data.length !== 0) {
if (recentData.length !== 0) {
// Logger.debug(`Notification already sent for team_id: ${team_id} and notificationType: ${notificationType} within the specified date range`);
return { success: false };
} else {
console.log(`Sending notification for team_id: ${team_id} and notificationType: ${notificationType}`);
// get the emails from the user with the team_id
const { data: emails, error: emailsError } = await supabase_service
.from("users")
@ -93,7 +117,7 @@ export async function sendNotificationInternal(
.eq("team_id", team_id);
if (emailsError) {
console.error("Error fetching emails: ", emailsError);
Logger.debug(`Error fetching emails: ${emailsError}`);
return { success: false };
}
@ -112,7 +136,7 @@ export async function sendNotificationInternal(
]);
if (insertError) {
console.error("Error inserting notification record: ", insertError);
Logger.debug(`Error inserting notification record: ${insertError}`);
return { success: false };
}

3
apps/api/src/services/posthog.ts
View File

@ -1,5 +1,6 @@
import { PostHog } from 'posthog-node';
import "dotenv/config";
import { Logger } from '../../src/lib/logger';
export default function PostHogClient() {
const posthogClient = new PostHog(process.env.POSTHOG_API_KEY, {
@ -19,7 +20,7 @@ class MockPostHog {
export const posthog = process.env.POSTHOG_API_KEY
? PostHogClient()
: (() => {
console.warn(
Logger.warn(
"POSTHOG_API_KEY is not provided - your events will not be logged. Using MockPostHog as a fallback. See posthog.ts for more."
);
return new MockPostHog();

12
apps/api/src/services/queue-service.ts
View File

@ -1,5 +1,6 @@
import Queue from "bull";
import { Queue as BullQueue } from "bull";
import { Logger } from "../lib/logger";
let webScraperQueue: BullQueue;
@ -7,11 +8,16 @@ export function getWebScraperQueue() {
if (!webScraperQueue) {
webScraperQueue = new Queue("web-scraper", process.env.REDIS_URL, {
settings: {
lockDuration: 2 * 60 * 60 * 1000, // 2 hours in milliseconds,
lockRenewTime: 30 * 60 * 1000, // 30 minutes in milliseconds
lockDuration: 1 * 60 * 1000, // 1 minute in milliseconds,
lockRenewTime: 15 * 1000, // 15 seconds in milliseconds
stalledInterval: 30 * 1000,
maxStalledCount: 10,
},
defaultJobOptions:{
attempts: 2
}
});
console.log("Web scraper queue created");
Logger.info("Web scraper queue created");
}
return webScraperQueue;
}

39
apps/api/src/services/queue-worker.ts
View File

@ -6,14 +6,21 @@ import { startWebScraperPipeline } from "../main/runWebScraper";
import { callWebhook } from "./webhook";
import { logJob } from "./logging/log_job";
import { initSDK } from '@hyperdx/node-opentelemetry';
import { Job } from "bull";
import { Logger } from "../lib/logger";
import { ScrapeEvents } from "../lib/scrape-events";
if (process.env.ENV === 'production') {
initSDK({ consoleCapture: true, additionalInstrumentations: []});
initSDK({
consoleCapture: true,
additionalInstrumentations: [],
});
}
getWebScraperQueue().process(
Math.floor(Number(process.env.NUM_WORKERS_PER_QUEUE ?? 8)),
async function (job, done) {
const wsq = getWebScraperQueue();
async function processJob(job: Job, done) {
Logger.info(`🐂 Worker taking job ${job.id}`);
try {
job.progress({
@ -41,6 +48,7 @@ getWebScraperQueue().process(
await callWebhook(job.data.team_id, job.id as string, data);
await logJob({
job_id: job.id as string,
success: success,
message: message,
num_docs: docs.length,
@ -53,11 +61,18 @@ getWebScraperQueue().process(
pageOptions: job.data.pageOptions,
origin: job.data.origin,
});
Logger.info(`🐂 Job done ${job.id}`);
done(null, data);
} catch (error) {
Logger.error(`🐂 Job errored ${job.id} - ${error}`);
if (await getWebScraperQueue().isPaused(false)) {
Logger.debug("🐂Queue is paused, ignoring");
return;
}
if (error instanceof CustomError) {
// Here we handle the error, then save the failed job
console.error(error.message); // or any other error handling
Logger.error(error.message); // or any other error handling
logtail.error("Custom error while ingesting", {
job_id: job.id,
@ -65,7 +80,7 @@ getWebScraperQueue().process(
dataIngestionJob: error.dataIngestionJob,
});
}
console.log(error);
Logger.error(error);
logtail.error("Overall error ingesting", {
job_id: job.id,
@ -80,6 +95,7 @@ getWebScraperQueue().process(
};
await callWebhook(job.data.team_id, job.id as string, data);
await logJob({
job_id: job.id as string,
success: false,
message: typeof error === 'string' ? error : (error.message ?? "Something went wrong... Contact help@mendable.ai"),
num_docs: 0,
@ -95,4 +111,15 @@ getWebScraperQueue().process(
done(null, data);
}
}
wsq.process(
Math.floor(Number(process.env.NUM_WORKERS_PER_QUEUE ?? 8)),
processJob
);
wsq.on("waiting", j => ScrapeEvents.logJobEvent(j, "waiting"));
wsq.on("active", j => ScrapeEvents.logJobEvent(j, "active"));
wsq.on("completed", j => ScrapeEvents.logJobEvent(j, "completed"));
wsq.on("paused", j => ScrapeEvents.logJobEvent(j, "paused"));
wsq.on("resumed", j => ScrapeEvents.logJobEvent(j, "resumed"));
wsq.on("removed", j => ScrapeEvents.logJobEvent(j, "removed"));

315
apps/api/src/services/rate-limiter.test.ts
View File

@ -1,48 +1,98 @@
import { getRateLimiter, serverRateLimiter, testSuiteRateLimiter, redisClient } from "./rate-limiter";
import {
getRateLimiter,
serverRateLimiter,
testSuiteRateLimiter,
redisRateLimitClient,
} from "./rate-limiter";
import { RateLimiterMode } from "../../src/types";
import { RateLimiterRedis } from "rate-limiter-flexible";
describe("Rate Limiter Service", () => {
beforeAll(async () => {
await redisClient.connect();
try {
await redisRateLimitClient.connect();
// if (process.env.REDIS_RATE_LIMIT_URL === "redis://localhost:6379") {
// console.log("Erasing all keys");
// // erase all the keys that start with "test-prefix"
// const keys = await redisRateLimitClient.keys("test-prefix:*");
// if (keys.length > 0) {
// await redisRateLimitClient.del(...keys);
// }
// }
} catch (error) {}
});
afterAll(async () => {
await redisClient.disconnect();
try {
// if (process.env.REDIS_RATE_LIMIT_URL === "redis://localhost:6379") {
await redisRateLimitClient.disconnect();
// }
} catch (error) {}
});
it("should return the testSuiteRateLimiter for specific tokens", () => {
const limiter = getRateLimiter("crawl" as RateLimiterMode, "a01ccae");
const limiter = getRateLimiter(
"crawl" as RateLimiterMode,
"test-prefix:a01ccae"
);
expect(limiter).toBe(testSuiteRateLimiter);
const limiter2 = getRateLimiter("scrape" as RateLimiterMode, "6254cf9");
const limiter2 = getRateLimiter(
"scrape" as RateLimiterMode,
"test-prefix:6254cf9"
);
expect(limiter2).toBe(testSuiteRateLimiter);
});
it("should return the serverRateLimiter if mode is not found", () => {
const limiter = getRateLimiter("nonexistent" as RateLimiterMode, "someToken");
const limiter = getRateLimiter(
"nonexistent" as RateLimiterMode,
"test-prefix:someToken"
);
expect(limiter).toBe(serverRateLimiter);
});
it("should return the correct rate limiter based on mode and plan", () => {
const limiter = getRateLimiter("crawl" as RateLimiterMode, "someToken", "free");
const limiter = getRateLimiter(
"crawl" as RateLimiterMode,
"test-prefix:someToken",
"free"
);
expect(limiter.points).toBe(2);
const limiter2 = getRateLimiter("scrape" as RateLimiterMode, "someToken", "standard");
const limiter2 = getRateLimiter(
"scrape" as RateLimiterMode,
"test-prefix:someToken",
"standard"
);
expect(limiter2.points).toBe(50);
const limiter3 = getRateLimiter("search" as RateLimiterMode, "someToken", "growth");
const limiter3 = getRateLimiter(
"search" as RateLimiterMode,
"test-prefix:someToken",
"growth"
);
expect(limiter3.points).toBe(500);
const limiter4 = getRateLimiter("crawlStatus" as RateLimiterMode, "someToken", "growth");
const limiter4 = getRateLimiter(
"crawlStatus" as RateLimiterMode,
"test-prefix:someToken",
"growth"
);
expect(limiter4.points).toBe(150);
});
it("should return the default rate limiter if plan is not provided", () => {
const limiter = getRateLimiter("crawl" as RateLimiterMode, "someToken");
const limiter = getRateLimiter(
"crawl" as RateLimiterMode,
"test-prefix:someToken"
);
expect(limiter.points).toBe(3);
const limiter2 = getRateLimiter("scrape" as RateLimiterMode, "someToken");
const limiter2 = getRateLimiter(
"scrape" as RateLimiterMode,
"test-prefix:someToken"
);
expect(limiter2.points).toBe(20);
});
@ -50,7 +100,7 @@ describe("Rate Limiter Service", () => {
const keyPrefix = "test-prefix";
const points = 10;
const limiter = new RateLimiterRedis({
storeClient: redisClient,
storeClient: redisRateLimitClient,
keyPrefix,
points,
duration: 60,
@ -62,26 +112,253 @@ describe("Rate Limiter Service", () => {
});
it("should return the correct rate limiter for 'preview' mode", () => {
const limiter = getRateLimiter("preview" as RateLimiterMode, "someToken", "free");
const limiter = getRateLimiter(
"preview" as RateLimiterMode,
"test-prefix:someToken",
"free"
);
expect(limiter.points).toBe(5);
const limiter2 = getRateLimiter("preview" as RateLimiterMode, "someToken");
const limiter2 = getRateLimiter(
"preview" as RateLimiterMode,
"test-prefix:someToken"
);
expect(limiter2.points).toBe(5);
});
it("should return the correct rate limiter for 'account' mode", () => {
const limiter = getRateLimiter("account" as RateLimiterMode, "someToken", "free");
const limiter = getRateLimiter(
"account" as RateLimiterMode,
"test-prefix:someToken",
"free"
);
expect(limiter.points).toBe(100);
const limiter2 = getRateLimiter("account" as RateLimiterMode, "someToken");
const limiter2 = getRateLimiter(
"account" as RateLimiterMode,
"test-prefix:someToken"
);
expect(limiter2.points).toBe(100);
});
it("should return the correct rate limiter for 'crawlStatus' mode", () => {
const limiter = getRateLimiter("crawlStatus" as RateLimiterMode, "someToken", "free");
const limiter = getRateLimiter(
"crawlStatus" as RateLimiterMode,
"test-prefix:someToken",
"free"
);
expect(limiter.points).toBe(150);
const limiter2 = getRateLimiter("crawlStatus" as RateLimiterMode, "someToken");
const limiter2 = getRateLimiter(
"crawlStatus" as RateLimiterMode,
"test-prefix:someToken"
);
expect(limiter2.points).toBe(150);
});
it("should consume points correctly for 'crawl' mode", async () => {
const limiter = getRateLimiter(
"crawl" as RateLimiterMode,
"test-prefix:someTokenCRAWL",
"free"
);
const consumePoints = 1;
const res = await limiter.consume(
"test-prefix:someTokenCRAWL",
consumePoints
);
expect(res.remainingPoints).toBe(1);
});
it("should consume points correctly for 'scrape' mode (DEFAULT)", async () => {
const limiter = getRateLimiter(
"scrape" as RateLimiterMode,
"test-prefix:someTokenX"
);
const consumePoints = 4;
const res = await limiter.consume("test-prefix:someTokenX", consumePoints);
expect(res.remainingPoints).toBe(16);
});
it("should consume points correctly for 'scrape' mode (HOBBY)", async () => {
const limiter = getRateLimiter(
"scrape" as RateLimiterMode,
"test-prefix:someTokenXY",
"hobby"
);
// expect hobby to have 100 points
expect(limiter.points).toBe(10);
const consumePoints = 5;
const res = await limiter.consume("test-prefix:someTokenXY", consumePoints);
expect(res.consumedPoints).toBe(5);
expect(res.remainingPoints).toBe(5);
});
it("should return the correct rate limiter for 'crawl' mode", () => {
const limiter = getRateLimiter(
"crawl" as RateLimiterMode,
"test-prefix:someToken",
"free"
);
expect(limiter.points).toBe(2);
const limiter2 = getRateLimiter(
"crawl" as RateLimiterMode,
"test-prefix:someToken",
"starter"
);
expect(limiter2.points).toBe(3);
const limiter3 = getRateLimiter(
"crawl" as RateLimiterMode,
"test-prefix:someToken",
"standard"
);
expect(limiter3.points).toBe(5);
});
it("should return the correct rate limiter for 'scrape' mode", () => {
const limiter = getRateLimiter(
"scrape" as RateLimiterMode,
"test-prefix:someToken",
"free"
);
expect(limiter.points).toBe(5);
const limiter2 = getRateLimiter(
"scrape" as RateLimiterMode,
"test-prefix:someToken",
"starter"
);
expect(limiter2.points).toBe(20);
const limiter3 = getRateLimiter(
"scrape" as RateLimiterMode,
"test-prefix:someToken",
"standard"
);
expect(limiter3.points).toBe(50);
});
it("should return the correct rate limiter for 'search' mode", () => {
const limiter = getRateLimiter(
"search" as RateLimiterMode,
"test-prefix:someToken",
"free"
);
expect(limiter.points).toBe(5);
const limiter2 = getRateLimiter(
"search" as RateLimiterMode,
"test-prefix:someToken",
"starter"
);
expect(limiter2.points).toBe(20);
const limiter3 = getRateLimiter(
"search" as RateLimiterMode,
"test-prefix:someToken",
"standard"
);
expect(limiter3.points).toBe(40);
});
it("should return the correct rate limiter for 'preview' mode", () => {
const limiter = getRateLimiter(
"preview" as RateLimiterMode,
"test-prefix:someToken",
"free"
);
expect(limiter.points).toBe(5);
const limiter2 = getRateLimiter(
"preview" as RateLimiterMode,
"test-prefix:someToken"
);
expect(limiter2.points).toBe(5);
});
it("should return the correct rate limiter for 'account' mode", () => {
const limiter = getRateLimiter(
"account" as RateLimiterMode,
"test-prefix:someToken",
"free"
);
expect(limiter.points).toBe(100);
const limiter2 = getRateLimiter(
"account" as RateLimiterMode,
"test-prefix:someToken"
);
expect(limiter2.points).toBe(100);
});
it("should return the correct rate limiter for 'crawlStatus' mode", () => {
const limiter = getRateLimiter(
"crawlStatus" as RateLimiterMode,
"test-prefix:someToken",
"free"
);
expect(limiter.points).toBe(150);
const limiter2 = getRateLimiter(
"crawlStatus" as RateLimiterMode,
"test-prefix:someToken"
);
expect(limiter2.points).toBe(150);
});
it("should return the correct rate limiter for 'testSuite' mode", () => {
const limiter = getRateLimiter(
"testSuite" as RateLimiterMode,
"test-prefix:someToken",
"free"
);
expect(limiter.points).toBe(10000);
const limiter2 = getRateLimiter(
"testSuite" as RateLimiterMode,
"test-prefix:someToken"
);
expect(limiter2.points).toBe(10000);
});
it("should throw an error when consuming more points than available", async () => {
const limiter = getRateLimiter(
"crawl" as RateLimiterMode,
"test-prefix:someToken"
);
const consumePoints = limiter.points + 1;
try {
await limiter.consume("test-prefix:someToken", consumePoints);
} catch (error) {
// expect remaining points to be 0
const res = await limiter.get("test-prefix:someToken");
expect(res.remainingPoints).toBe(0);
}
});
it("should reset points after duration", async () => {
const keyPrefix = "test-prefix";
const points = 10;
const duration = 1; // 1 second
const limiter = new RateLimiterRedis({
storeClient: redisRateLimitClient,
keyPrefix,
points,
duration,
});
const consumePoints = 5;
await limiter.consume("test-prefix:someToken", consumePoints);
await new Promise((resolve) => setTimeout(resolve, duration * 1000 + 100)); // Wait for duration + 100ms
const res = await limiter.consume("test-prefix:someToken", consumePoints);
expect(res.remainingPoints).toBe(points - consumePoints);
});
});

19
apps/api/src/services/rate-limiter.ts
View File

@ -1,6 +1,6 @@
import { RateLimiterRedis } from "rate-limiter-flexible";
import * as redis from "redis";
import { RateLimiterMode } from "../../src/types";
import Redis from "ioredis";
const RATE_LIMITS = {
crawl: {
@ -9,7 +9,7 @@ const RATE_LIMITS = {
starter: 3,
standard: 5,
standardOld: 40,
scale: 20,
scale: 50,
hobby: 3,
standardNew: 10,
standardnew: 10,
@ -21,7 +21,7 @@ const RATE_LIMITS = {
starter: 20,
standard: 50,
standardOld: 40,
scale: 50,
scale: 500,
hobby: 10,
standardNew: 50,
standardnew: 50,
@ -33,7 +33,7 @@ const RATE_LIMITS = {
starter: 20,
standard: 40,
standardOld: 40,
scale: 50,
scale: 500,
hobby: 10,
standardNew: 50,
standardnew: 50,
@ -57,14 +57,13 @@ const RATE_LIMITS = {
},
};
export const redisClient = redis.createClient({
url: process.env.REDIS_URL,
legacyMode: true,
});
export const redisRateLimitClient = new Redis(
process.env.REDIS_RATE_LIMIT_URL
)
const createRateLimiter = (keyPrefix, points) =>
new RateLimiterRedis({
storeClient: redisClient,
storeClient: redisRateLimitClient,
keyPrefix,
points,
duration: 60, // Duration in seconds
@ -76,7 +75,7 @@ export const serverRateLimiter = createRateLimiter(
);
export const testSuiteRateLimiter = new RateLimiterRedis({
storeClient: redisClient,
storeClient: redisRateLimitClient,
keyPrefix: "test-suite",
points: 10000,
duration: 60, // Duration in seconds

33
apps/api/src/services/redis.ts
View File

@ -1,32 +1,31 @@
import Redis from "ioredis";
// Initialize Redis client
const redis = new Redis(process.env.REDIS_URL);
import { redisRateLimitClient } from "./rate-limiter";
import { Logger } from "../lib/logger";
// Listen to 'error' events to the Redis connection
redis.on("error", (error) => {
redisRateLimitClient.on("error", (error) => {
try {
if (error.message === "ECONNRESET") {
console.log("Connection to Redis Session Store timed out.");
Logger.error("Connection to Redis Session Rate Limit Store timed out.");
} else if (error.message === "ECONNREFUSED") {
console.log("Connection to Redis Session Store refused!");
} else console.log(error);
Logger.error("Connection to Redis Session Rate Limit Store refused!");
} else Logger.error(error);
} catch (error) {}
});
// Listen to 'reconnecting' event to Redis
redis.on("reconnecting", (err) => {
redisRateLimitClient.on("reconnecting", (err) => {
try {
if (redis.status === "reconnecting")
console.log("Reconnecting to Redis Session Store...");
else console.log("Error reconnecting to Redis Session Store.");
if (redisRateLimitClient.status === "reconnecting")
Logger.info("Reconnecting to Redis Session Rate Limit Store...");
else Logger.error("Error reconnecting to Redis Session Rate Limit Store.");
} catch (error) {}
});
// Listen to the 'connect' event to Redis
redis.on("connect", (err) => {
redisRateLimitClient.on("connect", (err) => {
try {
if (!err) console.log("Connected to Redis Session Store!");
if (!err) Logger.info("Connected to Redis Session Rate Limit Store!");
} catch (error) {}
});
@ -38,9 +37,9 @@ redis.on("connect", (err) => {
*/
const setValue = async (key: string, value: string, expire?: number) => {
if (expire) {
await redis.set(key, value, "EX", expire);
await redisRateLimitClient.set(key, value, "EX", expire);
} else {
await redis.set(key, value);
await redisRateLimitClient.set(key, value);
}
};
@ -50,7 +49,7 @@ const setValue = async (key: string, value: string, expire?: number) => {
* @returns {Promise<string|null>} The value, if found, otherwise null.
*/
const getValue = async (key: string): Promise<string | null> => {
const value = await redis.get(key);
const value = await redisRateLimitClient.get(key);
return value;
};
@ -59,7 +58,7 @@ const getValue = async (key: string): Promise<string | null> => {
* @param {string} key The key to delete.
*/
const deleteKey = async (key: string) => {
await redis.del(key);
await redisRateLimitClient.del(key);
};
export { setValue, getValue, deleteKey };

29
apps/api/src/services/redlock.ts Normal file
View File

@ -0,0 +1,29 @@
import Redlock from "redlock";
import Client from "ioredis";
export const redlock = new Redlock(
// You should have one client for each independent redis node
// or cluster.
[new Client(process.env.REDIS_RATE_LIMIT_URL)],
{
// The expected clock drift; for more details see:
// http://redis.io/topics/distlock
driftFactor: 0.01, // multiplied by lock ttl to determine drift time
// The max number of times Redlock will attempt to lock a resource
// before erroring.
retryCount: 5,
// the time in ms between attempts
retryDelay: 100, // time in ms
// the max time in ms randomly added to retries
// to improve performance under high contention
// see https://www.awsarchitectureblog.com/2015/03/backoff.html
retryJitter: 200, // time in ms
// The minimum remaining time on a lock before an extension is automatically
// attempted with the `using` API.
automaticExtensionThreshold: 500, // time in ms
}
);

12
apps/api/src/services/supabase.ts
View File

@ -1,4 +1,5 @@
import { createClient, SupabaseClient } from "@supabase/supabase-js";
import { Logger } from "../lib/logger";
// SupabaseService class initializes the Supabase client conditionally based on environment variables.
class SupabaseService {
@ -10,13 +11,13 @@ class SupabaseService {
// Only initialize the Supabase client if both URL and Service Token are provided.
if (process.env.USE_DB_AUTHENTICATION === "false") {
// Warn the user that Authentication is disabled by setting the client to null
console.warn(
"\x1b[33mAuthentication is disabled. Supabase client will not be initialized.\x1b[0m"
Logger.warn(
"Authentication is disabled. Supabase client will not be initialized."
);
this.client = null;
} else if (!supabaseUrl || !supabaseServiceToken) {
console.error(
"\x1b[31mSupabase environment variables aren't configured correctly. Supabase client will not be initialized. Fix ENV configuration or disable DB authentication with USE_DB_AUTHENTICATION env variable\x1b[0m"
Logger.error(
"Supabase environment variables aren't configured correctly. Supabase client will not be initialized. Fix ENV configuration or disable DB authentication with USE_DB_AUTHENTICATION env variable"
);
} else {
this.client = createClient(supabaseUrl, supabaseServiceToken);
@ -38,9 +39,6 @@ export const supabase_service: SupabaseClient = new Proxy(
const client = target.getClient();
// If the Supabase client is not initialized, intercept property access to provide meaningful error feedback.
if (client === null) {
console.error(
"Attempted to access Supabase client when it's not configured."
);
return () => {
throw new Error("Supabase client is not configured.");
};

13
apps/api/src/services/webhook.ts
View File

@ -1,8 +1,9 @@
import { Logger } from "../../src/lib/logger";
import { supabase_service } from "./supabase";
export const callWebhook = async (teamId: string, jobId: string,data: any) => {
try {
const selfHostedUrl = process.env.SELF_HOSTED_WEBHOOK_URL;
const selfHostedUrl = process.env.SELF_HOSTED_WEBHOOK_URL?.replace("{{JOB_ID}}", jobId);
const useDbAuthentication = process.env.USE_DB_AUTHENTICATION === 'true';
let webhookUrl = selfHostedUrl;
@ -15,10 +16,7 @@ export const callWebhook = async (teamId: string, jobId: string,data: any) => {
.eq("team_id", teamId)
.limit(1);
if (error) {
console.error(
`Error fetching webhook URL for team ID: ${teamId}`,
error.message
);
Logger.error(`Error fetching webhook URL for team ID: ${teamId}, error: ${error.message}`);
return null;
}
@ -53,9 +51,6 @@ export const callWebhook = async (teamId: string, jobId: string,data: any) => {
}),
});
} catch (error) {
console.error(
`Error sending webhook for team ID: ${teamId}`,
error.message
);
Logger.debug(`Error sending webhook for team ID: ${teamId}, error: ${error.message}`);
}
};

2
apps/api/src/strings.ts
View File

@ -1,2 +1,4 @@
export const errorNoResults =
"No results found, please check the URL or contact us at help@mendable.ai to file a ticket.";
export const clientSideError = "client-side exception has occurred"

2
apps/api/src/types.ts
View File

@ -48,6 +48,7 @@ export interface RunWebScraperResult {
}
export interface FirecrawlJob {
job_id?: string;
success: boolean;
message: string;
num_docs: number;
@ -61,6 +62,7 @@ export interface FirecrawlJob {
origin: string;
extractor_options?: ExtractorOptions,
num_tokens?: number,
retry?: boolean,
}
export interface FirecrawlScrapeResponse {

25
apps/go-sdk/examples/.gitignore vendored Normal file
View File

@ -0,0 +1,25 @@
# If you prefer the allow list template instead of the deny list, see community template:
# https://github.com/github/gitignore/blob/main/community/Golang/Go.AllowList.gitignore
#
# Binaries for programs and plugins
*.exe
*.exe~
*.dll
*.so
*.dylib
# Test binary, built with `go test -c`
*.test
# Output of the go coverage tool, specifically when used with LiteIDE
*.out
# Dependency directories (remove the comment below to include it)
# vendor/
# Go workspace file
go.work
go.work.sum
# env file
.env

21
apps/go-sdk/examples/LICENSE Normal file
View File

@ -0,0 +1,21 @@
MIT License
Copyright (c) 2024 Mendable
Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal
in the Software without restriction, including without limitation the rights
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:
The above copyright notice and this permission notice shall be included in all
copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
SOFTWARE.

87
apps/go-sdk/examples/example.go Normal file
View File

@ -0,0 +1,87 @@
package main
import (
"encoding/json"
"fmt"
"log"
"github.com/google/uuid"
"github.com/mendableai/firecrawl-go"
)
func main() {
app, err := firecrawl.NewFirecrawlApp("fc-YOUR_API_KEY", "https://api.firecrawl.dev")
if err != nil {
log.Fatalf("Failed to create FirecrawlApp: %v", err)
}
// Scrape a website
scrapeResult, err := app.ScrapeURL("firecrawl.dev", nil)
if err != nil {
log.Fatalf("Failed to scrape URL: %v", err)
}
fmt.Println(scrapeResult.Markdown)
// Crawl a website
idempotencyKey := uuid.New().String() // optional idempotency key
crawlParams := map[string]any{
"crawlerOptions": map[string]any{
"excludes": []string{"blog/*"},
},
}
crawlResult, err := app.CrawlURL("mendable.ai", crawlParams, true, 2, idempotencyKey)
if err != nil {
log.Fatalf("Failed to crawl URL: %v", err)
}
jsonCrawlResult, err := json.MarshalIndent(crawlResult, "", " ")
if err != nil {
log.Fatalf("Failed to marshal crawl result: %v", err)
}
fmt.Println(string(jsonCrawlResult))
// LLM Extraction using JSON schema
jsonSchema := map[string]any{
"type": "object",
"properties": map[string]any{
"top": map[string]any{
"type": "array",
"items": map[string]any{
"type": "object",
"properties": map[string]any{
"title": map[string]string{"type": "string"},
"points": map[string]string{"type": "number"},
"by": map[string]string{"type": "string"},
"commentsURL": map[string]string{"type": "string"},
},
"required": []string{"title", "points", "by", "commentsURL"},
},
"minItems": 5,
"maxItems": 5,
"description": "Top 5 stories on Hacker News",
},
},
"required": []string{"top"},
}
llmExtractionParams := map[string]any{
"extractorOptions": firecrawl.ExtractorOptions{
ExtractionSchema: jsonSchema,
Mode: "llm-extraction",
},
"pageOptions": map[string]any{
"onlyMainContent": true,
},
}
llmExtractionResult, err := app.ScrapeURL("https://news.ycombinator.com", llmExtractionParams)
if err != nil {
log.Fatalf("Failed to perform LLM extraction: %v", err)
}
// Pretty print the LLM extraction result
jsonResult, err := json.MarshalIndent(llmExtractionResult.LLMExtraction, "", " ")
if err != nil {
log.Fatalf("Failed to marshal LLM extraction result: %v", err)
}
fmt.Println(string(jsonResult))
}

9
apps/go-sdk/examples/go.mod Normal file
View File

@ -0,0 +1,9 @@
module github.com/mendableai/firecrawl-go-examples
go 1.22.5
replace github.com/mendableai/firecrawl => ../
require github.com/google/uuid v1.6.0
require github.com/mendableai/firecrawl-go v0.0.0-20240813205613-366e8d8dcf46 // indirect

14
apps/go-sdk/examples/go.sum Normal file
View File

@ -0,0 +1,14 @@
github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c=
github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
github.com/google/uuid v1.6.0 h1:NIvaJDMOsjHA8n1jAhLSgzrAzy1Hgr+hNrb57e+94F0=
github.com/google/uuid v1.6.0/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
github.com/joho/godotenv v1.5.1 h1:7eLL/+HRGLY0ldzfGMeQkb7vMd0as4CfYvUVzLqw0N0=
github.com/joho/godotenv v1.5.1/go.mod h1:f4LDr5Voq0i2e/R5DDNOoa2zzDfwtkZa6DnEwAbqwq4=
github.com/mendableai/firecrawl-go v0.0.0-20240813205613-366e8d8dcf46 h1:461um7fbSQYj2E3ETl8GINuRg5MTY3BdjMnogwUIhBs=
github.com/mendableai/firecrawl-go v0.0.0-20240813205613-366e8d8dcf46/go.mod h1:mTGbJ37fy43aaqonp/tdpzCH516jHFw/XVvfFi4QXHo=
github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM=
github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
github.com/stretchr/testify v1.9.0 h1:HtqpIVDClZ4nwg75+f6Lvsy/wHu+3BoSGCbBAcpTsTg=
github.com/stretchr/testify v1.9.0/go.mod h1:r2ic/lqez/lEtzL7wO/rwa5dbSLXVDPFyf8C91i36aY=
gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA=
gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=

2
apps/go-sdk/firecrawl/.env.example Normal file
View File

@ -0,0 +1,2 @@
API_URL=http://localhost:3002
TEST_API_KEY=fc-YOUR-API-KEY

2
apps/go-sdk/firecrawl/.gitignore vendored Normal file
View File

@ -0,0 +1,2 @@
.env
vendor

21
apps/go-sdk/firecrawl/LICENSE Normal file
View File

@ -0,0 +1,21 @@
MIT License
Copyright (c) 2024 Sideguide Technologies Inc.
Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal
in the Software without restriction, including without limitation the rights
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:
The above copyright notice and this permission notice shall be included in all
copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
SOFTWARE.

189
apps/go-sdk/firecrawl/README.md Normal file
View File

@ -0,0 +1,189 @@
# Firecrawl Go SDK
The Firecrawl Go SDK is a library that allows you to easily scrape and crawl websites, and output the data in a format ready for use with language models (LLMs). It provides a simple and intuitive interface for interacting with the Firecrawl API.
## Installation
To install the Firecrawl Go SDK, you can
```bash
go get github.com/mendableai/firecrawl
```
## Usage
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.
Here's an example of how to use the SDK with error handling:
```go
import (
"fmt"
"log"
"github.com/mendableai/firecrawl/firecrawl"
)
func main() {
// Initialize the FirecrawlApp with your API key
app, err := firecrawl.NewFirecrawlApp("YOUR_API_KEY")
if err != nil {
log.Fatalf("Failed to initialize FirecrawlApp: %v", err)
}
// Scrape a single URL
url := "https://mendable.ai"
scrapedData, err := app.ScrapeURL(url, nil)
if err != nil {
log.Fatalf("Error occurred while scraping: %v", err)
}
fmt.Println(scrapedData)
// Crawl a website
crawlUrl := "https://mendable.ai"
params := map[string]any{
"pageOptions": map[string]any{
"onlyMainContent": true,
},
}
crawlResult, err := app.CrawlURL(crawlUrl, params)
if err != nil {
log.Fatalf("Error occurred while crawling: %v", err)
}
fmt.Println(crawlResult)
}
```
### 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.
```go
url := "https://mendable.ai"
scrapedData, err := app.ScrapeURL(url, nil)
if err != nil {
log.Fatalf("Failed to scrape URL: %v", err)
}
fmt.Println(scrapedData)
```
### Extracting structured data from a URL
With LLM extraction, you can easily extract structured data from any URL. Here is how you to use it:
```go
jsonSchema := map[string]any{
"type": "object",
"properties": map[string]any{
"top": map[string]any{
"type": "array",
"items": map[string]any{
"type": "object",
"properties": map[string]any{
"title": map[string]string{"type": "string"},
"points": map[string]string{"type": "number"},
"by": map[string]string{"type": "string"},
"commentsURL": map[string]string{"type": "string"},
},
"required": []string{"title", "points", "by", "commentsURL"},
},
"minItems": 5,
"maxItems": 5,
"description": "Top 5 stories on Hacker News",
},
},
"required": []string{"top"},
}
llmExtractionParams := map[string]any{
"extractorOptions": firecrawl.ExtractorOptions{
ExtractionSchema: jsonSchema,
},
}
scrapeResult, err := app.ScrapeURL("https://news.ycombinator.com", llmExtractionParams)
if err != nil {
log.Fatalf("Failed to perform LLM extraction: %v", err)
}
fmt.Println(scrapeResult)
```
### Search for a query
To search the web, get the most relevant results, scrap each page and return the markdown, use the `Search` method. The method takes the query as a parameter and returns the search results.
```go
query := "what is mendable?"
searchResult, err := app.Search(query)
if err != nil {
log.Fatalf("Failed to search: %v", err)
}
fmt.Println(searchResult)
```
### Crawling a Website
To crawl a website, 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.
```go
crawlParams := map[string]any{
"crawlerOptions": map[string]any{
"excludes": []string{"blog/*"},
"includes": []string{}, // leave empty for all pages
"limit": 1000,
},
"pageOptions": map[string]any{
"onlyMainContent": true,
},
}
crawlResult, err := app.CrawlURL("mendable.ai", crawlParams, true, 2, idempotencyKey)
if err != nil {
log.Fatalf("Failed to crawl URL: %v", err)
}
fmt.Println(crawlResult)
```
### Checking Crawl Status
To check the status of a crawl job, use the `CheckCrawlStatus` method. It takes the job ID as a parameter and returns the current status of the crawl job.
```go
status, err := app.CheckCrawlStatus(jobId)
if err != nil {
log.Fatalf("Failed to check crawl status: %v", err)
}
fmt.Println(status)
```
### Canceling a Crawl Job
To cancel a crawl job, use the `CancelCrawlJob` method. It takes the job ID as a parameter and returns the cancellation status of the crawl job.
```go
canceled, err := app.CancelCrawlJob(jobId)
if err != nil {
log.Fatalf("Failed to cancel crawl job: %v", err)
}
fmt.Println(canceled)
```
## Error Handling
The SDK handles errors returned by the Firecrawl API and raises appropriate exceptions. If an error occurs during a request, an exception will be raised with a descriptive error message.
## Contributing
Contributions to the Firecrawl Go SDK are welcome! If you find any issues or have suggestions for improvements, please open an issue or submit a pull request on the GitHub repository.
## License
The Firecrawl Go SDK is licensed under the MIT License. This means you are free to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the SDK, subject to the following conditions:
- The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
Please note that while this SDK is MIT licensed, it is part of a larger project which may be under different licensing terms. Always refer to the license information in the root directory of the main project for overall licensing details.

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