From ee282c3d5537f87ee81f84cf6ea6999c422268c0 Mon Sep 17 00:00:00 2001
From: rafaelsideguide <150964962+rafaelsideguide@users.noreply.github.com>
Date: Tue, 11 Jun 2024 15:24:39 -0300
Subject: [PATCH] Added allowBackwardCrawling option

---
 apps/api/src/controllers/crawl.ts          |  8 +++-----
 apps/api/src/lib/entities.ts               |  1 +
 apps/api/src/scraper/WebScraper/crawler.ts | 12 +++++++++++-
 apps/api/src/scraper/WebScraper/index.ts   |  4 +++-
 4 files changed, 18 insertions(+), 7 deletions(-)

diff --git a/apps/api/src/controllers/crawl.ts b/apps/api/src/controllers/crawl.ts
index 5345b4f1..55c3a2ea 100644
--- a/apps/api/src/controllers/crawl.ts
+++ b/apps/api/src/controllers/crawl.ts
@@ -55,7 +55,7 @@ export async function crawlController(req: Request, res: Response) {
     }
 
     const mode = req.body.mode ?? "crawl";
-    const crawlerOptions = req.body.crawlerOptions ?? {};
+    const crawlerOptions = req.body.crawlerOptions ?? { allowBackwardCrawling: false, returnOnlyUrls: true };
     const pageOptions = req.body.pageOptions ?? { onlyMainContent: false, includeHtml: false };
 
     if (mode === "single_urls" && !url.includes(",")) {
@@ -64,9 +64,7 @@ export async function crawlController(req: Request, res: Response) {
         await a.setOptions({
           mode: "single_urls",
           urls: [url],
-          crawlerOptions: {
-            returnOnlyUrls: true,
-          },
+          crawlerOptions: crawlerOptions,
           pageOptions: pageOptions,
         });
 
@@ -91,7 +89,7 @@ export async function crawlController(req: Request, res: Response) {
     const job = await addWebScraperJob({
       url: url,
       mode: mode ?? "crawl", // fix for single urls not working
-      crawlerOptions: { ...crawlerOptions },
+      crawlerOptions: crawlerOptions,
       team_id: team_id,
       pageOptions: pageOptions,
       origin: req.body.origin ?? "api",
diff --git a/apps/api/src/lib/entities.ts b/apps/api/src/lib/entities.ts
index 744c07be..facc81e6 100644
--- a/apps/api/src/lib/entities.ts
+++ b/apps/api/src/lib/entities.ts
@@ -46,6 +46,7 @@ export type CrawlerOptions = {
   replaceAllPathsWithAbsolutePaths?: boolean;
   ignoreSitemap?: boolean;
   mode?: "default" | "fast"; // have a mode of some sort
+  allowBackwardCrawling?: boolean;
 }
 
 export type WebScraperOptions = {
diff --git a/apps/api/src/scraper/WebScraper/crawler.ts b/apps/api/src/scraper/WebScraper/crawler.ts
index fc95e7ca..77209917 100644
--- a/apps/api/src/scraper/WebScraper/crawler.ts
+++ b/apps/api/src/scraper/WebScraper/crawler.ts
@@ -20,6 +20,7 @@ export class WebCrawler {
   private robotsTxtUrl: string;
   private robots: any;
   private generateImgAltText: boolean;
+  private allowBackwardCrawling: boolean;
 
   constructor({
     initialUrl,
@@ -29,6 +30,7 @@ export class WebCrawler {
     limit = 10000,
     generateImgAltText = false,
     maxCrawledDepth = 10,
+    allowBackwardCrawling = false
   }: {
     initialUrl: string;
     includes?: string[];
@@ -37,6 +39,7 @@ export class WebCrawler {
     limit?: number;
     generateImgAltText?: boolean;
     maxCrawledDepth?: number;
+    allowBackwardCrawling?: boolean;
   }) {
     this.initialUrl = initialUrl;
     this.baseUrl = new URL(initialUrl).origin;
@@ -49,6 +52,7 @@ export class WebCrawler {
     this.maxCrawledLinks = maxCrawledLinks ?? limit;
     this.maxCrawledDepth = maxCrawledDepth ?? 10;
     this.generateImgAltText = generateImgAltText ?? false;
+    this.allowBackwardCrawling = allowBackwardCrawling ?? false;
   }
 
   private filterLinks(sitemapLinks: string[], limit: number, maxDepth: number): string[] {
@@ -90,10 +94,16 @@ export class WebCrawler {
         const linkHostname = normalizedLink.hostname.replace(/^www\./, '');
 
         // Ensure the protocol and hostname match, and the path starts with the initial URL's path
-        if (linkHostname !== initialHostname || !normalizedLink.pathname.startsWith(normalizedInitialUrl.pathname)) {
+        if (linkHostname !== initialHostname) {
           return false;
         }
 
+        if (!this.allowBackwardCrawling) {
+          if (!normalizedLink.pathname.startsWith(normalizedInitialUrl.pathname)) {
+            return false;
+          }
+        }
+
         const isAllowed = this.robots.isAllowed(link, "FireCrawlAgent") ?? true;
         // Check if the link is disallowed by robots.txt
         if (!isAllowed) {
diff --git a/apps/api/src/scraper/WebScraper/index.ts b/apps/api/src/scraper/WebScraper/index.ts
index 7dcd1751..53443202 100644
--- a/apps/api/src/scraper/WebScraper/index.ts
+++ b/apps/api/src/scraper/WebScraper/index.ts
@@ -38,8 +38,8 @@ export class WebScraperDataProvider {
   private generateImgAltTextModel: "gpt-4-turbo" | "claude-3-opus" =
     "gpt-4-turbo";
   private crawlerMode: string = "default";
+  private allowBackwardCrawling: boolean = false;
 
-  
   authorize(): void {
     throw new Error("Method not implemented.");
   }
@@ -171,6 +171,7 @@ export class WebScraperDataProvider {
       maxCrawledDepth: this.maxCrawledDepth,
       limit: this.limit,
       generateImgAltText: this.generateImgAltText,
+      allowBackwardCrawling: this.allowBackwardCrawling,
     });
 
     let links = await crawler.start(
@@ -480,6 +481,7 @@ export class WebScraperDataProvider {
     this.excludes = this.excludes.filter((item) => item !== "");
     this.crawlerMode = options.crawlerOptions?.mode ?? "default";
     this.ignoreSitemap = options.crawlerOptions?.ignoreSitemap ?? false;
+    this.allowBackwardCrawling = options.crawlerOptions?.allowBackwardCrawling ?? false;
 
     // make sure all urls start with https://
     this.urls = this.urls.map((url) => {