Merge branch 'main' into nsc/rate-limiter-tests

apps/api/src/__tests__/e2e_withAuth/index.test.ts

@@ -619,12 +619,13 @@ describe("E2E Tests for API Routes", () => {
     }, 180000);
 
     it.concurrent("should return a successful response with relative max depth option for a valid crawl job with maxDepths equals to zero", async () => {
+      
       const crawlResponse = await request(TEST_URL)
         .post("/v0/crawl")
         .set("Authorization", `Bearer ${process.env.TEST_API_KEY}`)
         .set("Content-Type", "application/json")
         .send({
-          url: "https://www.scrapethissite.com",
+          url: "https://www.mendable.ai",
           crawlerOptions: { maxDepth: 0 },
         });
       expect(crawlResponse.statusCode).toBe(200);
@@ -651,6 +652,11 @@ describe("E2E Tests for API Routes", () => {
         .get(`/v0/crawl/status/${crawlResponse.body.jobId}`)
         .set("Authorization", `Bearer ${process.env.TEST_API_KEY}`);
 
+        const testurls = completedResponse.body.data.map(
+          (item: any) => item.metadata?.sourceURL
+        );
+        //console.log(testurls)
+
       expect(completedResponse.statusCode).toBe(200);
       expect(completedResponse.body).toHaveProperty("status");
       expect(completedResponse.body.status).toBe("completed");
@@ -671,58 +677,9 @@ describe("E2E Tests for API Routes", () => {
       });
     }, 180000);
 
-    it.concurrent("should return a successful response with relative max depth option for a valid crawl job with maxDepth equals to 2", async () => {
-      const crawlResponse = await request(TEST_URL)
-        .post("/v0/crawl")
-        .set("Authorization", `Bearer ${process.env.TEST_API_KEY}`)
-        .set("Content-Type", "application/json")
-        .send({
-          url: "proxyway.com",
-          crawlerOptions: { maxDepth: 2, limit: 5 },
-        });
-      expect(crawlResponse.statusCode).toBe(200);
 
-      const response = await request(TEST_URL)
-        .get(`/v0/crawl/status/${crawlResponse.body.jobId}`)
-        .set("Authorization", `Bearer ${process.env.TEST_API_KEY}`);
-      expect(response.statusCode).toBe(200);
-      expect(response.body).toHaveProperty("status");
-      expect(["active", "waiting"]).toContain(response.body.status);
-      // wait for 60 seconds
-      let isCompleted = false;
-      while (!isCompleted) {
-        const statusCheckResponse = await request(TEST_URL)
-          .get(`/v0/crawl/status/${crawlResponse.body.jobId}`)
-          .set("Authorization", `Bearer ${process.env.TEST_API_KEY}`);
-        expect(statusCheckResponse.statusCode).toBe(200);
-        isCompleted = statusCheckResponse.body.status === "completed";
-        if (!isCompleted) {
-          await new Promise((resolve) => setTimeout(resolve, 1000)); // Wait for 1 second before checking again
-        }
-      }
-      const completedResponse = await request(TEST_URL)
-        .get(`/v0/crawl/status/${crawlResponse.body.jobId}`)
-        .set("Authorization", `Bearer ${process.env.TEST_API_KEY}`);
 
-      expect(completedResponse.statusCode).toBe(200);
-      expect(completedResponse.body).toHaveProperty("status");
-      expect(completedResponse.body.status).toBe("completed");
-      expect(completedResponse.body).toHaveProperty("data");
-      expect(completedResponse.body.data[0]).toHaveProperty("content");
-      expect(completedResponse.body.data[0]).toHaveProperty("markdown");
-      expect(completedResponse.body.data[0]).toHaveProperty("metadata");
-      const urls = completedResponse.body.data.map(
-        (item: any) => item.metadata?.sourceURL
-      );
-      expect(urls.length).toBeGreaterThanOrEqual(1);
-
-      // Check if all URLs have an absolute maximum depth of 3 after the base URL depth was 2 and the maxDepth was 1
-      urls.forEach((url: string) => {
-        const pathSplits = new URL(url).pathname.split('/');
-        const depth = pathSplits.length - (pathSplits[0].length === 0 && pathSplits[pathSplits.length - 1].length === 0 ? 1 : 0);
-        expect(depth).toBeLessThanOrEqual(3);
-      });
-    }, 180000);
+    
 
     // it.concurrent("should return a successful response with a valid API key and valid limit option", async () => {
     //   const crawlResponse = await request(TEST_URL)
@@ -1009,54 +966,6 @@ describe("E2E Tests for API Routes", () => {
     }, 180000); // 120 seconds
 
 
-    it.concurrent("should return a successful response with max depth option for a valid crawl job", async () => {
-      const crawlResponse = await request(TEST_URL)
-        .post("/v0/crawl")
-        .set("Authorization", `Bearer ${process.env.TEST_API_KEY}`)
-        .set("Content-Type", "application/json")
-        .send({
-          url: "https://www.scrapethissite.com",
-          crawlerOptions: { maxDepth: 1 },
-        });
-      expect(crawlResponse.statusCode).toBe(200);
-
-      let isCompleted = false;
-      let completedResponse;
-
-      while (!isCompleted) {
-        const response = await request(TEST_URL)
-          .get(`/v0/crawl/status/${crawlResponse.body.jobId}`)
-          .set("Authorization", `Bearer ${process.env.TEST_API_KEY}`);
-        expect(response.statusCode).toBe(200);
-        expect(response.body).toHaveProperty("status");
-
-        if (response.body.status === "completed") {
-          isCompleted = true;
-          completedResponse = response;
-        }
-      }
-      expect(completedResponse.statusCode).toBe(200);
-      expect(completedResponse.body).toHaveProperty("status");
-      expect(completedResponse.body.status).toBe("completed");
-      expect(completedResponse.body).toHaveProperty("data");
-      expect(completedResponse.body.data[0]).toHaveProperty("content");
-      expect(completedResponse.body.data[0]).toHaveProperty("markdown");
-      expect(completedResponse.body.data[0]).toHaveProperty("metadata");
-      expect(completedResponse.body.data[0].metadata.pageStatusCode).toBe(200);
-      expect(completedResponse.body.data[0].metadata.pageError).toBeUndefined();
-
-      const urls = completedResponse.body.data.map(
-        (item: any) => item.metadata?.sourceURL
-      );
-      expect(urls.length).toBeGreaterThan(1);
-
-      // Check if all URLs have a maximum depth of 1
-      urls.forEach((url) => {
-        const pathSplits = new URL(url).pathname.split('/');
-        const depth = pathSplits.length - (pathSplits[0].length === 0 && pathSplits[pathSplits.length - 1].length === 0 ? 1 : 0);
-        expect(depth).toBeLessThanOrEqual(2);
-      });
-    }, 180000);
 
     it.concurrent("should return a successful response for a valid crawl job with includeHtml set to true option (2)", async () => {
       const crawlResponse = await request(TEST_URL)

apps/api/src/scraper/WebScraper/__tests__/crawler.test.ts

@@ -0,0 +1,163 @@
+// crawler.test.ts
+import { WebCrawler } from '../crawler';
+import axios from 'axios';
+import robotsParser from 'robots-parser';
+import { getAdjustedMaxDepth } from '../utils/maxDepthUtils';
+
+jest.mock('axios');
+jest.mock('robots-parser');
+
+describe('WebCrawler maxDepth and filterLinks', () => {
+  let crawler: WebCrawler;
+  const mockAxios = axios as jest.Mocked<typeof axios>;
+  const mockRobotsParser = robotsParser as jest.MockedFunction<typeof robotsParser>;
+
+  let maxCrawledDepth: number;
+
+  beforeEach(() => {
+    // Setup default mocks
+    mockAxios.get.mockImplementation((url) => {
+      if (url.includes('robots.txt')) {
+        return Promise.resolve({ data: 'User-agent: *\nAllow: /' });
+      } else if (url.includes('sitemap.xml')) {
+        return Promise.resolve({ data: 'sitemap content' }); // You would normally parse this to URLs
+      }
+      return Promise.resolve({ data: '<html></html>' });
+    });
+
+    mockRobotsParser.mockReturnValue({
+      isAllowed: jest.fn().mockReturnValue(true),
+      isDisallowed: jest.fn().mockReturnValue(false),
+      getMatchingLineNumber: jest.fn().mockReturnValue(0),
+      getCrawlDelay: jest.fn().mockReturnValue(0),
+      getSitemaps: jest.fn().mockReturnValue([]),
+      getPreferredHost: jest.fn().mockReturnValue('example.com')
+    });
+  });
+
+  it('should filter out links that exceed maxDepth param of 2 based on enterURL depth of 0 ', async () => {
+    const initialUrl = 'http://example.com'; // Set initial URL for this test
+    const enteredMaxCrawledDepth = 2;
+    maxCrawledDepth = getAdjustedMaxDepth(initialUrl, enteredMaxCrawledDepth);
+
+
+    crawler = new WebCrawler({
+      initialUrl: initialUrl,
+      includes: [],
+      excludes: [],
+      limit: 100,
+      maxCrawledDepth: maxCrawledDepth, // Set maxDepth for testing
+    });
+
+    // Mock sitemap fetching function to return controlled links
+    crawler['tryFetchSitemapLinks'] = jest.fn().mockResolvedValue([
+      initialUrl, // depth 0
+      initialUrl + '/page1', // depth 1
+      initialUrl + '/page1/page2', // depth 2
+      initialUrl + '/page1/page2/page3' // depth 3, should be filtered out
+    ]);
+
+    const results = await crawler.start(undefined, undefined, undefined, undefined, undefined, maxCrawledDepth);
+    expect(results).toEqual([
+      { url: initialUrl, html: '' },
+      { url: initialUrl + '/page1', html: '' },
+      { url: initialUrl + '/page1/page2', html: '' }
+    ]);
+
+
+    // Ensure that the link with depth 3 is not included
+    expect(results.some(r => r.url === initialUrl + '/page1/page2/page3')).toBe(false);
+  });
+
+  it('should filter out links that exceed maxDepth param of 0 based on enterURL depth of 0 ', async () => {
+    const initialUrl = 'http://example.com'; // Set initial URL for this test
+    const enteredMaxCrawledDepth = 0;
+    maxCrawledDepth = getAdjustedMaxDepth(initialUrl, enteredMaxCrawledDepth);
+   
+
+    crawler = new WebCrawler({
+      initialUrl: initialUrl,
+      includes: [],
+      excludes: [],
+      limit: 100,
+      maxCrawledDepth: maxCrawledDepth, // Set maxDepth for testing
+    });
+
+    // Mock sitemap fetching function to return controlled links
+    crawler['tryFetchSitemapLinks'] = jest.fn().mockResolvedValue([
+      initialUrl, // depth 0
+      initialUrl + '/page1', // depth 1
+      initialUrl + '/page1/page2', // depth 2
+      initialUrl + '/page1/page2/page3' // depth 3, should be filtered out
+    ]);
+
+    const results = await crawler.start(undefined, undefined, undefined, undefined, undefined, maxCrawledDepth);
+    expect(results).toEqual([
+      { url: initialUrl, html: '' },
+    ]);  
+  });
+
+  it('should filter out links that exceed maxDepth param of 1 based on enterURL depth of 1 ', async () => {
+    const initialUrl = 'http://example.com/page1'; // Set initial URL for this test
+    const enteredMaxCrawledDepth = 1;
+    maxCrawledDepth = getAdjustedMaxDepth(initialUrl, enteredMaxCrawledDepth);
+  
+
+    crawler = new WebCrawler({
+      initialUrl: initialUrl,
+      includes: [],
+      excludes: [],
+      limit: 100,
+      maxCrawledDepth: maxCrawledDepth, // Set maxDepth for testing
+    });
+
+    // Mock sitemap fetching function to return controlled links
+    crawler['tryFetchSitemapLinks'] = jest.fn().mockResolvedValue([
+      initialUrl, // depth 0
+      initialUrl + '/page2', // depth 1
+      initialUrl + '/page2/page3', // depth 2
+      initialUrl + '/page2/page3/page4' // depth 3, should be filtered out
+    ]);
+
+    const results = await crawler.start(undefined, undefined, undefined, undefined, undefined, maxCrawledDepth);
+    expect(results).toEqual([
+      { url: initialUrl, html: '' },
+      { url: initialUrl + '/page2', html: '' }
+    ]);
+  });
+
+  it('should filter out links that exceed maxDepth param of 1 based on enterURL depth of 2 ', async () => {
+    const initialUrl = 'http://example.com/page1'; // Set initial URL for this test
+    const enteredMaxCrawledDepth = 2;
+    maxCrawledDepth = getAdjustedMaxDepth(initialUrl, enteredMaxCrawledDepth);
+ 
+
+    crawler = new WebCrawler({
+      initialUrl: initialUrl,
+      includes: [],
+      excludes: [],
+      limit: 100,
+      maxCrawledDepth: maxCrawledDepth, // Set maxDepth for testing
+    });
+
+    // Mock sitemap fetching function to return controlled links
+    crawler['tryFetchSitemapLinks'] = jest.fn().mockResolvedValue([
+      initialUrl, // depth 0
+      initialUrl + '/page2', // depth 1
+      initialUrl + '/page2/page3', // depth 2
+      initialUrl + '/page2/page3/page4' // depth 3, should be filtered out
+    ]);
+
+    const results = await crawler.start(undefined, undefined, undefined, undefined, undefined, maxCrawledDepth);
+    expect(results).toEqual([
+      { url: initialUrl, html: '' },
+      { url: initialUrl + '/page2', html: '' },
+      { url: initialUrl + '/page2/page3', html: '' }
+    ]);   
+  });
+
+
+
+  // Add more tests to cover other scenarios, such as checking includes and excludes
+});
+

apps/api/src/scraper/WebScraper/crawler.ts

@@ -6,6 +6,7 @@ import async from "async";
 import { CrawlerOptions, PageOptions, Progress } from "../../lib/entities";
 import { scrapSingleUrl, scrapWithScrapingBee } from "./single_url";
 import robotsParser from "robots-parser";
+import { getURLDepth } from "./utils/maxDepthUtils";
 
 export class WebCrawler {
   private initialUrl: string;
@@ -60,8 +61,10 @@ export class WebCrawler {
       .filter((link) => {
         const url = new URL(link);
         const path = url.pathname;
-        const depth = url.pathname.split('/').length - 1;
+        
+        const depth = getURLDepth(url.toString());
 
+        
         // Check if the link exceeds the maximum depth allowed
         if (depth > maxDepth) {
           return false;
@@ -136,8 +139,10 @@ export class WebCrawler {
 
     if(!crawlerOptions?.ignoreSitemap){
       const sitemapLinks = await this.tryFetchSitemapLinks(this.initialUrl);
+    
       if (sitemapLinks.length > 0) {
         let filteredLinks = this.filterLinks(sitemapLinks, limit, maxDepth);
+       
         return filteredLinks.map(link => ({ url: link, html: "" }));
       }
     }
@@ -148,6 +153,7 @@ export class WebCrawler {
       concurrencyLimit,
       inProgress
     );
+   
     
     if (
       urls.length === 0 &&
@@ -224,11 +230,10 @@ export class WebCrawler {
   }
 
   async crawl(url: string, pageOptions: PageOptions): Promise<{url: string, html: string, pageStatusCode?: number, pageError?: string}[]> {
-    const normalizedUrl = this.normalizeCrawlUrl(url);
-    if (this.visited.has(normalizedUrl) || !this.robots.isAllowed(url, "FireCrawlAgent")) {
+    if (this.visited.has(url) || !this.robots.isAllowed(url, "FireCrawlAgent")) {
       return [];
     }
-    this.visited.add(normalizedUrl);
+    this.visited.add(url);
 
     if (!url.startsWith("http")) {
       url = "https://" + url;
@@ -276,15 +281,16 @@ export class WebCrawler {
           const urlObj = new URL(fullUrl);
           const path = urlObj.pathname;
 
+
           if (
             this.isInternalLink(fullUrl) &&
-            this.matchesPattern(fullUrl) &&
             this.noSections(fullUrl) &&
             // The idea here to comment this out is to allow wider website coverage as we filter this anyway afterwards
             // this.matchesIncludes(path) &&
             !this.matchesExcludes(path) &&
-            this.robots.isAllowed(fullUrl, "FireCrawlAgent")
+            this.isRobotsAllowed(fullUrl)
           ) {
+
             links.push({ url: fullUrl, html: content, pageStatusCode, pageError });
           }
         }
@@ -294,12 +300,15 @@ export class WebCrawler {
         return links;
       }
       // Create a new list to return to avoid modifying the visited list
-      return links.filter((link) => !this.visited.has(this.normalizeCrawlUrl(link.url)));
+      return links.filter((link) => !this.visited.has(link.url));
     } catch (error) {
       return [];
     }
   }
 
+  private isRobotsAllowed(url: string): boolean {
+    return (this.robots ? (this.robots.isAllowed(url, "FireCrawlAgent") ?? true) : true)
+  }
   private normalizeCrawlUrl(url: string): string {
     try{
       const urlObj = new URL(url);
@@ -326,12 +335,10 @@ export class WebCrawler {
 
   private isInternalLink(link: string): boolean {
     const urlObj = new URL(link, this.baseUrl);
-    const domainWithoutProtocol = this.baseUrl.replace(/^https?:\/\//, "");
-    return urlObj.hostname === domainWithoutProtocol;
-  }
-
-  private matchesPattern(link: string): boolean {
-    return true; // Placeholder for future pattern matching implementation
+    const baseDomain = this.baseUrl.replace(/^https?:\/\//, "").replace(/^www\./, "").trim();
+    const linkDomain = urlObj.hostname.replace(/^www\./, "").trim();
+    
+    return linkDomain === baseDomain;
   }
 
   private isFile(url: string): boolean {

apps/api/src/scraper/WebScraper/index.ts

@@ -18,6 +18,7 @@ import {
 import { generateCompletions } from "../../lib/LLM-extraction";
 import { getWebScraperQueue } from "../../../src/services/queue-service";
 import { fetchAndProcessDocx } from "./utils/docxProcessor";
+import { getAdjustedMaxDepth, getURLDepth } from "./utils/maxDepthUtils";
 
 export class WebScraperDataProvider {
   private bullJobId: string;
@@ -163,16 +164,12 @@ export class WebScraperDataProvider {
     inProgress?: (progress: Progress) => void
   ): Promise<Document[]> {
 
-    const pathSplits = new URL(this.urls[0]).pathname.split('/');
-    const baseURLDepth = pathSplits.length - (pathSplits[0].length === 0 && pathSplits[pathSplits.length - 1].length === 0 ? 1 : 0);
-    const adjustedMaxDepth = this.maxCrawledDepth + baseURLDepth;
-    
     const crawler = new WebCrawler({
       initialUrl: this.urls[0],
       includes: this.includes,
       excludes: this.excludes,
       maxCrawledLinks: this.maxCrawledLinks,
-      maxCrawledDepth: adjustedMaxDepth,
+      maxCrawledDepth: getAdjustedMaxDepth(this.urls[0], this.maxCrawledDepth),
       limit: this.limit,
       generateImgAltText: this.generateImgAltText,
       allowBackwardCrawling: this.allowBackwardCrawling,
@@ -580,8 +577,7 @@ export class WebScraperDataProvider {
   filterDepth(documents: Document[]): Document[] {
     return documents.filter((document) => {
       const url = new URL(document.metadata.sourceURL);
-      const path = url.pathname;
-      return path.split("/").length <= this.maxCrawledDepth;
+      return getURLDepth(url.toString()) <= this.maxCrawledDepth;
     });
   }
 }

apps/api/src/scraper/WebScraper/utils/__tests__/maxDepthUtils.test.ts

@@ -0,0 +1,47 @@
+import { getURLDepth, getAdjustedMaxDepth } from '../maxDepthUtils';
+
+describe('Testing getURLDepth and getAdjustedMaxDepth', () => {
+  it('should return 0 for root - mendable.ai', () => {
+    const enteredURL = "https://www.mendable.ai/"
+    expect(getURLDepth(enteredURL)).toBe(0);
+  });
+
+  it('should return 0 for root - scrapethissite.com', () => {
+    const enteredURL = "https://scrapethissite.com/"
+    expect(getURLDepth(enteredURL)).toBe(0);
+  });
+
+  it('should return 1 for scrapethissite.com/pages', () => {
+    const enteredURL = "https://scrapethissite.com/pages"
+    expect(getURLDepth(enteredURL)).toBe(1);
+  });
+
+  it('should return 2 for scrapethissite.com/pages/articles', () => {
+    const enteredURL = "https://scrapethissite.com/pages/articles"
+    expect(getURLDepth(enteredURL)).toBe(2);
+
+  });
+
+  it('Adjusted maxDepth should return 1 for scrapethissite.com and max depth param of 1', () => {
+    const enteredURL = "https://scrapethissite.com"
+    expect(getAdjustedMaxDepth(enteredURL, 1)).toBe(1);
+
+  });
+  it('Adjusted maxDepth should return 0 for scrapethissite.com and max depth param of 0', () => {
+    const enteredURL = "https://scrapethissite.com"
+    expect(getAdjustedMaxDepth(enteredURL, 0)).toBe(0);
+
+  });
+
+  it('Adjusted maxDepth should return 0 for mendable.ai and max depth param of 0', () => {
+    const enteredURL = "https://mendable.ai"
+    expect(getAdjustedMaxDepth(enteredURL, 0)).toBe(0);
+  });
+
+  it('Adjusted maxDepth should return 4 for scrapethissite.com/pages/articles and max depth param of 2', () => {
+    const enteredURL = "https://scrapethissite.com/pages/articles"
+    expect(getAdjustedMaxDepth(enteredURL, 2)).toBe(4);
+  });
+
+  
+});

apps/api/src/scraper/WebScraper/utils/maxDepthUtils.ts

@@ -0,0 +1,12 @@
+
+
+export function getAdjustedMaxDepth(url: string, maxCrawlDepth: number): number {
+  const baseURLDepth = getURLDepth(url);
+  const adjustedMaxDepth = maxCrawlDepth + baseURLDepth;
+  return adjustedMaxDepth;
+}
+
+export function getURLDepth(url: string): number {
+  const pathSplits = new URL(url).pathname.split('/');
+  return pathSplits.length - (pathSplits[0].length === 0 && pathSplits[pathSplits.length - 1].length === 0 ? 1 : 0) - 1;
+}