diff --git a/apps/api/src/__tests__/e2e_withAuth/index.test.ts b/apps/api/src/__tests__/e2e_withAuth/index.test.ts index 3b1c596..c11f398 100644 --- a/apps/api/src/__tests__/e2e_withAuth/index.test.ts +++ b/apps/api/src/__tests__/e2e_withAuth/index.test.ts @@ -563,7 +563,7 @@ describe("E2E Tests for API Routes", () => { const depth = pathSplits.length - (pathSplits[0].length === 0 && pathSplits[pathSplits.length - 1].length === 0 ? 1 : 0); expect(depth).toBeLessThanOrEqual(2); }); - }, 240000); + }, 180000); it.concurrent("should return a successful response with relative max depth option for a valid crawl job", async () => { const crawlResponse = await request(TEST_URL) @@ -616,7 +616,7 @@ describe("E2E Tests for API Routes", () => { const depth = pathSplits.length - (pathSplits[0].length === 0 && pathSplits[pathSplits.length - 1].length === 0 ? 1 : 0); expect(depth).toBeLessThanOrEqual(3); }); - }, 240000); + }, 180000); it.concurrent("should return a successful response with relative max depth option for a valid crawl job with maxDepths equals to zero", async () => { @@ -675,60 +675,11 @@ describe("E2E Tests for API Routes", () => { const depth = pathSplits.length - (pathSplits[0].length === 0 && pathSplits[pathSplits.length - 1].length === 0 ? 1 : 0); expect(depth).toBeLessThanOrEqual(1); }); - }, 240000); + }, 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 ${process.env.TEST_API_KEY}`) - .set("Content-Type", "application/json") - .send({ - url: "https://www.scrapethissite.com", - crawlerOptions: { maxDepth: 2, limit: 5 }, - }); - expect(crawlResponse.statusCode).toBe(200); + - const response = await request(TEST_URL) - .get(`/v0/crawl/status/${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); - }); - }, 240000); + // it.concurrent("should return a successful response with a valid API key and valid limit option", async () => { // const crawlResponse = await request(TEST_URL) @@ -828,7 +779,7 @@ describe("E2E Tests for API Routes", () => { expect(completedResponse.body.data[0].metadata.pageStatusCode).toBe(200); expect(completedResponse.body.data[0].metadata.pageError).toBeUndefined(); - }, 240000); + }, 180000); }); @@ -971,7 +922,7 @@ describe("E2E Tests for API Routes", () => { ); expect(childrenLinks.length).toBe(completedResponse.body.data.length); - }, 240000); // 120 seconds + }, 180000); // 120 seconds it.concurrent('should return a successful response for a valid crawl job with PDF files without explicit .pdf extension ', async () => { const crawlResponse = await request(TEST_URL) @@ -1012,7 +963,7 @@ describe("E2E Tests for API Routes", () => { expect(completedResponse.body.data[0]).toHaveProperty("metadata"); expect(completedResponse.body.data[0].metadata.pageStatusCode).toBe(200); expect(completedResponse.body.data[0].metadata.pageError).toBeUndefined(); - }, 240000); // 120 seconds + }, 180000); // 120 seconds it.concurrent("should return a successful response with max depth option for a valid crawl job", async () => { @@ -1062,7 +1013,7 @@ describe("E2E Tests for API Routes", () => { const depth = pathSplits.length - (pathSplits[0].length === 0 && pathSplits[pathSplits.length - 1].length === 0 ? 1 : 0); expect(depth).toBeLessThanOrEqual(2); }); - }, 240000); + }, 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) diff --git a/apps/api/src/scraper/WebScraper/__tests__/crawler.test.ts b/apps/api/src/scraper/WebScraper/__tests__/crawler.test.ts new file mode 100644 index 0000000..6f7b632 --- /dev/null +++ b/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; + const mockRobotsParser = robotsParser as jest.MockedFunction; + + 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: '' }); + }); + + 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); + console.log(maxCrawledDepth); + + 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); + console.log(maxCrawledDepth); + + 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); + console.log(maxCrawledDepth); + + 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 +}); + diff --git a/apps/api/src/scraper/WebScraper/crawler.ts b/apps/api/src/scraper/WebScraper/crawler.ts index 3171ec7..e1a5e05 100644 --- a/apps/api/src/scraper/WebScraper/crawler.ts +++ b/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; @@ -61,8 +62,7 @@ export class WebCrawler { const url = new URL(link); const path = url.pathname; - const pathSplits = new URL(url).pathname.split('/'); - const depth = pathSplits.length - (pathSplits[0].length === 0 && pathSplits[pathSplits.length - 1].length === 0 ? 1 : 0) -1; + const depth = getURLDepth(url.toString()); // Check if the link exceeds the maximum depth allowed diff --git a/apps/api/src/scraper/WebScraper/index.ts b/apps/api/src/scraper/WebScraper/index.ts index c19711d..21301af 100644 --- a/apps/api/src/scraper/WebScraper/index.ts +++ b/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 { - 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) -1; - 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; }); } } diff --git a/apps/api/src/scraper/WebScraper/utils/__tests__/maxDepthUtils.test.ts b/apps/api/src/scraper/WebScraper/utils/__tests__/maxDepthUtils.test.ts new file mode 100644 index 0000000..e77242c --- /dev/null +++ b/apps/api/src/scraper/WebScraper/utils/__tests__/maxDepthUtils.test.ts @@ -0,0 +1,37 @@ +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', () => { + const enteredURL = "https://scrapethissite.com" + expect(getAdjustedMaxDepth(enteredURL, 1)).toBe(1); + + }); + + it('Adjusted maxDepth should return 5 for scrapethissite.com/pages/articles', () => { + const enteredURL = "https://scrapethissite.com/pages/articles" + expect(getAdjustedMaxDepth(enteredURL, 2)).toBe(5); + }); + + +}); diff --git a/apps/api/src/scraper/WebScraper/utils/maxDepthUtils.ts b/apps/api/src/scraper/WebScraper/utils/maxDepthUtils.ts new file mode 100644 index 0000000..c1fea7f --- /dev/null +++ b/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; +}