testing crawl with new.abb.com case

many unnecessary console.logs for tracing the code execution

apps/api/requests.http

@@ -1,10 +1,10 @@
 ### Crawl Website
 POST http://localhost:3002/v0/scrape HTTP/1.1
-Authorization: Bearer 
+Authorization: Bearer fc-
 content-type: application/json
 
 {
-    "url":"https://docs.mendable.ai"
+    "url":"new.abb.com/sustainability/foundation"
 }
 
 
@@ -14,16 +14,24 @@ GET http://localhost:3002/v0/jobs/active HTTP/1.1
 
 ### Scrape Website
 POST http://localhost:3002/v0/crawl HTTP/1.1
-Authorization: Bearer 
+Authorization: Bearer fc-
 content-type: application/json
 
 {
-    "url":"https://www.mendable.ai",
+  "url": "new.abb.com/sustainability/foundation"
-    "crawlerOptions": {
-        "returnOnlyUrls": true
-    }
 }
 
+## "reoveTags": [],
+  # "mode": "crawl",
+  # "crawlerOptions": {
+  #     "allowBackwardCrawling": false
+  # },
+  # "pageOptions": {
+  #   "onlyMainContent": false,
+  #   "includeHtml": false,
+  #   "parsePDF": true
+  # }
+
 
 
 

apps/api/src/controllers/crawl.ts

@@ -66,6 +66,7 @@ export async function crawlController(req: Request, res: Response) {
       parsePDF: true
     };
 
+    console.log('1. here OK!')
     if (mode === "single_urls" && !url.includes(",")) {
       try {
         const a = new WebScraperDataProvider();
@@ -84,6 +85,7 @@ export async function crawlController(req: Request, res: Response) {
             current_url: progress.currentDocumentUrl,
           });
         });
+        console.log('crawlController - return res.json...')
         return res.json({
           success: true,
           documents: docs,

apps/api/src/lib/html-to-markdown.ts

@@ -1,5 +1,6 @@
 
 export function parseMarkdown(html: string) {
+  console.log('parseMarkdown - start!')
   var TurndownService = require("turndown");
   var turndownPluginGfm = require('joplin-turndown-plugin-gfm')
 
@@ -50,6 +51,6 @@ export function parseMarkdown(html: string) {
     /\[Skip to Content\]\(#[^\)]*\)/gi,
     ""
   );
-
+  console.log('parseMarkdown - return')
   return markdownContent;
 }

apps/api/src/main/runWebScraper.ts

@@ -78,9 +78,11 @@ export async function runWebScraper({
         pageOptions: pageOptions,
       });
     }
+    console.log('runWebScraper - getDocuments')
     const docs = (await provider.getDocuments(false, (progress: Progress) => {
       inProgress(progress);
     })) as Document[];
+    console.log('runWebScraper - getDocuments - done - docs.length:', docs.length)
 
     if (docs.length === 0) {
       return {

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

@@ -129,24 +129,31 @@ export class WebCrawler {
   ): Promise<{ url: string, html: string }[]> {
     // Fetch and parse robots.txt
     try {
-      const response = await axios.get(this.robotsTxtUrl);
+      console.log('3.1 here OK')
+      console.log('this.robotsTxtUrl:', this.robotsTxtUrl)
+      const response = await axios.get(this.robotsTxtUrl, { timeout: 3000 });
+      console.log('????', {response})
+      console.log('3.2 here OK')
       this.robots = robotsParser(this.robotsTxtUrl, response.data);
     } catch (error) {
       console.log(`Failed to fetch robots.txt from ${this.robotsTxtUrl}`);
 
     }
 
-
+    console.log('4. here OK!')
     if(!crawlerOptions?.ignoreSitemap){
+      console.log('4.1')
       const sitemapLinks = await this.tryFetchSitemapLinks(this.initialUrl);
-    
+      console.log('4.2')
       if (sitemapLinks.length > 0) {
+        console.log('4.3')
         let filteredLinks = this.filterLinks(sitemapLinks, limit, maxDepth);
-       
+        console.log('4.4')
         return filteredLinks.map(link => ({ url: link, html: "" }));
       }
     }
 
+    console.log('5. here OK!')
     const urls = await this.crawlUrls(
       [this.initialUrl],
       pageOptions,
@@ -154,7 +161,7 @@ export class WebCrawler {
       inProgress
     );
    
-    
+    console.log('6. here OK!')
     if (
       urls.length === 0 &&
       this.filterLinks([this.initialUrl], limit, this.maxCrawledDepth).length > 0
@@ -164,6 +171,7 @@ export class WebCrawler {
 
     // make sure to run include exclude here again
     const filteredUrls = this.filterLinks(urls.map(urlObj => urlObj.url), limit, this.maxCrawledDepth);
+    console.log('7. here OK!')
     return filteredUrls.map(url => ({ url, html: urls.find(urlObj => urlObj.url === url)?.html || "" }));
   }
 
@@ -180,6 +188,7 @@ export class WebCrawler {
         }
         return;
       }
+      console.log('crawlUrls - crawl')
       const newUrls = await this.crawl(task, pageOptions);
       // add the initial url if not already added
       // if (this.visited.size === 1) {
@@ -192,7 +201,7 @@ export class WebCrawler {
       //   }
       // }
 
-
+      console.log('---??---')
       newUrls.forEach((page) => this.crawledUrls.set(page.url, page.html));
       
       if (inProgress && newUrls.length > 0) {
@@ -210,12 +219,14 @@ export class WebCrawler {
           currentDocumentUrl: task,
         });
       }
+      console.log('----???----')
       await this.crawlUrls(newUrls.map((p) => p.url), pageOptions, concurrencyLimit, inProgress);
       if (callback && typeof callback === "function") {
         callback();
       }
     }, concurrencyLimit);
 
+    console.log('crawlUrls - queue.push')
     queue.push(
       urls.filter(
         (url) =>
@@ -225,7 +236,9 @@ export class WebCrawler {
         if (err) console.error(err);
       }
     );
+    console.log('crawlUrls - queue.drain')
     await queue.drain();
+    console.log('crawlUrls - return')
     return Array.from(this.crawledUrls.entries()).map(([url, html]) => ({ url, html }));
   }
 
@@ -253,16 +266,22 @@ export class WebCrawler {
 
       // If it is the first link, fetch with single url
       if (this.visited.size === 1) {
+        console.log('crawl scrapSingleUrl...')
         const page = await scrapSingleUrl(url, { ...pageOptions, includeHtml: true });
+        console.log('got a page! lets continue...')
         content = page.html ?? "";
         pageStatusCode = page.metadata?.pageStatusCode;
         pageError = page.metadata?.pageError || undefined;
       } else {
-        const response = await axios.get(url);
+        // console.log('crawl - else')
+        const response = await axios.get(url, { timeout: 3000 });
+        console.log('crawl - else - response ok')
         content = response.data ?? "";
         pageStatusCode = response.status;
         pageError = response.statusText != "OK" ? response.statusText : undefined;
       }
+
+      console.log('crawl... keep going')
       const $ = load(content);
       let links: { url: string, html: string, pageStatusCode?: number, pageError?: string }[] = [];
 
@@ -271,14 +290,17 @@ export class WebCrawler {
         links.push({ url, html: content, pageStatusCode, pageError });
       }
 
+      console.log('crawl... keep going 2')
       $("a").each((_, element) => {
         const href = $(element).attr("href");
         if (href) {
+          console.log('href:', href)
           let fullUrl = href;
           if (!href.startsWith("http")) {
             fullUrl = new URL(href, this.baseUrl).toString();
           }
           const urlObj = new URL(fullUrl);
+          console.log('urlObj:', urlObj)
           const path = urlObj.pathname;
 
 
@@ -295,10 +317,13 @@ export class WebCrawler {
           }
         }
       });
+      console.log('crawl... keep going 3')
 
       if (this.visited.size === 1) {
         return links;
       }
+
+      console.log('returning crawl...')
       // Create a new list to return to avoid modifying the visited list
       return links.filter((link) => !this.visited.has(link.url));
     } catch (error) {
@@ -385,6 +410,7 @@ export class WebCrawler {
 
   // 
   private async tryFetchSitemapLinks(url: string): Promise<string[]> {
+    console.log("4.1.1 - Normalizing URL");
     const normalizeUrl = (url: string) => {
       url = url.replace(/^https?:\/\//, "").replace(/^www\./, "");
       if (url.endsWith("/")) {
@@ -393,46 +419,48 @@ export class WebCrawler {
       return url;
     };
 
+    console.log("4.1.2 - Constructing sitemap URL");
     const sitemapUrl = url.endsWith("/sitemap.xml")
       ? url
       : `${url}/sitemap.xml`;
 
     let sitemapLinks: string[] = [];
 
+    console.log("4.1.3 - Fetching sitemap from constructed URL");
     try {
-      const response = await axios.get(sitemapUrl);
+      const response = await axios.get(sitemapUrl, { timeout: 3000 });
       if (response.status === 200) {
+        console.log("4.1.4 - Extracting links from sitemap");
         sitemapLinks = await getLinksFromSitemap(sitemapUrl);
       }
     } catch (error) {
-      // Error handling for failed sitemap fetch
+      console.error(`Failed to fetch sitemap from ${sitemapUrl}: ${error}`);
-      // console.error(`Failed to fetch sitemap from ${sitemapUrl}: ${error}`);
     }
 
     if (sitemapLinks.length === 0) {
-      // If the first one doesn't work, try the base URL
+      console.log("4.1.5 - Trying base URL sitemap as fallback");
       const baseUrlSitemap = `${this.baseUrl}/sitemap.xml`;
       try {
-        const response = await axios.get(baseUrlSitemap);
+        const response = await axios.get(baseUrlSitemap, { timeout: 3000 });
         if (response.status === 200) {
+          console.log("4.1.6 - Extracting links from base URL sitemap");
           sitemapLinks = await getLinksFromSitemap(baseUrlSitemap);
         }
       } catch (error) {
-        // Error handling for failed base URL sitemap fetch
+        console.error(`Failed to fetch sitemap from ${baseUrlSitemap}: ${error}`);
-        // console.error(`Failed to fetch sitemap from ${baseUrlSitemap}: ${error}`);
       }
     }
 
-    // Normalize and check if the URL is present in any of the sitemaps
+    console.log("4.1.7 - Normalizing sitemap links");
     const normalizedUrl = normalizeUrl(url);
     const normalizedSitemapLinks = sitemapLinks.map(link => normalizeUrl(link));
 
-    // has to be greater than 0 to avoid adding the initial URL to the sitemap links, and preventing crawler to crawl
+    console.log("4.1.8 - Checking if normalized URL is already included");
     if (!normalizedSitemapLinks.includes(normalizedUrl) && sitemapLinks.length > 0) {
-      // do not push the normalized url
+      console.log("4.1.9 - Adding initial URL to sitemap links");
       sitemapLinks.push(url);
     }
-
+    console.log("4.1.10 - Returning sitemap links");
     return sitemapLinks;
   }
 }

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

@@ -63,11 +63,13 @@ export class WebScraperDataProvider {
       await Promise.all(
         batchUrls.map(async (url, index) => {
           const existingHTML = allHtmls ? allHtmls[i + index] : "";
+          console.log('convertUrlsToDocuments - scrapSingleUrl')
           const result = await scrapSingleUrl(
             url,
             this.pageOptions,
             existingHTML
           );
+          console.log('convertUrlsToDocuments - result ok')
           processedUrls++;
           if (inProgress) {
             inProgress({
@@ -98,6 +100,7 @@ export class WebScraperDataProvider {
         return [] as Document[];
       }
     }
+    console.log('returning results from convertUrlsToDocuments...')
     return results.filter((result) => result !== null) as Document[];
   }
 
@@ -106,7 +109,7 @@ export class WebScraperDataProvider {
     inProgress?: (progress: Progress) => void
   ): Promise<Document[]> {
     this.validateInitialUrl();
-
+    console.log('2. here OK!')
     if (!useCaching) {
       return this.processDocumentsWithoutCache(inProgress);
     }
@@ -175,6 +178,7 @@ export class WebScraperDataProvider {
       allowBackwardCrawling: this.allowBackwardCrawling,
     });
 
+    console.log('3. here OK!')
     let links = await crawler.start(
       inProgress,
       this.pageOptions,
@@ -186,21 +190,28 @@ export class WebScraperDataProvider {
       this.maxCrawledDepth
     );
 
+    console.log("8 - Mapping URLs from links");
     let allLinks = links.map((e) => e.url);
+    console.log("9 - Mapping HTML content from links");
     const allHtmls = links.map((e) => e.html);
 
+    console.log("10 - Checking if only URLs should be returned");
     if (this.returnOnlyUrls) {
       return this.returnOnlyUrlsResponse(allLinks, inProgress);
     }
 
     let documents = [];
+    console.log("11 - Checking if crawler is in fast mode and HTML content is present");
     // check if fast mode is enabled and there is html inside the links
     if (this.crawlerMode === "fast" && links.some((link) => link.html)) {
+      console.log("12 - Processing links with HTML content in fast mode");
       documents = await this.processLinks(allLinks, inProgress, allHtmls);
     } else {
+      console.log("13 - Processing links in normal mode");
       documents = await this.processLinks(allLinks, inProgress);
     }
 
+    console.log("14 - Caching and finalizing documents");
     return this.cacheAndFinalizeDocuments(documents, allLinks);
   }
 
@@ -259,14 +270,22 @@ export class WebScraperDataProvider {
 
     links = links.filter(link => !pdfLinks.includes(link) && !docLinks.includes(link));
 
+    console.log('processLinks - convertUrlsToDocuments...')
     let documents = await this.convertUrlsToDocuments(
       links,
       inProgress,
       allHtmls
     );
-    documents = await this.getSitemapData(this.urls[0], documents);
+    console.log('processLinks - convertUrlsToDocuments - done')
 
+    console.log('processLinks - getSitemapData...')
+    documents = await this.getSitemapData(this.urls[0], documents);
+    console.log('processLinks - getSitemapData - done')
+
+    console.log('processLinks - applyPathReplacements...')
     documents = this.applyPathReplacements(documents);
+    console.log('processLinks - applyPathReplacements - done')
+
     // documents = await this.applyImgAltText(documents);
 
     if (
@@ -275,6 +294,7 @@ export class WebScraperDataProvider {
     ) {
       documents = await generateCompletions(documents, this.extractorOptions);
     }
+    console.log('processLinks - returning...')
     return documents.concat(pdfDocuments).concat(docxDocuments);
   }
 
@@ -320,8 +340,11 @@ export class WebScraperDataProvider {
     documents: Document[],
     links: string[]
   ): Promise<Document[]> {
+    console.log('cacheAndFinalizeDocuments - 1')
     await this.setCachedDocuments(documents, links);
+    console.log('cacheAndFinalizeDocuments - 2')
     documents = this.removeChildLinks(documents);
+    console.log('cacheAndFinalizeDocuments - 3')
     return documents.splice(0, this.limit);
   }
 

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

@@ -113,13 +113,25 @@ export async function scrapWithScrapingBee(
   pageOptions: { parsePDF?: boolean } = { parsePDF: true }
 ): Promise<{ content: string, pageStatusCode?: number, pageError?: string }> {
   try {
+    console.log("13. scrapWithScrapingBee - 1")
     const client = new ScrapingBeeClient(process.env.SCRAPING_BEE_API_KEY);
+    console.log("13. scrapWithScrapingBee - 2")
     const clientParams = await generateRequestParams(
       url,
       wait_browser,
       timeout,
     );
-
+    console.log({ url,
+      wait_browser,
+      timeout })
+    console.log({
+      ...clientParams,
+      params: {
+        ...clientParams.params,
+        'transparent_status_code': 'True'
+      }
+    })
+    console.log("13. scrapWithScrapingBee - 3")
     const response = await client.get({
       ...clientParams,
       params: {
@@ -127,7 +139,7 @@ export async function scrapWithScrapingBee(
         'transparent_status_code': 'True'
       }
     });
-
+    console.log("13. scrapWithScrapingBee - 4")
     const contentType = response.headers["content-type"];
     if (contentType && contentType.includes("application/pdf")) {
       return await fetchAndProcessPdf(url, pageOptions?.parsePDF);
@@ -140,6 +152,7 @@ export async function scrapWithScrapingBee(
       } catch (decodeError) {
         console.error(`[ScrapingBee][c] Error decoding response data for url: ${url} -> ${decodeError}`);
       }
+      console.log("13. scrapWithScrapingBee - 5 - returning ok")
       return { content: text, pageStatusCode: response.status, pageError: response.statusText != "OK" ? response.statusText : undefined };
     }
   } catch (error) {
@@ -396,8 +409,13 @@ export async function scrapSingleUrl(
       screenshot = customScrapedContent.screenshot;
     }
 
+    console.log(
+      'chegou aqui'
+    )
+
     //* TODO: add an optional to return markdown or structured/extracted content
     let cleanedHtml = removeUnwantedElements(scraperResponse.text, pageOptions);
+    console.log('cleanedHtml')
 
     return {
       text: await parseMarkdown(cleanedHtml),
@@ -432,7 +450,9 @@ export async function scrapSingleUrl(
         break;
       }
 
+      console.log('attemptScraping - 1')
       const attempt = await attemptScraping(urlToScrap, scraper);
+      console.log('attemptScraping - 2 - return ok')
       text = attempt.text ?? '';
       html = attempt.html ?? '';
       screenshot = attempt.screenshot ?? '';
@@ -451,6 +471,7 @@ export async function scrapSingleUrl(
         console.info(`Falling back to ${scrapersInOrder[nextScraperIndex]}`);
       }
     }
+    console.log('ok... here we are...')
 
     if (!text) {
       throw new Error(`All scraping methods failed for URL: ${urlToScrap}`);
@@ -487,6 +508,7 @@ export async function scrapSingleUrl(
       };
     }
 
+    console.log('returning document...')
     return document;
   } catch (error) {
     console.error(`Error: ${error} - Failed to fetch URL: ${urlToScrap}`);

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

@@ -8,7 +8,7 @@ export async function getLinksFromSitemap(
   try {
     let content: string;
     try {
-      const response = await axios.get(sitemapUrl);
+      const response = await axios.get(sitemapUrl, { timeout: 3000 });
       content = response.data;
     } catch (error) {
       console.error(`Request failed for ${sitemapUrl}: ${error}`);
@@ -42,7 +42,7 @@ export async function getLinksFromSitemap(
 export const fetchSitemapData = async (url: string): Promise<SitemapEntry[] | null> => {
   const sitemapUrl = url.endsWith("/sitemap.xml") ? url : `${url}/sitemap.xml`;
   try {
-    const response = await axios.get(sitemapUrl);
+    const response = await axios.get(sitemapUrl, { timeout: 3000 });
     if (response.status === 200) {
       const xml = response.data;
       const parsedXml = await parseStringPromise(xml);

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

@@ -43,6 +43,10 @@ export function isUrlBlocked(url: string): boolean {
   }
 
   try {
+    if (!url.startsWith('http://') && !url.startsWith('https://')) {
+      url = 'https://' + url;
+    }
+    
     const urlObj = new URL(url);
     const hostname = urlObj.hostname.toLowerCase();
 

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

@@ -71,7 +71,7 @@ export async function processPdfToText(filePath: string, parsePDF: boolean): Pro
 
       while (attempt < maxAttempts && !resultAvailable) {
         try {
-          resultResponse = await axios.get(resultUrl, { headers });
+          resultResponse = await axios.get(resultUrl, { headers, timeout: 6000 });
           if (resultResponse.status === 200) {
             resultAvailable = true; // Exit condition met
           } else {

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

@@ -4,7 +4,7 @@ export async function attemptScrapWithRequests(
   urlToScrap: string
 ): Promise<string | null> {
   try {
-    const response = await axios.get(urlToScrap);
+    const response = await axios.get(urlToScrap, { timeout: 15000 });
 
     if (!response.data) {
       console.log("Failed normal requests as well");

apps/api/src/services/queue-worker.ts

@@ -14,6 +14,7 @@ if(process.env.ENV === 'production') {
 getWebScraperQueue().process(
   Math.floor(Number(process.env.NUM_WORKERS_PER_QUEUE ?? 8)),
   async function (job, done) {
+    console.log('getWebScraperQueue - start')
     try {
       job.progress({
         current: 1,
@@ -22,11 +23,13 @@ getWebScraperQueue().process(
         current_url: "",
       });
       const start = Date.now();
-
+      console.log('getWebScraperQueue - startWebScraperPipeline')
       const { success, message, docs } = await startWebScraperPipeline({ job });
+      console.log('getWebScraperQueue - startWebScraperPipeline - done')
       const end = Date.now();
       const timeTakenInSeconds = (end - start) / 1000;
 
+      console.log('docs.length:', docs.length)
       const data = {
         success: success,
         result: {