upgrading pois

lib/FredyPipelineExecutioner.js

@@ -227,7 +227,7 @@ class FredyPipelineExecutioner {
     const extractor = new Extractor({ ...this._providerConfig.puppeteerOptions, browser: this._browser });
     return new Promise((resolve, reject) => {
       extractor
-        .execute(url, this._providerConfig.waitForSelector)
+        .execute(url, this._providerConfig.waitForSelector, this._jobKey)
         .then(() => {
           const listings = extractor.parseResponseText(
             this._providerConfig.crawlContainer,

lib/provider/immobilienDe.js

@@ -26,7 +26,7 @@ function parseId(shortenedLink) {
 
 async function fetchDetails(listing, browser) {
   try {
-    const html = await puppeteerExtractor(listing.link, null, { browser });
+    const html = await puppeteerExtractor(listing.link, null, { browser, name: 'immobilienDe_details' });
     if (!html) return listing;
 
     const $ = cheerio.load(html);

lib/provider/immowelt.js

@@ -16,7 +16,7 @@ let appliedBlackList = [];
 
 async function fetchDetails(listing, browser) {
   try {
-    const html = await puppeteerExtractor(listing.link, null, { browser });
+    const html = await puppeteerExtractor(listing.link, null, { browser, name: 'immowelt_details' });
     if (!html) return listing;
 
     const $ = cheerio.load(html);

lib/provider/kleinanzeigen.js

@@ -128,7 +128,7 @@ async function enrichListingFromDetails(listing, browser) {
   if (!absoluteLink) return listing;
 
   try {
-    const html = await puppeteerExtractor(absoluteLink, null, { browser });
+    const html = await puppeteerExtractor(absoluteLink, null, { browser, name: 'kleinanzeigen_details' });
     if (!html) return { ...listing, link: absoluteLink };
 
     const { detailAddress, detailDescription } = extractDetailFromHtml(html);

lib/provider/sparkasse.js

@@ -16,7 +16,7 @@ let appliedBlackList = [];
 
 async function fetchDetails(listing, browser) {
   try {
-    const html = await puppeteerExtractor(listing.link, 'body', { browser });
+    const html = await puppeteerExtractor(listing.link, 'body', { browser, name: 'sparkasse_details' });
 
     const $ = cheerio.load(html);
     const nextDataRaw = $('#__NEXT_DATA__').text;

lib/provider/wgGesucht.js

@@ -16,7 +16,7 @@ let appliedBlackList = [];
 
 async function fetchDetails(listing, browser) {
   try {
-    const html = await puppeteerExtractor(listing.link, null, { browser });
+    const html = await puppeteerExtractor(listing.link, null, { browser, name: 'wgGesucht_details' });
     if (!html) return listing;
 
     const $ = cheerio.load(html);

lib/services/extractor/extractor.js

@@ -29,11 +29,12 @@ export default class Extractor {
    * your response will never contain what you are really looking for
    * @param url
    * @param waitForSelector
+   * @param jobKey
    */
-  execute = async (url, waitForSelector = null) => {
+  execute = async (url, waitForSelector = null, jobKey = null) => {
     this.responseText = null;
     try {
-      this.responseText = await puppeteerExtractor(url, waitForSelector, this.options);
+      this.responseText = await puppeteerExtractor(url, waitForSelector, { ...this.options, name: jobKey });
       if (this.responseText != null) {
         loadParser(this.responseText);
       }

lib/services/extractor/puppeteerExtractor.js

@@ -148,7 +148,11 @@ export default async function execute(url, waitForSelector, options) {
     if (botDetected(pageSource, statusCode)) {
       logger.warn('We have been detected as a bot :-/ Tried url: => ', url);
 
-      await trackPoi(TRACKING_POIS.DETECTED_AS_BOT);
+      if (options != null && options.name != null) {
+        await trackPoi(TRACKING_POIS.DETECTED_AS_BOT + '_' + options.name);
+      } else {
+        await trackPoi(TRACKING_POIS.DETECTED_AS_BOT);
+      }
 
       result = null;
     } else {

package.json

@@ -1,6 +1,6 @@
 {
   "name": "fredy",
-  "version": "22.0.5",
+  "version": "22.0.6",
   "description": "[F]ind [R]eal [E]states [d]amn eas[y].",
   "scripts": {
     "prepare": "husky",

tools/testFixtures/downloadFixtures.js

@@ -95,7 +95,10 @@ async function downloadHtmlProvider(name, providerConfig, launchBrowser, closeBr
 
   const browser = await launchBrowser(providerConfig.url, {});
   try {
-    const html = await puppeteerExtractor(providerConfig.url, providerConfig.waitForSelector, { browser });
+    const html = await puppeteerExtractor(providerConfig.url, providerConfig.waitForSelector, {
+      browser,
+      name: 'dowload_fixtures',
+    });
 
     if (!html) {
       console.warn(`  Failed to download ${name}`);