upgrading dependencies | adding sqlite for later analysis

* building multi platform docker images

* upgrading dependencies | using scraping ant for neubaukompass

.github/workflows/docker.yml

@@ -44,3 +44,4 @@ jobs:
           push: true
           tags: ${{ steps.meta.outputs.tags }}
           labels: ${{ steps.meta.outputs.labels }}
+          platforms: linux/amd64, linux/arm64

.github/workflows/test.yml

@@ -15,7 +15,7 @@ jobs:
       - name: Setup node
         uses: actions/setup-node@v2.5.1
         with:
-          node-version: 18
+          node-version: 20
           cache: 'yarn'
       - run: yarn install
       - run: yarn run test

Dockerfile

@@ -1,19 +1,20 @@
-# syntax=docker/dockerfile:1.3
+FROM node:20
-FROM node:18-alpine AS builder
+
-COPY --chown=1000:1000 . /fredy
 WORKDIR  /fredy
-USER 1000
+
+COPY . /fredy
+
 RUN yarn install
+
+RUN yarn global add pm2
+
 RUN yarn run prod
 
-FROM node:16-alpine
-COPY --from=builder --chown=1000:1000 /fredy /fredy
 RUN mkdir /db /conf && \
   chown 1000:1000 /db /conf && \
   chmod 777 -R /db/ && \
   ln -s /db /fredy/db && ln -s /conf /fredy/conf
+
 EXPOSE 9998
-USER 1000
+
-VOLUME [ "/conf", "/db" ]
+CMD pm2-runtime index.js
-WORKDIR  /fredy
-CMD node index.js --no-daemon

README.md

@@ -17,7 +17,7 @@ _Fredy_ is supported by JetBrains under Open Source Support Program
 
 ## Usage  
 
-- Make sure to use Node.js 18 or above
+- Make sure to use Node.js 20 or above
 - Run the following commands:
 ```ssh
 yarn (or npm install)
@@ -78,15 +78,20 @@ yarn run test
 # Architecture
 ![Architecture](/doc/architecture.jpg "Architecture")
 
-### Immoscout / Immonet
+### Immoscout / Immonet / NeubauKompass
-I have added **experimental** support for Immoscout and Immonet. They both are somewhat special, because they have decided to secure their service from bots using Re-Capture. Finding a way around this is barely possible. For _Fredy_ to be able to bypass this check, I'm using a service called [ScrapingAnt](https://scrapingant.com/). The trick is to use a headless browser, rotating proxies and (once successfully validated) to re-send the cookies each time.
+I have added **experimental** support for Immoscout, Immonet and NeubauKompass. They all are somewhat special, because they have decided to secure their service from bots using Re-Capture. Finding a way around this is barely possible. For _Fredy_ to be able to bypass this check, I'm using a service called [ScrapingAnt](https://scrapingant.com/). The trick is to use a headless browser, rotating proxies and (once successfully validated) to re-send the cookies each time.
 
 To be able to use Immoscout / Immonet, you need to create an account at ScrapingAnt. Configure the API key in the "General Settings" tab (visible when logged in as administrator).
 The rest will be handled by _Fredy_. Keep in mind, the support is experimental. There might be bugs and you might not always pass the re-capture check, but most of the time it works rather well :)
 
 If you need more than the 1000 API calls allowed per month, I'd suggest opting for a paid account... ScrapingAnt loves OpenSource, therefore they have decided to give all _Fredy_ users a 10% discount by using the code **FREDY10** (Disclaimer: I do not earn any money for recommending their service).
 
-### Contribution guidelines  
+### 👐 Contributing
+Thanks to all the people who already contributed!
+
+<a href="https://github.com/orangecoding/fredy/graphs/contributors">
+  <img src="https://contrib.rocks/image?repo=orangecoding/fredy" />
+</a>
 
 See [Contributing](https://github.com/orangecoding/fredy/blob/master/CONTRIBUTING.md)
 

docker-compose.yml

@@ -1,4 +1,4 @@
-version: '3.3'
+version: '3.8'
 services:
   fredy:
     container_name: fredy
@@ -13,3 +13,4 @@ services:
       - ./db:/db
     ports:
         - 9998:9998
+    restart: unless-stopped

lib/FredyRuntime.js

@@ -87,7 +87,10 @@ class FredyRuntime {
     return listings.map(this._providerConfig.normalize);
   }
   _filter(listings) {
-    return listings.filter(this._providerConfig.filter);
+    //only return those where all the fields have been found
+    const keys = Object.keys(this._providerConfig.crawlFields);
+    const filteredListings = listings.filter((item) => keys.every((key) => key in item));
+    return filteredListings.filter(this._providerConfig.filter);
   }
   _findNew(listings) {
     const newListings = listings.filter((o) => getKnownListings(this._jobKey, this._providerId)[o.id] == null);

lib/notification/adapter/apprise.js

@@ -3,12 +3,12 @@ import { getJob } from '../../services/storage/jobStorage.js';
 import fetch from 'node-fetch';
 
 export const send = ({ serviceName, newListings, notificationConfig, jobKey }) => {
-  const { priority, server } = notificationConfig.find((adapter) => adapter.id === config.id).fields;
+  const { server } = notificationConfig.find((adapter) => adapter.id === config.id).fields;
   const job = getJob(jobKey);
   const jobName = job == null ? jobKey : job.name;
   const promises = newListings.map((newListing) => {
     const title = `${jobName} at ${serviceName}: ${newListing.title}`;
-    const message = `Address: ${newListing.address}\nSize: ${newListing.size}\nPrice: ${newListing.price}\Link: ${newListing.link}`;
+    const message = `Address: ${newListing.address}\nSize: ${newListing.size}\nPrice: ${newListing.price}\nink: ${newListing.link}`;
     return fetch(server, {
       method: 'POST',
       headers: { 'Content-Type': 'application/json' },
@@ -27,15 +27,10 @@ export const config = {
   readme: markdown2Html('lib/notification/adapter/apprise.md'),
   description: 'Fredy will send new listings to your Apprise instance.',
   fields: {
-    priority: {
-      type: 'number',
-      label: 'Priority',
-      description: 'The priority of the send notification.',
-    },
     server: {
       type: 'text',
       label: 'Server',
-      description: 'The server url to send the notification to.',
+      description: 'The server URL to send the notification to.',
     },
   },
 };

lib/notification/adapter/apprise.md

@@ -1,5 +1,3 @@
 ### Apprise Adapter
 
 Refer to the [instructions](https://github.com/caronc/apprise-api#installation) on how to set up an Apprise instance and how to configure your preferred notification service.
-
-In addition to the Apprise instance, the priority must be defined.

lib/notification/adapter/sqlite.js

@@ -0,0 +1,25 @@
+import { markdown2Html } from '../../services/markdown.js';
+import Database from 'better-sqlite3';
+export const send = ({ serviceName, newListings, jobKey }) => {
+  const db = new Database('db/listings.db');
+  const fields = ['serviceName', 'jobKey', 'id', 'size', 'rooms', 'price', 'address', 'title', 'link', 'description'];
+  db.prepare(`CREATE TABLE IF NOT EXISTS listing (${fields.join(' TEXT, ')} TEXT);`).run();
+  const insert = db.prepare(`INSERT INTO listing (${fields.join(', ')}) VALUES (@${fields.join(', @')})`);
+  newListings.map((listing) => {
+    let insertListing = {};
+    fields.map((field) => {
+      insertListing[field] = listing[field];
+    });
+    insertListing.serviceName = serviceName;
+    insertListing.jobKey = jobKey;
+    insert.run(insertListing);
+  });
+  return Promise.resolve();
+};
+export const config = {
+  id: 'sqlite',
+  name: 'Sqlite',
+  description: 'This adapter stores listings in a local sqlite3 database.',
+  config: {},
+  readme: markdown2Html('lib/notification/adapter/sqlite.md'),
+};

lib/notification/adapter/sqlite.md

@@ -0,0 +1,7 @@
+### Sqlite Adapter
+This adapter stores search results in a sqlite database located in db/listings.db. This file can be used for further analysis later on.   
+
+Fields are:
+```
+['serviceName', 'jobKey', 'id', 'size', 'rooms', 'price', 'address', 'title', 'link', 'description']
+```

lib/provider/einsAImmobilien.js

@@ -1,18 +1,40 @@
-import utils from '../utils.js';
+import utils, { buildHash } from '../utils.js';
 let appliedBlackList = [];
+
 function normalize(o) {
   let size = `${o.size.replace(' Wohnfläche ', '').trim()}`;
   if (o.rooms != null) {
     size += ` / / ${o.rooms.trim()}`;
   }
   const link = `https://www.1a-immobilienmarkt.de/expose/${o.id}.html`;
-  return Object.assign(o, { size, link });
+  const price = normalizePrice(o.price);
+  const id = buildHash(o.id, price);
+  return Object.assign(o, { id, price, size, link });
+}
+
+/**
+ * einsAImmobilien sometimes use a weird pricing label such as `775.700,00 EUR Kaufpreis ab 2.475 € mtl`.
+ * Make sure to extract only the actual price out of the string.
+ * @param price
+ * @returns {*}
+ */
+function normalizePrice(price) {
+  if (price == null) {
+    return null;
+  }
+  const regex = /(\d{1,3}(?:\.\d{3})*,\d{2})\s?(EUR|€)/g;
+  const result = price.match(regex);
+  if (result == null || result.length === 0) {
+    return price;
+  }
+  return result[0];
 }
 function applyBlacklist(o) {
   const titleNotBlacklisted = !utils.isOneOf(o.title, appliedBlackList);
   const descNotBlacklisted = !utils.isOneOf(o.description, appliedBlackList);
   return titleNotBlacklisted && descNotBlacklisted;
 }
+
 const config = {
   url: null,
   crawlContainer: '.tabelle',
@@ -23,7 +45,6 @@ const config = {
     size: '.tabelle .inner_object_data .data_boxes div:nth-child(1)',
     rooms: '.tabelle .inner_object_data .data_boxes div:nth-child(2)',
     title: '.tabelle .inner_object_data .tabelle_inhalt_titel_black | removeNewline | trim',
-    description: '.tabelle .inner_object_data .objekt_beschreibung | removeNewline | trim',
   },
   normalize: normalize,
   filter: applyBlacklist,

lib/provider/immobilienDe.js

@@ -1,4 +1,4 @@
-import utils from '../utils.js';
+import utils, {buildHash} from '../utils.js';
 let appliedBlackList = [];
 function shortenLink(link) {
   return link.substring(0, link.indexOf('?'));
@@ -7,12 +7,12 @@ function parseId(shortenedLink) {
   return shortenedLink.substring(shortenedLink.lastIndexOf('/') + 1);
 }
 function normalize(o) {
-  const id = parseId(shortenLink(o.link));
   const size = o.size || 'N/A m²';
   const price = o.price || 'N/A €';
   const title = o.title || 'No title available';
   const address = o.address || 'No address available';
   const link = shortenLink(o.link);
+  const id = buildHash(parseId(shortenLink(o.link)), o.price);
   return Object.assign(o, { id, price, size, title, address, link });
 }
 function applyBlacklist(o) {

lib/provider/immonet.js

@@ -1,12 +1,12 @@
-import utils from '../utils.js';
+import utils, {buildHash} from '../utils.js';
 let appliedBlackList = [];
 function normalize(o) {
-  const id = o.id.substring(o.id.lastIndexOf('/') + 1, o.id.length);
   const size = o.size != null ? o.size.replace('Wohnfläche ', '') : 'N/A m²';
   const price = o.price.replace('Kaufpreis ', '');
   const address = o.address.split(' • ')[o.address.split(' • ').length - 1];
   const title = o.title || 'No title available';
   const link = o.id;
+  const id = buildHash(o.id.substring(o.id.lastIndexOf('/') + 1, o.id.length), price);
   return Object.assign(o, { id, address, price, size, title, link });
 }
 function applyBlacklist(o) {

lib/provider/immoscout.js

@@ -1,4 +1,4 @@
-import utils from '../utils.js';
+import utils, {buildHash} from '../utils.js';
 let appliedBlackList = [];
 function nullOrEmpty(val) {
   return val == null || val.length === 0;
@@ -6,8 +6,9 @@ function nullOrEmpty(val) {
 function normalize(o) {
   const title = nullOrEmpty(o.title) ? 'NO TITLE FOUND' : o.title.replace('NEU', '');
   const address = nullOrEmpty(o.address) ? 'NO ADDRESS FOUND' : (o.address || '').replace(/\(.*\),.*$/, '').trim();
-  const link = nullOrEmpty(o.address) ? 'NO LINK' : `https://www.immobilienscout24.de${o.link.substring(o.link.indexOf('/expose'))}`;
+  const link = nullOrEmpty(o.link) ? 'NO LINK' : `https://www.immobilienscout24.de${o.link.substring(o.link.indexOf('/expose'))}`;
-  return Object.assign(o, { title, address, link });
+  const id = buildHash(o.id, o.price);
+  return Object.assign(o, { id, title, address, link });
 }
 function applyBlacklist(o) {
   return !utils.isOneOf(o.title, appliedBlackList);

lib/provider/immoswp.js

@@ -1,44 +1,48 @@
-import utils from '../utils.js';
+import utils, {buildHash} from '../utils.js';
+
 let appliedBlackList = [];
+
 function normalize(o) {
-  const id = o.id.substring(o.id.indexOf('-') + 1, o.id.length);
+    const size = o.size || 'N/A m²';
-  const size = o.size || 'N/A m²';
+    const price = (o.price || '--- €').replace('Preis auf Anfrage', '--- €');
-  const price = (o.price || '--- €').replace('Preis auf Anfrage', '--- €');
+    const title = o.title || 'No title available';
-  const address = o.address || 'No address available';
+    const immoId = o.id.substring(o.id.indexOf('-') + 1, o.id.length);
-  const title = o.title || 'No title available';
+    const link = `https://immo.swp.de/immobilien/${immoId}`;
-  const link = `https://immo.swp.de/immobilien/${id}`;
+    const description = o.description;
-  const description = o.description;
+    const id = buildHash(immoId, price);
-  return Object.assign(o, { id, address, price, size, title, link, description });
+    return Object.assign(o, {id, price, size, title, link, description});
 }
+
 function applyBlacklist(o) {
-  const titleNotBlacklisted = !utils.isOneOf(o.title, appliedBlackList);
+    const titleNotBlacklisted = !utils.isOneOf(o.title, appliedBlackList);
-  const descNotBlacklisted = !utils.isOneOf(o.description, appliedBlackList);
+    const descNotBlacklisted = !utils.isOneOf(o.description, appliedBlackList);
-  return titleNotBlacklisted && descNotBlacklisted;
+    return titleNotBlacklisted && descNotBlacklisted;
 }
+
 const config = {
-  url: null,
+    url: null,
-  crawlContainer: '.js-serp-item',
+    crawlContainer: '.js-serp-item',
-  sortByDateParam: 's=most_recently_updated_first',
+    sortByDateParam: 's=most_recently_updated_first',
-  crawlFields: {
+    crawlFields: {
-    id: '@id',
+        id: '.js-bookmark-btn@data-id',
-    price: 'div.item__spec.item-spec-price | trim',
+        price: 'div.align-items-start div:first-child | trim',
-    size: 'div.item__spec.item-spec-area | trim',
+        size: 'div.align-items-start div:nth-child(3) | trim',
-    title: 'a.js-item-title-link@title',
+        title: '.card-title h2 | trim',
-    address: 'div.item__locality | removeNewline | trim',
+        link: '.ci-search-result__link@href',
-    description: 'div.item__main-info-points.clearfix p small | removeNewline | trim',
+        description: '.js-show-more-item-sm | removeNewline | trim',
-  },
+    },
-  paginate: 'li.page-item.pagination__item a.page-link@href',
+    paginate: 'li.page-item.pagination__item a.page-link@href',
-  normalize: normalize,
+    normalize: normalize,
-  filter: applyBlacklist,
+    filter: applyBlacklist,
 };
 export const init = (sourceConfig, blacklist) => {
-  config.enabled = sourceConfig.enabled;
+    config.enabled = sourceConfig.enabled;
-  config.url = sourceConfig.url;
+    config.url = sourceConfig.url;
-  appliedBlackList = blacklist || [];
+    appliedBlackList = blacklist || [];
 };
 export const metaInformation = {
-  name: 'Immo Südwest Presse',
+    name: 'Immo Südwest Presse',
-  baseUrl: 'https://immo.swp.de/',
+    baseUrl: 'https://immo.swp.de/',
-  id: 'immoswp',
+    id: 'immoswp',
 };
-export { config };
+export {config};

lib/provider/immowelt.js

@@ -1,24 +1,30 @@
-import utils from '../utils.js';
+import utils, { buildHash } from '../utils.js';
+
 let appliedBlackList = [];
+
 function normalize(o) {
-  return o;
+  const id = buildHash(o.id, o.price);
+  return Object.assign(o, { id });
 }
+
 function applyBlacklist(o) {
   const titleNotBlacklisted = !utils.isOneOf(o.title, appliedBlackList);
   const descNotBlacklisted = !utils.isOneOf(o.description, appliedBlackList);
   return titleNotBlacklisted && descNotBlacklisted;
 }
+
 const config = {
   url: null,
-  crawlContainer: "div[class^='EstateItem-']",
+  crawlContainer:
-  sortByDateParam: 'sd=DESC&sf=TIMESTAMP',
+    'div[data-testid="serp-card-testid"]:not(div[data-testid="serp-enlargementlist-testid"] div[data-testid="serp-card-testid"])',
+  sortByDateParam: 'order=DateDesc',
   crawlFields: {
     id: 'a@id',
-    price: "div[class^='KeyFacts-'] [data-test='price'] | removeNewline | trim",
+    price: 'div[data-testid="cardmfe-price-testid"] | removeNewline | trim',
-    size: "div[class^='KeyFacts-'] [data-test='area'] | removeNewline | trim",
+    size: 'div[data-testid="cardmfe-keyfacts-testid"] | removeNewline | trim',
-    title: "div[class^='FactsMain-'] h2",
+    title: '.css-1cbj9xw',
     link: 'a@href',
-    address: "div[class^='estateFacts-'] span | removeNewline | trim",
+    address: 'div[data-testid="cardmfe-description-box-address"] | removeNewline | trim',
   },
   paginate: '#pnlPaging #nlbPlus@href',
   normalize: normalize,

lib/provider/kleinanzeigen.js

@@ -1,44 +1,49 @@
-import utils from '../utils.js';
+import utils, {buildHash} from '../utils.js';
+
 let appliedBlackList = [];
 let appliedBlacklistedDistricts = [];
+
 function normalize(o) {
-  const size = o.size || '--- m²';
+    const size = o.size || '--- m²';
-  return Object.assign(o, { size });
+    const id = buildHash(o.id, o.price);
+    return Object.assign(o, {id, size});
 }
+
 function applyBlacklist(o) {
-  const titleNotBlacklisted = !utils.isOneOf(o.title, appliedBlackList);
+    const titleNotBlacklisted = !utils.isOneOf(o.title, appliedBlackList);
-  const descNotBlacklisted = !utils.isOneOf(o.description, appliedBlackList);
+    const descNotBlacklisted = !utils.isOneOf(o.description, appliedBlackList);
-  const isBlacklistedDistrict =
+    const isBlacklistedDistrict =
-    appliedBlacklistedDistricts.length === 0 ? false : utils.isOneOf(o.description, appliedBlacklistedDistricts);
+        appliedBlacklistedDistricts.length === 0 ? false : utils.isOneOf(o.description, appliedBlacklistedDistricts);
-  return !isBlacklistedDistrict && titleNotBlacklisted && descNotBlacklisted;
+    return !isBlacklistedDistrict && titleNotBlacklisted && descNotBlacklisted;
 }
+
 const config = {
-  url: null,
+    url: null,
-  crawlContainer: '#srchrslt-adtable .ad-listitem ',
+    crawlContainer: '#srchrslt-adtable .ad-listitem ',
-  //sort by date is standard oO
+    //sort by date is standard oO
-  sortByDateParam: null,
+    sortByDateParam: null,
-  crawlFields: {
+    crawlFields: {
-    id: '.aditem@data-adid | int',
+        id: '.aditem@data-adid | int',
-    price: '.aditem-main--middle--price-shipping--price | removeNewline | trim',
+        price: '.aditem-main--middle--price-shipping--price | removeNewline | trim',
-    size: '.aditem-main .text-module-end span:nth-child(2) | removeNewline | trim',
+        size: '.aditem-main .text-module-end span:nth-child(2) | removeNewline | trim',
-    title: '.aditem-main .text-module-begin a | removeNewline | trim',
+        title: '.aditem-main .text-module-begin a | removeNewline | trim',
-    link: '.aditem-main .text-module-begin a@href | removeNewline | trim',
+        link: '.aditem-main .text-module-begin a@href | removeNewline | trim',
-    description: '.aditem-main p:not(.text-module-end) | removeNewline | trim',
+        description: '.aditem-main p:not(.text-module-end) | removeNewline | trim',
-    address: '.aditem-main--top--left | trim | removeNewline',
+        address: '.aditem-main--top--left | trim | removeNewline',
-  },
+    },
-  paginate: '#srchrslt-pagination .pagination-next@href',
+    paginate: '#srchrslt-pagination .pagination-next@href',
-  normalize: normalize,
+    normalize: normalize,
-  filter: applyBlacklist,
+    filter: applyBlacklist,
 };
 export const metaInformation = {
-  name: 'Ebay Kleinanzeigen',
+    name: 'Ebay Kleinanzeigen',
-  baseUrl: 'https://www.kleinanzeigen.de/',
+    baseUrl: 'https://www.kleinanzeigen.de/',
-  id: 'kleinanzeigen',
+    id: 'kleinanzeigen',
 };
 export const init = (sourceConfig, blacklist, blacklistedDistricts) => {
-  config.enabled = sourceConfig.enabled;
+    config.enabled = sourceConfig.enabled;
-  config.url = sourceConfig.url;
+    config.url = sourceConfig.url;
-  appliedBlacklistedDistricts = blacklistedDistricts || [];
+    appliedBlacklistedDistricts = blacklistedDistricts || [];
-  appliedBlackList = blacklist || [];
+    appliedBlackList = blacklist || [];
 };
-export { config };
+export {config};

lib/provider/neubauKompass.js

@@ -1,34 +1,44 @@
-import utils from '../utils.js';
+import utils, {buildHash} from '../utils.js';
+
 let appliedBlackList = [];
+
+function nullOrEmpty(val) {
+    return val == null || val.length === 0;
+}
+
 function normalize(o) {
-  return o;
+    const link = nullOrEmpty(o.link) ? 'NO LINK' : `https://www.neubaukompass.de${o.link.substring(o.link.indexOf('/neubau'))}`;
+    const id = buildHash(o.id, o.price);
+    return Object.assign(o, {id, link});
 }
+
 function applyBlacklist(o) {
-  return !utils.isOneOf(o.title, appliedBlackList);
+    return !utils.isOneOf(o.title, appliedBlackList);
 }
+
 const config = {
-  url: null,
+    url: null,
-  crawlContainer: '.nbk-container >div article',
+    crawlContainer: '.nbk-container >div article',
-  sortByDateParam: 'Sortierung=Id&Richtung=DESC',
+    sortByDateParam: 'Sortierung=Id&Richtung=DESC',
-  crawlFields: {
+    crawlFields: {
-    id: '@id',
+        id: '@id',
-    title: 'a.nbk-truncate@title | removeNewline | trim',
+        title: 'a.nbk-truncate@title | removeNewline | trim',
-    link: 'a.nbk-truncate@href',
+        link: 'a.nbk-truncate@href',
-    address: 'p.nbk-truncate | removeNewline | trim',
+        address: 'p.nbk-truncate | removeNewline | trim',
-    price: 'p.nbk-mb-0 | removeNewline | trim',
+        price: 'p.nbk-mb-0 | removeNewline | trim',
-  },
+    },
-  paginate: '.numbered-pager__bottom .numbered-pager--info li:nth-child(2) a@href',
+    paginate: '.numbered-pager__bottom .numbered-pager--info li:nth-child(2) a@href',
-  normalize: normalize,
+    normalize: normalize,
-  filter: applyBlacklist,
+    filter: applyBlacklist,
 };
 export const init = (sourceConfig, blacklist) => {
-  config.enabled = sourceConfig.enabled;
+    config.enabled = sourceConfig.enabled;
-  config.url = sourceConfig.url;
+    config.url = sourceConfig.url;
-  appliedBlackList = blacklist || [];
+    appliedBlackList = blacklist || [];
 };
 export const metaInformation = {
-  name: 'Neubau Kompass',
+    name: 'Neubau Kompass',
-  baseUrl: 'https://www.neubaukompass.de/',
+    baseUrl: 'https://www.neubaukompass.de/',
-  id: 'neubauKompass',
+    id: 'neubauKompass',
 };
-export { config };
+export {config};

lib/provider/wgGesucht.js

@@ -1,36 +1,41 @@
-import utils from '../utils.js';
+import utils, {buildHash} from '../utils.js';
+
 let appliedBlackList = [];
+
 function normalize(o) {
-  return o;
+    const id = buildHash(o.id, o.price);
+    return Object.assign(o, {id});
 }
+
 function applyBlacklist(o) {
-  const titleNotBlacklisted = !utils.isOneOf(o.title, appliedBlackList);
+    const titleNotBlacklisted = !utils.isOneOf(o.title, appliedBlackList);
-  const descNotBlacklisted = !utils.isOneOf(o.description, appliedBlackList);
+    const descNotBlacklisted = !utils.isOneOf(o.description, appliedBlackList);
-  return o.id != null && titleNotBlacklisted && descNotBlacklisted;
+    return o.id != null && titleNotBlacklisted && descNotBlacklisted;
 }
+
 const config = {
-  url: null,
+    url: null,
-  crawlContainer: '#main_column .wgg_card',
+    crawlContainer: '#main_column .wgg_card',
-  sortByDateParam: 'sort_column=0&sort_order=0',
+    sortByDateParam: 'sort_column=0&sort_order=0',
-  crawlFields: {
+    crawlFields: {
-    id: '@data-id',
+        id: '@data-id',
-    details: '.row .noprint .col-xs-11 |removeNewline |trim',
+        details: '.row .noprint .col-xs-11 |removeNewline |trim',
-    price: '.middle .col-xs-3 |removeNewline |trim',
+        price: '.middle .col-xs-3 |removeNewline |trim',
-    size: '.middle .text-right |removeNewline |trim',
+        size: '.middle .text-right |removeNewline |trim',
-    title: '.truncate_title a |removeNewline |trim',
+        title: '.truncate_title a |removeNewline |trim',
-    link: '.truncate_title a@href',
+        link: '.truncate_title a@href',
-  },
+    },
-  normalize: normalize,
+    normalize: normalize,
-  filter: applyBlacklist,
+    filter: applyBlacklist,
 };
 export const init = (sourceConfig, blacklist) => {
-  config.enabled = sourceConfig.enabled;
+    config.enabled = sourceConfig.enabled;
-  config.url = sourceConfig.url;
+    config.url = sourceConfig.url;
-  appliedBlackList = blacklist || [];
+    appliedBlackList = blacklist || [];
 };
 export const metaInformation = {
-  name: 'Wg gesucht',
+    name: 'Wg gesucht',
-  baseUrl: 'https://www.wg-gesucht.de/',
+    baseUrl: 'https://www.wg-gesucht.de/',
-  id: 'wgGesucht',
+    id: 'wgGesucht',
 };
-export { config };
+export {config};

lib/services/requestDriver.js

@@ -24,13 +24,16 @@ function makeDriver(headers = {}) {
         },
       });
       const result = await response.text();
+      if (EXPECTED_STATUS_CODES.includes(response.status)) {
+        throw new Error(`${response.status}`);
+      }
       if (cookies.length === 0) {
         cookies = response.headers.raw()['set-cookie'] || [];
       }
       callback(null, result);
     } catch (exception) {
       /* eslint-disable no-console */
-      if (!EXPECTED_STATUS_CODES.includes(exception.response?.status)) {
+      if (!EXPECTED_STATUS_CODES.includes(exception.response?.status) && !EXPECTED_STATUS_CODES.includes(Number(exception.message))) {
         console.error(`Error while trying to scrape data from scraping ant. Received error: ${exception.message}`);
         callback(null, []);
         return;

lib/services/scrapingAnt.js

@@ -1,5 +1,6 @@
 import { metaInformation as immoScoutInfo } from '../provider/immoscout.js';
 import { metaInformation as immoNetInfo } from '../provider/immonet.js';
+import { metaInformation as neuBauCompassInfo } from '../provider/neubauKompass.js';
 import { config } from '../utils.js';
 
 const additionalImmonetUrlParams = `&wait_for_selector=.content-wrapper-tiles&js_snippet=${Buffer.from(
@@ -7,7 +8,7 @@ const additionalImmonetUrlParams = `&wait_for_selector=.content-wrapper-tiles&js
 ).toString('base64')}`;
 
 const needScrapingAnt = (id) => {
-  return id.toLowerCase() === immoScoutInfo.id || id.toLowerCase() === immoNetInfo.id;
+  return id.toLowerCase() === immoScoutInfo.id || id.toLowerCase() === immoNetInfo.id || id.toLowerCase() === neuBauCompassInfo.id.toLowerCase();
 };
 export const transformUrlForScrapingAnt = (url, id) => {
   let urlParams = '';

lib/utils.js

@@ -1,51 +1,69 @@
-import { dirname } from 'node:path';
+import {dirname} from 'node:path';
-import { fileURLToPath } from 'node:url';
+import {fileURLToPath} from 'node:url';
-import { readFile } from 'fs/promises';
+import {readFile} from 'fs/promises';
+import {createHash} from 'crypto';
 
 function isOneOf(word, arr) {
-  if (arr == null || arr.length === 0) {
+    if (arr == null || arr.length === 0) {
-    return false;
+        return false;
-  }
+    }
-  const expression = String.raw`\b(${arr.join('|')})\b`;
+    const expression = String.raw`\b(${arr.join('|')})\b`;
-  const blacklist = new RegExp(expression, 'ig');
+    const blacklist = new RegExp(expression, 'ig');
-  return blacklist.test(word);
+    return blacklist.test(word);
 }
+
 function nullOrEmpty(val) {
-  return val == null || val.length === 0;
+    return val == null || val.length === 0;
 }
+
 function timeStringToMs(timeString, now) {
-  const d = new Date(now);
+    const d = new Date(now);
-  const parts = timeString.split(':');
+    const parts = timeString.split(':');
-  d.setHours(parts[0]);
+    d.setHours(parts[0]);
-  d.setMinutes(parts[1]);
+    d.setMinutes(parts[1]);
-  d.setSeconds(0);
+    d.setSeconds(0);
-  return d.getTime();
+    return d.getTime();
 }
+
 function duringWorkingHoursOrNotSet(config, now) {
-  const { workingHours } = config;
+    const {workingHours} = config;
-  if (workingHours == null || nullOrEmpty(workingHours.from) || nullOrEmpty(workingHours.to)) {
+    if (workingHours == null || nullOrEmpty(workingHours.from) || nullOrEmpty(workingHours.to)) {
-    return true;
+        return true;
-  }
+    }
-  const toDate = timeStringToMs(workingHours.to, now);
+    const toDate = timeStringToMs(workingHours.to, now);
-  const fromDate = timeStringToMs(workingHours.from, now);
+    const fromDate = timeStringToMs(workingHours.from, now);
-  return fromDate <= now && toDate >= now;
+    return fromDate <= now && toDate >= now;
 }
 
 function getDirName() {
-  return dirname(fileURLToPath(import.meta.url));
+    return dirname(fileURLToPath(import.meta.url));
+}
+
+function buildHash(...inputs) {
+    if (inputs == null) {
+        return null;
+    }
+    const cleaned = inputs.filter(i => i != null && i.length > 0);
+    if (cleaned.length === 0) {
+        return null;
+    }
+    return createHash('sha256')
+        .update(cleaned.join(','))
+        .digest('hex');
 }
 
 const config = JSON.parse(await readFile(new URL('../conf/config.json', import.meta.url)));
 
-export { isOneOf };
+export {isOneOf};
-export { nullOrEmpty };
+export {nullOrEmpty};
-export { duringWorkingHoursOrNotSet };
+export {duringWorkingHoursOrNotSet};
-export { getDirName };
+export {getDirName};
-export { config };
+export {config};
+export {buildHash};
 export default {
-  isOneOf,
+    isOneOf,
-  nullOrEmpty,
+    nullOrEmpty,
-  duringWorkingHoursOrNotSet,
+    duringWorkingHoursOrNotSet,
-  getDirName,
+    getDirName,
-  config,
+    config,
 };

package.json

@@ -1,6 +1,6 @@
 {
   "name": "fredy",
-  "version": "8.0.4",
+  "version": "10.2.0",
   "description": "[F]ind [R]eal [E]states [d]amn eas[y].",
   "scripts": {
     "start": "node index.js",
@@ -45,7 +45,7 @@
   },
   "license": "MIT",
   "engines": {
-    "node": ">=16.0.0",
+    "node": ">=20.0.0",
     "npm": ">=7.0.0"
   },
   "browserslist": [
@@ -55,54 +55,54 @@
     "Firefox ESR"
   ],
   "dependencies": {
-    "@douyinfe/semi-ui": "2.52.0",
+    "@douyinfe/semi-ui": "2.68.3",
     "@rematch/core": "2.2.0",
     "@rematch/loading": "2.1.2",
-    "@sendgrid/mail": "8.1.0",
+    "@sendgrid/mail": "8.1.4",
-    "@vitejs/plugin-react": "4.2.1",
+    "@vitejs/plugin-react": "4.3.3",
-    "better-sqlite3": "8.6.0",
+    "better-sqlite3": "^11.5.0",
-    "body-parser": "1.20.2",
+    "body-parser": "1.20.3",
     "cookie-session": "2.1.0",
     "handlebars": "4.7.8",
-    "highcharts": "11.3.0",
+    "highcharts": "11.4.8",
     "highcharts-react-official": "3.2.1",
     "lodash": "4.17.21",
     "lowdb": "6.0.1",
     "markdown": "^0.5.0",
-    "nanoid": "5.0.5",
+    "nanoid": "5.0.8",
     "node-fetch": "3.3.2",
-    "node-mailjet": "6.0.5",
+    "node-mailjet": "6.0.6",
-    "query-string": "8.2.0",
+    "query-string": "9.1.1",
-    "react": "18.2.0",
+    "react": "18.3.1",
-    "react-dom": "18.2.0",
+    "react-dom": "18.3.1",
-    "react-redux": "9.1.0",
+    "react-redux": "9.1.2",
     "react-router": "5.2.1",
     "react-router-dom": "5.3.0",
     "redux": "5.0.1",
     "redux-thunk": "3.1.0",
-    "restana": "4.9.7",
+    "restana": "4.9.9",
-    "serve-static": "1.15.0",
+    "serve-static": "1.16.2",
     "slack": "11.0.2",
     "string-similarity": "^4.0.4",
-    "vite": "5.0.12",
+    "vite": "5.4.10",
     "x-ray": "2.3.4"
   },
   "devDependencies": {
-    "@babel/core": "7.23.9",
+    "@babel/core": "7.26.0",
-    "@babel/eslint-parser": "7.23.10",
+    "@babel/eslint-parser": "7.25.9",
-    "@babel/preset-env": "7.23.9",
+    "@babel/preset-env": "7.26.0",
-    "@babel/preset-react": "7.23.3",
+    "@babel/preset-react": "7.25.9",
-    "chai": "5.0.3",
+    "chai": "5.1.2",
     "eslint": "8.56.0",
     "eslint-config-prettier": "8.8.0",
-    "eslint-plugin-react": "7.33.2",
+    "eslint-plugin-react": "7.37.2",
-    "esmock": "2.6.3",
+    "esmock": "2.6.9",
     "history": "5.3.0",
     "husky": "4.3.8",
     "less": "4.2.0",
     "lint-staged": "13.2.2",
-    "mocha": "10.2.0",
+    "mocha": "10.8.2",
-    "prettier": "3.2.5",
+    "prettier": "3.3.3",
     "redux-logger": "3.0.6"
   }
 }

test/provider/einsAImmobilien.test.js

@@ -20,7 +20,7 @@ describe('#einsAImmobilien testsuite()', () => {
         expect(notificationObj.serviceName).to.equal('einsAImmobilien');
         notificationObj.payload.forEach((notify) => {
           /** check the actual structure **/
-          expect(notify.id).to.be.a('number');
+          expect(notify.id).to.be.a('string');
           expect(notify.price).to.be.a('string');
           expect(notify.size).to.be.a('string');
           expect(notify.title).to.be.a('string');

test/provider/immoswp.test.js

@@ -25,12 +25,10 @@ describe('#immoswp testsuite()', () => {
           expect(notify.size).to.be.a('string');
           expect(notify.title).to.be.a('string');
           expect(notify.link).to.be.a('string');
-          expect(notify.address).to.be.a('string');
           /** check the values if possible **/
           expect(notify.price).that.does.include('€');
           expect(notify.title).to.be.not.empty;
           expect(notify.link).that.does.include('https://immo.swp.de');
-          expect(notify.address).to.be.not.empty;
         });
         resolve();
       });

test/provider/kleinanzeigen.test.js

@@ -20,7 +20,7 @@ describe('#kleinanzeigen testsuite()', () => {
         expect(notificationObj.serviceName).to.equal('kleinanzeigen');
         notificationObj.payload.forEach((notify) => {
           /** check the actual structure **/
-          expect(notify.id).to.be.a('number');
+          expect(notify.id).to.be.a('string');
           expect(notify.title).to.be.a('string');
           expect(notify.link).to.be.a('string');
           expect(notify.address).to.be.a('string');

test/provider/neubauKompass.test.js

@@ -1,36 +1,44 @@
 import * as similarityCache from '../../lib/services/similarity-check/similarityCache.js';
-import { get } from '../mocks/mockNotification.js';
+import {get} from '../mocks/mockNotification.js';
-import { mockFredy, providerConfig } from '../utils.js';
+import {mockFredy, providerConfig} from '../utils.js';
-import { expect } from 'chai';
+import {expect} from 'chai';
 import * as provider from '../../lib/provider/neubauKompass.js';
+import * as scrapingAnt from '../../lib/services/scrapingAnt.js';
 
 describe('#neubauKompass testsuite()', () => {
-  after(() => {
+    after(() => {
-    similarityCache.stopCacheCleanup();
+        similarityCache.stopCacheCleanup();
-  });
+    });
-  provider.init(providerConfig.neubauKompass, [], []);
+    provider.init(providerConfig.neubauKompass, [], []);
-  it('should test neubauKompass provider', async () => {
+    it('should test neubauKompass provider', async () => {
-    const Fredy = await mockFredy();
+        const Fredy = await mockFredy();
-    return await new Promise((resolve) => {
+        return await new Promise((resolve) => {
-      const fredy = new Fredy(provider.config, null, provider.metaInformation.id, 'neubauKompass', similarityCache);
+            if (!scrapingAnt.isScrapingAntApiKeySet()) {
-      fredy.execute().then((listing) => {
+                /* eslint-disable no-console */
-        expect(listing).to.be.a('array');
+                console.info('Skipping Neubaukompass test as ScrapingAnt Api Key is not set.');
-        const notificationObj = get();
+                /* eslint-enable no-console */
-        expect(notificationObj.serviceName).to.equal('neubauKompass');
+                resolve();
-        notificationObj.payload.forEach((notify) => {
+                return;
-          expect(notify).to.be.a('object');
+            }
-          /** check the actual structure **/
+            const fredy = new Fredy(provider.config, null, provider.metaInformation.id, 'neubauKompass', similarityCache);
-          expect(notify.id).to.be.a('string');
+            fredy.execute().then((listing) => {
-          expect(notify.title).to.be.a('string');
+                expect(listing).to.be.a('array');
-          expect(notify.link).to.be.a('string');
+                const notificationObj = get();
-          expect(notify.address).to.be.a('string');
+                expect(notificationObj.serviceName).to.equal('neubauKompass');
-          /** check the values if possible **/
+                notificationObj.payload.forEach((notify) => {
-          expect(notify.title).to.be.not.empty;
+                    expect(notify).to.be.a('object');
-          expect(notify.link).that.does.include('https://www.neubaukompass.de');
+                    /** check the actual structure **/
-          expect(notify.address).to.be.not.empty;
+                    expect(notify.id).to.be.a('string');
-        });
+                    expect(notify.title).to.be.a('string');
-        resolve();
+                    expect(notify.link).to.be.a('string');
-      });
+                    expect(notify.address).to.be.a('string');
+                    /** check the values if possible **/
+                    expect(notify.title).to.be.not.empty;
+                    expect(notify.link).that.does.include('https://www.neubaukompass.de');
+                    expect(notify.address).to.be.not.empty;
+                });
+                resolve();
+            });
+        });
     });
-  });
 });

test/provider/testProvider.json

@@ -13,7 +13,7 @@
     "enabled": true
   },
   "immowelt": {
-    "url": "https://www.immowelt.de/liste/duesseldorf/wohnungen/kaufen?d=true&rmi=3&sd=DESC&sf=TIMESTAMP&sp=1",
+    "url": "https://www.immowelt.de/classified-search?distributionTypes=Buy,Buy_Auction,Compulsory_Auction&estateTypes=House,Apartment&locations=AD08DE2350",
     "enabled": true
   },
   "immoscout": {

test/queryStringMutator/testData.json

@@ -1,7 +1,7 @@
 [
   {
-    "url": "https://www.immowelt.de/liste/40589/wohnungen/mieten?d=true&sd=DESC&sf=PRIMARY_PRICE_AMOUNT&sp=1",
+    "url": "https://www.immowelt.de/classified-search?distributionTypes=Buy,Buy_Auction,Compulsory_Auction&estateTypes=House,Apartment&locations=AD08DE2350",
-    "shouldBecome": "https://www.immowelt.de/liste/40589/wohnungen/mieten?d=true&sd=DESC&sf=TIMESTAMP&sp=1",
+    "shouldBecome": "https://www.immowelt.de/classified-search?distributionTypes=Buy,Buy_Auction,Compulsory_Auction&estateTypes=House,Apartment&locations=AD08DE2350&order=DateDesc",
     "id": "immowelt"
   },
   {

test/utils/utils.test.js

@@ -0,0 +1,16 @@
+import { expect } from 'chai';
+import {buildHash} from '../../lib/utils.js';
+
+describe('utilsCheck', () => {
+  describe('#utilsCheck()', () => {
+      it('should be null when null input', () => {
+          expect(buildHash(null)).to.be.null;
+      });
+      it('should be null when null empty', () => {
+          expect(buildHash('')).to.be.null;
+      });
+      it('should return a value', () => {
+          expect(buildHash('bla', '', null)).to.be.a.string;
+      });
+  });
+});

ui/src/views/generalSettings/GeneralSettings.jsx

@@ -184,8 +184,7 @@ const GeneralSettings = function GeneralSettings() {
                     more likely to fail, but they are cheaper. A call with a datacenter proxy cost 10 credits.
                     <h4>Residential-Proxy</h4>
                     High-quality proxy server located in one of the real people houses across the world. Datacenter
-                    proxies are faster and more likely to success, but they are more expensive. A call with a datacenter
+                    proxies are faster and more likely to success, but they are more expensive.
-                    proxy cost 250 credits.
                     <br />
                     <br />
                     <b>

ui/src/views/jobs/ProcessingTimes.jsx

@@ -45,7 +45,7 @@ export default function ProcessingTimes({ processingTimes }) {
               {format(new Date(processingTimes.scrapingAntData.end_date))}
               <br />
               Credits: {processingTimes.scrapingAntData.remained_credits}/
-              {processingTimes.scrapingAntData.plan_total_credits} (250 credits per call)
+              {processingTimes.scrapingAntData.plan_total_credits}
             </p>
             If you want to scrape Immoscout or Immonet more often, you have to purchase a premium account of{' '}
             <a href="https://scrapingant.com/" target="_blank" rel="noreferrer">

ui/src/views/jobs/mutation/components/provider/ProviderMutator.jsx

@@ -101,7 +101,7 @@ export default function ProviderMutator({ onVisibilityChanged, visible = false,
         description={
           <div>
             <p>
-              If you chose Immoscout or Immonet as a provider, make sure to also add the scrapingAnt apiKey to the config.json.
+              If you chose Immoscout, Immonet or NeubauKompass as a provider, make sure to also add the scrapingAnt apiKey to the config.json.
               (See readme)
             </p>
             <p>