building multi platform docker images (#101)

* 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/i386, linux/arm64

Dockerfile

@@ -1,19 +1,20 @@
-# syntax=docker/dockerfile:1.3
-FROM node:18-alpine AS builder
-COPY --chown=1000:1000 . /fredy
+FROM node:18
+
 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" ]
-WORKDIR  /fredy
-CMD node index.js --no-daemon
+
+CMD pm2-runtime index.js

README.md

@@ -78,15 +78,20 @@ yarn run test
 # Architecture
 ![Architecture](/doc/architecture.jpg "Architecture")
 
-### Immoscout / Immonet
-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.
+### Immoscout / Immonet / NeubauKompass
+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/notification/adapter/apprise.js

@@ -3,7 +3,7 @@ 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) => {
@@ -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/provider/immoscout.js

@@ -6,7 +6,7 @@ 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 });
 }
 function applyBlacklist(o) {

lib/provider/immoswp.js

@@ -1,44 +1,47 @@
 import utils 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 price = (o.price || '--- €').replace('Preis auf Anfrage', '--- €');
-  const address = o.address || 'No address available';
-  const title = o.title || 'No title available';
-  const link = `https://immo.swp.de/immobilien/${id}`;
-  const description = o.description;
-  return Object.assign(o, { id, address, price, size, title, link, description });
+    const id = o.id.substring(o.id.indexOf('-') + 1, o.id.length);
+    const size = o.size || 'N/A m²';
+    const price = (o.price || '--- €').replace('Preis auf Anfrage', '--- €');
+    const title = o.title || 'No title available';
+    const link = `https://immo.swp.de/immobilien/${id}`;
+    const description = o.description;
+    return Object.assign(o, {id, price, size, title, link, description});
 }
+
 function applyBlacklist(o) {
-  const titleNotBlacklisted = !utils.isOneOf(o.title, appliedBlackList);
-  const descNotBlacklisted = !utils.isOneOf(o.description, appliedBlackList);
-  return titleNotBlacklisted && descNotBlacklisted;
+    const titleNotBlacklisted = !utils.isOneOf(o.title, appliedBlackList);
+    const descNotBlacklisted = !utils.isOneOf(o.description, appliedBlackList);
+    return titleNotBlacklisted && descNotBlacklisted;
 }
+
 const config = {
-  url: null,
-  crawlContainer: '.js-serp-item',
-  sortByDateParam: 's=most_recently_updated_first',
-  crawlFields: {
-    id: '@id',
-    price: 'div.item__spec.item-spec-price | trim',
-    size: 'div.item__spec.item-spec-area | trim',
-    title: 'a.js-item-title-link@title',
-    address: 'div.item__locality | removeNewline | trim',
-    description: 'div.item__main-info-points.clearfix p small | removeNewline | trim',
-  },
-  paginate: 'li.page-item.pagination__item a.page-link@href',
-  normalize: normalize,
-  filter: applyBlacklist,
+    url: null,
+    crawlContainer: '.js-serp-item',
+    sortByDateParam: 's=most_recently_updated_first',
+    crawlFields: {
+        id: '.js-bookmark-btn@data-id',
+        price: 'div.align-items-start div:first-child | trim',
+        size: 'div.align-items-start div:nth-child(3) | trim',
+        title: '.card-title h2 | trim',
+        link: '.ci-search-result__link@href',
+        description: '.js-show-more-item-sm | removeNewline | trim',
+    },
+    paginate: 'li.page-item.pagination__item a.page-link@href',
+    normalize: normalize,
+    filter: applyBlacklist,
 };
 export const init = (sourceConfig, blacklist) => {
-  config.enabled = sourceConfig.enabled;
-  config.url = sourceConfig.url;
-  appliedBlackList = blacklist || [];
+    config.enabled = sourceConfig.enabled;
+    config.url = sourceConfig.url;
+    appliedBlackList = blacklist || [];
 };
 export const metaInformation = {
-  name: 'Immo Südwest Presse',
-  baseUrl: 'https://immo.swp.de/',
-  id: 'immoswp',
+    name: 'Immo Südwest Presse',
+    baseUrl: 'https://immo.swp.de/',
+    id: 'immoswp',
 };
-export { config };
+export {config};

lib/provider/neubauKompass.js

@@ -1,7 +1,11 @@
 import utils 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'))}`;
+  return {...o, link};
 }
 function applyBlacklist(o) {
   return !utils.isOneOf(o.title, appliedBlackList);

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 = '';

package.json

@@ -1,6 +1,6 @@
 {
   "name": "fredy",
-  "version": "8.0.4",
+  "version": "8.1.0",
   "description": "[F]ind [R]eal [E]states [d]amn eas[y].",
   "scripts": {
     "start": "node index.js",
@@ -55,54 +55,54 @@
     "Firefox ESR"
   ],
   "dependencies": {
-    "@douyinfe/semi-ui": "2.52.0",
+    "@douyinfe/semi-ui": "2.62.1",
     "@rematch/core": "2.2.0",
     "@rematch/loading": "2.1.2",
-    "@sendgrid/mail": "8.1.0",
-    "@vitejs/plugin-react": "4.2.1",
+    "@sendgrid/mail": "8.1.3",
+    "@vitejs/plugin-react": "4.3.1",
     "better-sqlite3": "8.6.0",
     "body-parser": "1.20.2",
     "cookie-session": "2.1.0",
     "handlebars": "4.7.8",
-    "highcharts": "11.3.0",
+    "highcharts": "11.4.6",
     "highcharts-react-official": "3.2.1",
     "lodash": "4.17.21",
     "lowdb": "6.0.1",
     "markdown": "^0.5.0",
-    "nanoid": "5.0.5",
+    "nanoid": "5.0.7",
     "node-fetch": "3.3.2",
     "node-mailjet": "6.0.5",
     "query-string": "8.2.0",
-    "react": "18.2.0",
-    "react-dom": "18.2.0",
-    "react-redux": "9.1.0",
+    "react": "18.3.1",
+    "react-dom": "18.3.1",
+    "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",
     "slack": "11.0.2",
     "string-similarity": "^4.0.4",
-    "vite": "5.0.12",
+    "vite": "5.3.4",
     "x-ray": "2.3.4"
   },
   "devDependencies": {
-    "@babel/core": "7.23.9",
-    "@babel/eslint-parser": "7.23.10",
-    "@babel/preset-env": "7.23.9",
-    "@babel/preset-react": "7.23.3",
-    "chai": "5.0.3",
+    "@babel/core": "7.24.9",
+    "@babel/eslint-parser": "7.24.8",
+    "@babel/preset-env": "7.24.8",
+    "@babel/preset-react": "7.24.7",
+    "chai": "5.1.1",
     "eslint": "8.56.0",
     "eslint-config-prettier": "8.8.0",
-    "eslint-plugin-react": "7.33.2",
-    "esmock": "2.6.3",
+    "eslint-plugin-react": "7.35.0",
+    "esmock": "2.6.7",
     "history": "5.3.0",
     "husky": "4.3.8",
     "less": "4.2.0",
     "lint-staged": "13.2.2",
-    "mocha": "10.2.0",
-    "prettier": "3.2.5",
+    "mocha": "10.7.0",
+    "prettier": "3.3.3",
     "redux-logger": "3.0.6"
   }
 }

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/neubauKompass.test.js

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

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
-                    proxy cost 250 credits.
+                    proxies are faster and more likely to success, but they are more expensive.
                     <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>