Feature/spec filter (#276)

* feat(): create map component, add area filtering to the job config

* feat(): filter listings by area filter

* chore(): cleanup

* feat(): solve feedback

* feat(): solve most providers

* feat(): solve maybe other providers

* feat(): add specFilter config, also add rooms to listing

* feat(): change tests

* feat(): fix kleinanzeigen parser

* feat(): add spec filter switch for listing overviiews

* feat(): add rooms and size to the overview and detail of a listing

* feat(): rem label

* feat(): add types, update providers, they now return specs as numbers

* feat(): add jsonconfig to enable type checks

* feat: add type for prividerConfig, add fieldNames per provider

* feat: fix tests, provider, add formatListing

* chore: remov duplicates

* feat(): fix tests

* feat: fix immoscout

* chore: geojson typing

* feat: solve requested changes

lib/provider/wgGesucht.js

@@ -5,9 +5,12 @@
 
 import { isOneOf, buildHash } from '../utils.js';
 import checkIfListingIsActive from '../services/listings/listingActiveTester.js';
+import { extractNumber } from '../utils/extract-number.js';
 import puppeteerExtractor from '../services/extractor/puppeteerExtractor.js';
 import * as cheerio from 'cheerio';
 import logger from '../services/logger.js';
+/** @import { ParsedListing } from '../types/listing.js' */
+/** @import { ProviderConfig } from '../types/providerConfig.js' */
 
 let appliedBlackList = [];
 
@@ -32,20 +35,39 @@ async function fetchDetails(listing, browser) {
     return listing;
   }
 }
-
+/**
+ * @param {any} o
+ * @returns {ParsedListing}
+ */
 function normalize(o) {
   const id = buildHash(o.id, o.price);
   const link = `https://www.wg-gesucht.de${o.link}`;
   const image = o.image != null ? o.image.replace('small', 'large') : null;
-  return Object.assign(o, { id, link, image });
+  const [rooms, city, road] = o.details?.split(' | ') || [];
+  return {
+    id,
+    link,
+    title: o.title || '',
+    price: extractNumber(o.price),
+    size: extractNumber(o.size),
+    rooms: extractNumber(rooms),
+    address: `${city}, ${road}`,
+    image,
+    description: o.description,
+  };
 }
 
+/**
+ * @param {ParsedListing} o
+ * @returns {boolean}
+ */
 function applyBlacklist(o) {
   const titleNotBlacklisted = !isOneOf(o.title, appliedBlackList);
   const descNotBlacklisted = !isOneOf(o.description, appliedBlackList);
   return o.id != null && titleNotBlacklisted && descNotBlacklisted;
 }
 
+/** @type {ProviderConfig} */
 const config = {
   url: null,
   crawlContainer: '#main_column .wgg_card',
@@ -56,10 +78,13 @@ const config = {
     details: '.row .noprint .col-xs-11 |removeNewline |trim',
     price: '.middle .col-xs-3 |removeNewline |trim',
     size: '.middle .text-right |removeNewline |trim',
+    rooms: '.middle .text-right |removeNewline |trim',
     title: '.truncate_title a |removeNewline |trim',
     link: '.truncate_title a@href',
     image: '.img-responsive@src',
+    description: '.row .noprint .col-xs-11 |removeNewline |trim',
   },
+  fieldNames: ['id', 'link', 'title', 'price', 'size', 'rooms', 'address', 'image', 'description'],
   normalize: normalize,
   filter: applyBlacklist,
   fetchDetails,