Feature/kleinanzeigen new (#292)

* Feature/Kleinanzeigen addresses (#289)

* upgrade dependencies

* immoscout_details -> provider_details

* fetching details more generic

* removing claude action

* fixing sparkassen selector

* improvements

* fixing immobilienDE test

* upgrading dependencies

* settings for many provider

---------

Co-authored-by: Adrian Bach <65734063+realDayaa@users.noreply.github.com>
This commit is contained in:
Christian Kellner
2026-04-07 19:53:40 +02:00
committed by GitHub
parent 7888c5b340
commit cdc0cbda2f
35 changed files with 1098 additions and 501 deletions

View File

@@ -5,6 +5,9 @@
import { buildHash, isOneOf } from '../utils.js';
import checkIfListingIsActive from '../services/listings/listingActiveTester.js';
import puppeteerExtractor from '../services/extractor/puppeteerExtractor.js';
import * as cheerio from 'cheerio';
import logger from '../services/logger.js';
let appliedBlackList = [];
@@ -18,6 +21,51 @@ function parseId(shortenedLink) {
return shortenedLink.substring(shortenedLink.lastIndexOf('/') + 1);
}
async function fetchDetails(listing, browser) {
try {
const html = await puppeteerExtractor(listing.link, null, { browser });
if (!html) return listing;
const $ = cheerio.load(html);
// Try JSON-LD first
let description = null;
let address = listing.address;
$('script[type="application/ld+json"]').each((_, el) => {
if (description) return;
try {
const data = JSON.parse($(el).text());
const nodes = Array.isArray(data) ? data : [data];
for (const node of nodes) {
if (node.description && !description) description = String(node.description).replace(/\s+/g, ' ').trim();
const addr = node.address || node?.mainEntity?.address;
if (addr && addr.streetAddress && address === listing.address) {
const parts = [addr.streetAddress, addr.postalCode, addr.addressLocality].filter(Boolean);
if (parts.length) address = parts.join(' ');
}
}
} catch {
// ignore malformed JSON-LD
}
});
// Fallback: common description selectors used by immobilien.de
if (!description) {
const sel = ['.beschreibung', '.freitext', '.objektbeschreibung', '.description'].find((s) => $(s).length > 0);
if (sel) description = $(sel).text().replace(/\s+/g, ' ').trim();
}
return {
...listing,
address,
description: description || listing.description,
};
} catch (error) {
logger.warn(`Could not fetch immobilien.de detail page for listing '${listing.id}'.`, error?.message || error);
return listing;
}
}
function normalize(o) {
const baseUrl = 'https://www.immobilien.de';
const size = o.size || null;
@@ -25,8 +73,8 @@ function normalize(o) {
const title = o.title || 'No title available';
const address = o.address || null;
const shortLink = shortenLink(o.link);
const link = baseUrl + shortLink;
const image = baseUrl + o.image;
const link = shortLink ? (shortLink.startsWith('http') ? shortLink : baseUrl + shortLink) : baseUrl;
const image = o.image ? (o.image.startsWith('http') ? o.image : baseUrl + o.image) : null;
const id = buildHash(parseId(shortLink), o.price);
return Object.assign(o, { id, price, size, title, address, link, image });
}
@@ -39,21 +87,22 @@ function applyBlacklist(o) {
const config = {
url: null,
crawlContainer: 'a:has(div.list_entry)',
crawlContainer: 'a.lr-card',
sortByDateParam: 'sort_col=*created_ts&sort_dir=desc',
waitForSelector: 'body',
waitForSelector: null,
crawlFields: {
id: '@href', //will be transformed later
price: '.immo_preis .label_info',
size: '.flaeche .label_info | removeNewline | trim',
title: 'h3 span',
price: '.lr-card__price-amount | trim',
size: '.lr-card__fact:has(.lr-card__fact-label:contains("Fläche")) .lr-card__fact-value | trim',
title: '.lr-card__title | trim',
description: '.description | trim',
link: '@href',
address: '.place',
image: 'img@src',
address: '.lr-card__address span | trim',
image: 'img.lr-card__gallery-img@src',
},
normalize: normalize,
normalize,
filter: applyBlacklist,
fetchDetails,
activeTester: checkIfListingIsActive,
};
export const init = (sourceConfig, blacklist) => {