mirror of
https://github.com/orangecoding/fredy.git
synced 2026-06-16 12:31:07 +00:00
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:
committed by
GitHub
parent
7888c5b340
commit
cdc0cbda2f
@@ -5,14 +5,151 @@
|
||||
|
||||
import { buildHash, isOneOf } from '../utils.js';
|
||||
import checkIfListingIsActive from '../services/listings/listingActiveTester.js';
|
||||
import puppeteerExtractor from '../services/extractor/puppeteerExtractor.js';
|
||||
import logger from '../services/logger.js';
|
||||
import * as cheerio from 'cheerio';
|
||||
|
||||
let appliedBlackList = [];
|
||||
let appliedBlacklistedDistricts = [];
|
||||
|
||||
function toAbsoluteLink(link) {
|
||||
if (!link) return null;
|
||||
return link.startsWith('http') ? link : `https://www.kleinanzeigen.de${link}`;
|
||||
}
|
||||
|
||||
function cleanText(value) {
|
||||
if (value == null) return '';
|
||||
return String(value)
|
||||
.replace(/<[^>]*>/g, ' ')
|
||||
.replace(/\s+/g, ' ')
|
||||
.trim();
|
||||
}
|
||||
|
||||
function buildAddressFromJsonLd(address) {
|
||||
if (!address || typeof address !== 'object') return null;
|
||||
|
||||
const locality = cleanText(address.addressLocality);
|
||||
const region = cleanText(address.addressRegion);
|
||||
const postalCode = cleanText(address.postalCode);
|
||||
const streetAddress = cleanText(address.streetAddress);
|
||||
|
||||
const cityPart = [region, locality].filter(Boolean).join(' - ');
|
||||
const tail = [postalCode, cityPart || locality || region].filter(Boolean).join(' ');
|
||||
const fullAddress = [streetAddress, tail].filter(Boolean).join(', ');
|
||||
|
||||
return fullAddress || null;
|
||||
}
|
||||
|
||||
function flattenJsonLdNodes(node, acc = []) {
|
||||
if (node == null) return acc;
|
||||
|
||||
if (Array.isArray(node)) {
|
||||
node.forEach((item) => flattenJsonLdNodes(item, acc));
|
||||
return acc;
|
||||
}
|
||||
|
||||
if (typeof node !== 'object') return acc;
|
||||
|
||||
acc.push(node);
|
||||
|
||||
if (Array.isArray(node['@graph'])) {
|
||||
node['@graph'].forEach((item) => flattenJsonLdNodes(item, acc));
|
||||
}
|
||||
|
||||
if (node.mainEntity) {
|
||||
flattenJsonLdNodes(node.mainEntity, acc);
|
||||
}
|
||||
|
||||
if (node.itemOffered) {
|
||||
flattenJsonLdNodes(node.itemOffered, acc);
|
||||
}
|
||||
|
||||
return acc;
|
||||
}
|
||||
|
||||
function extractDetailFromHtml(html) {
|
||||
const $ = cheerio.load(html);
|
||||
const nodes = [];
|
||||
|
||||
// Prefer the rendered postal address block from the detail page because
|
||||
// it contains the street line that is missing from list results.
|
||||
const streetFromDom = cleanText($('#street-address').first().text());
|
||||
const localityFromDom = cleanText($('#viewad-locality').first().text());
|
||||
const domAddress = [streetFromDom, localityFromDom].filter(Boolean).join(' ');
|
||||
|
||||
$('script[type="application/ld+json"]').each((_, element) => {
|
||||
const content = $(element).text();
|
||||
if (!content) return;
|
||||
|
||||
try {
|
||||
const parsed = JSON.parse(content);
|
||||
flattenJsonLdNodes(parsed, nodes);
|
||||
} catch {
|
||||
// Ignore broken JSON-LD blocks from ads/trackers and keep trying others.
|
||||
}
|
||||
});
|
||||
|
||||
let detailAddress = null;
|
||||
let detailDescription = null;
|
||||
|
||||
if (domAddress) {
|
||||
detailAddress = domAddress;
|
||||
}
|
||||
|
||||
for (const node of nodes) {
|
||||
const candidateAddress = buildAddressFromJsonLd(
|
||||
node.address || node?.itemOffered?.address || node?.offers?.address,
|
||||
);
|
||||
if (!detailAddress && candidateAddress) {
|
||||
detailAddress = candidateAddress;
|
||||
}
|
||||
|
||||
const candidateDescription = cleanText(node.description || node?.itemOffered?.description);
|
||||
if (!detailDescription && candidateDescription) {
|
||||
detailDescription = candidateDescription;
|
||||
}
|
||||
|
||||
if (detailAddress && detailDescription) {
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
return {
|
||||
detailAddress,
|
||||
detailDescription,
|
||||
};
|
||||
}
|
||||
|
||||
async function enrichListingFromDetails(listing, browser) {
|
||||
const absoluteLink = toAbsoluteLink(listing.link);
|
||||
if (!absoluteLink) return listing;
|
||||
|
||||
try {
|
||||
const html = await puppeteerExtractor(absoluteLink, null, { browser });
|
||||
if (!html) return { ...listing, link: absoluteLink };
|
||||
|
||||
const { detailAddress, detailDescription } = extractDetailFromHtml(html);
|
||||
|
||||
return {
|
||||
...listing,
|
||||
link: absoluteLink,
|
||||
address: detailAddress || listing.address,
|
||||
description: detailDescription || listing.description,
|
||||
};
|
||||
} catch (error) {
|
||||
logger.warn(`Could not fetch Kleinanzeigen detail page for listing '${listing.id}'.`, error?.message || error);
|
||||
return { ...listing, link: absoluteLink };
|
||||
}
|
||||
}
|
||||
|
||||
async function fetchDetails(listing, browser) {
|
||||
return enrichListingFromDetails(listing, browser);
|
||||
}
|
||||
|
||||
function normalize(o) {
|
||||
const size = o.size || '--- m²';
|
||||
const id = buildHash(o.id, o.price);
|
||||
const link = `https://www.kleinanzeigen.de${o.link}`;
|
||||
const link = toAbsoluteLink(o.link) || o.link;
|
||||
return Object.assign(o, { id, size, link });
|
||||
}
|
||||
|
||||
@@ -40,12 +177,13 @@ const config = {
|
||||
address: '.aditem-main--top--left | trim | removeNewline',
|
||||
image: 'img@src',
|
||||
},
|
||||
fetchDetails,
|
||||
normalize: normalize,
|
||||
filter: applyBlacklist,
|
||||
activeTester: checkIfListingIsActive,
|
||||
};
|
||||
export const metaInformation = {
|
||||
name: 'Ebay Kleinanzeigen',
|
||||
name: 'Kleinanzeigen',
|
||||
baseUrl: 'https://www.kleinanzeigen.de/',
|
||||
id: 'kleinanzeigen',
|
||||
};
|
||||
|
||||
Reference in New Issue
Block a user