Files
fredy/lib/provider/immobilienDe.js
Christian Kellner f0b146fd7f Adding images to scraping data (#157)
* Fredy now supports pulling the main Image from the listing and send it together with the usual information
2025-08-30 21:21:34 +02:00

61 lines
1.8 KiB
JavaScript

import utils, { buildHash } from '../utils.js';
let appliedBlackList = [];
function shortenLink(link) {
return link.substring(0, link.indexOf('?'));
}
function parseId(shortenedLink) {
return shortenedLink.substring(shortenedLink.lastIndexOf('/') + 1);
}
function normalize(o) {
const baseUrl = 'https://www.immobilien.de';
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 shortLink = shortenLink(o.link);
const link = `${baseUrl}/${shortLink}`;
const image = baseUrl + o.image;
const id = buildHash(parseId(shortLink), o.price);
return Object.assign(o, { id, price, size, title, address, link, image });
}
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: '._ref',
sortByDateParam: 'sort_col=*created_ts&sort_dir=desc',
waitForSelector: 'body',
crawlFields: {
id: '@href', //will be transformed later
price: '.list_entry .immo_preis .label_info',
size: '.list_entry .flaeche .label_info | removeNewline | trim',
title: '.list_entry .part_text h3 span',
description: '.list_entry .description | trim',
link: '@href',
address: '.list_entry .place',
image: '.list_entry img@src',
},
normalize: normalize,
filter: applyBlacklist,
};
export const init = (sourceConfig, blacklist) => {
config.enabled = sourceConfig.enabled;
config.url = sourceConfig.url;
appliedBlackList = blacklist || [];
};
export const metaInformation = {
name: 'Immobilien.de',
baseUrl: 'https://www.immobilien.de/',
id: 'immobilienDe',
};
export { config };