External/fredy
1
0
Fork 0
mirror of https://github.com/orangecoding/fredy.git synced 2026-06-16 12:31:07 +00:00
Code Issues Packages Projects Releases Wiki Activity

Feature/spec filter (#276)

Browse Source 
* 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
This commit is contained in:
Stephan
2026-04-12 09:17:23 +02:00
committed by GitHub
parent 05f74f99ef
commit 10c94eea0a
49 changed files with 1004 additions and 250 deletions
Download Patch File Download Diff File Expand all files Collapse all files

29
lib/provider/einsAImmobilien.js
View File

@@ -5,8 +5,16 @@
import { buildHash, isOneOf } from '../utils.js';
import checkIfListingIsActive from '../services/listings/listingActiveTester.js';
import { extractNumber } from '../utils/extract-number.js';
/** @import { ParsedListing } from '../types/listing.js' */
/** @import { ProviderConfig } from '../types/providerConfig.js' */
let appliedBlackList = [];
/**
* @param {any} o
* @returns {ParsedListing}
*/
function normalize(o) {
const baseUrl = 'https://www.1a-immobilienmarkt.de';
const link = `${baseUrl}/expose/${o.id}.html`;
@@ -14,7 +22,17 @@ function normalize(o) {
const id = buildHash(o.id, price);
const image = baseUrl + o.image;
const address = o.address == null ? null : o.address.trim().replaceAll('/', ',');
return Object.assign(o, { id, price, link, image, address });
return {
id,
link,
title: o.title || '',
price: extractNumber(price),
size: extractNumber(o.size),
rooms: extractNumber(o.rooms),
address,
image,
description: undefined,
};
}
/**
@@ -34,13 +52,19 @@ function normalizePrice(price) {
}
return result[0];
}
/**
* @param {ParsedListing} o
* @returns {boolean}
*/
function applyBlacklist(o) {
const titleNotBlacklisted = !isOneOf(o.title, appliedBlackList);
const descNotBlacklisted = !isOneOf(o.description, appliedBlackList);
return titleNotBlacklisted && descNotBlacklisted;
}
/** @type {ProviderConfig} */
const config = {
fieldNames: ['id', 'link', 'title', 'price', 'size', 'rooms', 'address', 'image', 'description'],
url: null,
crawlContainer: '.tabelle',
sortByDateParam: 'sort_type=newest',
@@ -48,7 +72,8 @@ const config = {
crawlFields: {
id: '.inner_object_data input[name="marker_objekt_id"]@value | int',
price: '.inner_object_data .single_data_price | removeNewline | trim',
size: '.tabelle .tabelle_inhalt_infos .single_data_box | removeNewline | trim',
size: '.tabelle .tabelle_inhalt_infos .single_data_box:nth-of-type(1) | removeNewline | trim',
rooms: '.tabelle .tabelle_inhalt_infos .single_data_box:nth-of-type(2) | removeNewline | trim',
title: '.inner_object_data .tabelle_inhalt_titel_black | removeNewline | trim',
image: '.inner_object_pic img@src',
address: '.tabelle .tabelle_inhalt_infos .left_information > div:nth-child(2) | removeNewline | trim',