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
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

10
lib/types/browser.js Normal file
View File

@@ -0,0 +1,10 @@
/*
* Copyright (c) 2026 by Christian Kellner.
* Licensed under Apache-2.0 with Commons Clause and Attribution/Naming Clause
*/
/**
* @typedef {import('puppeteer').Browser} Browser
*/
export {};

19
lib/types/filter.js Normal file
View File

@@ -0,0 +1,19 @@
/*
* Copyright (c) 2026 by Christian Kellner.
* Licensed under Apache-2.0 with Commons Clause and Attribution/Naming Clause
*/
/**
* @typedef {Object} SpecFilter
* @property {number} [minRooms] Minimum number of rooms.
* @property {number} [minSize] Minimum size in m².
* @property {number} [maxPrice] Maximum price.
*/
/**
* @typedef {Object} SpatialFilter GeoJSON FeatureCollection.
* @property {Array<Object>} [features] GeoJSON features for spatial filtering (typically Polygons).
* @property {string} [type] Type 'FeatureCollection'.
*/
export {};

23
lib/types/job.js Normal file
View File

@@ -0,0 +1,23 @@
/*
* Copyright (c) 2026 by Christian Kellner.
* Licensed under Apache-2.0 with Commons Clause and Attribution/Naming Clause
*/
/** @import { SpecFilter, SpatialFilter } from './filter.js' */
/**
* @typedef {Object} Job
* @property {string} id Job ID.
* @property {string} [userId] Owner user id.
* @property {string} [name] Job display name.
* @property {boolean} [enabled] Whether the job is enabled.
* @property {Array<any>} [blacklist] Blacklist entries.
* @property {Array<any>} [provider] Provider configuration list.
* @property {Object} [notificationAdapter] Notification configuration.
* @property {Array<string>} [shared_with_user] Users this job is shared with.
* @property {SpatialFilter | null} [spatialFilter] Optional spatial filter configuration as GeoJSON FeatureCollection.
* @property {SpecFilter | null} [specFilter] Optional listing specifications.
* @property {number} [numberOfFoundListings] Count of active listings for this job.
*/
export {};

22
lib/types/listing.js Normal file
View File

@@ -0,0 +1,22 @@
/*
* Copyright (c) 2026 by Christian Kellner.
* Licensed under Apache-2.0 with Commons Clause and Attribution/Naming Clause
*/
/**
* @typedef {Object} ParsedListing
* @property {string} id Stable unique identifier (hash) of the listing.
* @property {string} link Link to the listing detail page.
* @property {string} image Link to the listing image.
* @property {string} title Title or headline of the listing.
* @property {string} [description] Description of the listing.
* @property {string} [address] Optional address/location text.
* @property {number} [price] Optional price of the listing.
* @property {number} [size] Optional size of the listing.
* @property {number} [rooms] Optional number of rooms.
* @property {number} [latitude] Optional latitude.
* @property {number} [longitude] Optional longitude.
* @property {number} [distance_to_destination] Optional distance to destination.
*/
export {};

View File

@@ -0,0 +1,25 @@
/*
* Copyright (c) 2026 by Christian Kellner.
* Licensed under Apache-2.0 with Commons Clause and Attribution/Naming Clause
*/
/** @import { ParsedListing } from './listing.js' */
/**
* @typedef {Object} ProviderConfig
* @property {string} [url] Base URL to crawl.
* @property {string} [sortByDateParam] Query parameter used to enforce sorting by date.
* @property {string} [waitForSelector] CSS selector to wait for before parsing content.
* @property {Object.<string, string>} crawlFields Mapping of field names to selectors/paths.
* @property {string[]} fieldNames List of field names that this provider supports.
* @property {string} [crawlContainer] CSS selector for the container holding listing items.
* @property {(raw: any) => ParsedListing} normalize Function to convert raw scraped data into a ParsedListing shape.
* @property {(listing: ParsedListing) => boolean} filter Function to filter out unwanted listings.
* @property {(url: string, waitForSelector?: string) => Promise<any[]>} [getListings] Optional override to fetch listings.
* @property {(listing:ParsedListing, browser:any)=>Promise<ParsedListing>} [providerConfig.fetchDetails] Optional per-listing detail enrichment. Called in parallel for each new listing after deduplication. Receives the shared browser instance. Must always resolve (never reject).
* @property {Object} [puppeteerOptions] Puppeteer specific options.
* @property {boolean} [enabled] Whether the provider is enabled.
* @property {(url: string) => Promise<number> | number} [activeTester] Function to check if a listing is still active.
*/
export {};

View File

@@ -0,0 +1,11 @@
/*
* Copyright (c) 2026 by Christian Kellner.
* Licensed under Apache-2.0 with Commons Clause and Attribution/Naming Clause
*/
/**
* @typedef {Object} SimilarityCache
* @property {(params: { title?: string, address?: string, price?: number|string }) => boolean} checkAndAddEntry Checks if a listing is similar and adds it if not.
*/
export {};