scrape search for listing

search_kleinanzeigen.py

@@ -0,0 +1,72 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+""" Author:                     Hendrik Schutter, mail@hendrikschutter.com
+    Date of creation:           2025/11/24
+    Date of last modification:  2025/11/24
+"""
+
+from bs4 import BeautifulSoup
+import datetime
+from tinydb import TinyDB, Query
+import urllib3
+import sys
+import helper
+
+urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
+
+def make_soup(url):
+    user_agent = {"user-agent": helper.get_random_user_agent()}
+    # print(user_agent)
+    http = urllib3.PoolManager(10, headers=user_agent)
+    r = http.request("GET", url)
+    return BeautifulSoup(r.data, "lxml")
+
+
+def search(search_term, max_pages, min_price, max_price):
+    # Sorted by newest listing
+    # No Geo distance
+    # Only private sellers
+    # Only offerings
+
+    base_url = "https://www.kleinanzeigen.de"
+
+    found_listings = set()
+
+    for page_counter in range(1, max_pages+1):
+        listing_url = (
+            base_url + "/s-anbieter:privat/anzeige:angebote/preis:" + str(min_price) + ":" + str(max_price) + "/seite:"+ str(page_counter)+"/"
+            + search_term.replace(" ", "-")
+            + "/k0"
+        )
+
+        print ("Web Page: ", listing_url)
+        soup = make_soup(listing_url)
+        results = soup.find_all("li", class_="ad-listitem fully-clickable-card")
+        #print(len(results))
+
+        if(len(results) <= 0):
+            break
+
+        for result in results:
+            try:
+                #print(result)
+                listing_url = result.a["href"]
+                #print("url: " + base_url + listing_url)
+                found_listings.add(base_url + listing_url)
+            except (AttributeError, KeyError) as ex:
+                pass
+
+    return found_listings
+
+
+if __name__ == "__main__":
+    found_listings = search("Fahrrad", max_pages=1, min_price = 24, max_price=42)
+    print(found_listings)
+    print(len(found_listings))
+
+
+
+
+
+
+