scrape seller shop

search_seller.py

@@ -0,0 +1,63 @@
+
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+""" Author:                     Hendrik Schutter, mail@hendrikschutter.com
+    Date of creation:           2022/05/31
+    Date of last modification:  2022/05/31
+"""
+
+from bs4 import BeautifulSoup
+import datetime
+from tinydb import TinyDB, Query
+import urllib3
+import sys
+
+urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
+
+def make_soup(url):
+    http = urllib3.PoolManager()
+    r = http.request("GET", url)
+    return BeautifulSoup(r.data,'lxml')
+
+def seller_listings(seller_name, db):
+    #sort by newest listing
+    #display page 1 (first)
+    #EU only
+    #60 listings in one result page
+    
+    page_counter = 1
+    last_result_page = False
+    
+    while not last_result_page:
+        result_page_added = 0
+        url = 'https://www.ebay.de/sch/m.html?_ssn='+ seller_name + '&_sop=10&_pgn='+ str(page_counter)
+        print ("Web Page: ", url)
+
+        soup = make_soup(url)
+        results = soup.find_all("li", class_="sresult lvresult clearfix li")
+
+ 
+
+        for result in results:
+            try:
+                rec = {
+                    'epid': result.a['href'].split("?", 1)[0],
+                }
+                #check if listing is allready stored
+                if not db.search(Query().epid == rec["epid"]):
+                    result_page_added += 1
+                    db.insert(rec)
+
+            except (AttributeError, KeyError) as ex:
+                pass
+        if (result_page_added == 0): 
+            last_result_page = True
+        
+        page_counter += 1
+
+
+if __name__ == "__main__":
+    seller_db = TinyDB("seller_db.json")
+    seller_listings("electro-network*com", seller_db)
+    print(len(seller_db.all()))
+