85 lines
2.2 KiB
Python
85 lines
2.2 KiB
Python
#!/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
|
|
import random
|
|
|
|
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 seller_listings(seller_name, db):
|
|
# sort by newest listing
|
|
|
|
page_counter = 1
|
|
last_result_page = False
|
|
|
|
while not last_result_page:
|
|
result_page_added = 0
|
|
|
|
if page_counter == 1:
|
|
url = (
|
|
"https://www.ebay.de/sch/m.html?_ssn="
|
|
+ seller_name
|
|
+ "&_sop=10&_pgn="
|
|
+ str(page_counter)
|
|
)
|
|
else:
|
|
url = (
|
|
"https://www.ebay.de/sch/m.html?_ssn="
|
|
+ seller_name
|
|
+ "&_sop=10&_pgn="
|
|
+ str(page_counter)
|
|
+ "&_skc="
|
|
+ str(60 * (page_counter - 1))
|
|
+ "&rt=nc"
|
|
)
|
|
|
|
# print ("Web Page: ", url)
|
|
|
|
soup = make_soup(url)
|
|
results = soup.find_all(
|
|
"li", class_="s-item s-item__dsa-on-bottom s-item__pl-on-bottom"
|
|
)
|
|
|
|
for result in results:
|
|
# print(result)
|
|
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()))
|