eBayCompetitorPriceCompare/compare.py

140 lines
5.8 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: 2024/08/18
"""
from bs4 import BeautifulSoup
from datetime import datetime
from tinydb import TinyDB, Query
import urllib3
import sys
from tqdm import tqdm
import scrape_listing as sl
import search_eBay as se
import export_html as exhtml
if __name__ == "__main__":
seller_db = TinyDB("seller_db.json")
database_length = len(seller_db.all())
comparison_results = list()
seller_listing_data = False
if database_length == 0:
print("Unable to load seller shop database!")
sys.exit(-1)
# print("Loaded seller shop database: " + str(database_lenght) + " listings")
pbar = tqdm(total=database_length) # print progress bar
compare_start_timestamp = datetime.now() # set start time for comparing
for shop_listing_url in seller_db.all():
# print(shop_listing_url["epid"])
for retrieve_counter in range(42):
try:
seller_listing_data = sl.scrape_listing(shop_listing_url["epid"])
break
except:
pass
# print("Unable to retrieve seller listing data from: " + shop_listing_url["epid"])
if seller_listing_data:
#print("\n\nCompare: " + seller_listing_data["title"] + " | " + str(seller_listing_data["price"]) + "€ | " + shop_listing_url["epid"])
comparison_result = {
"seller_listing": seller_listing_data,
"competitor_listings": list(),
"max_price_delta": float(0.0),
}
competitor_listings = se.search(seller_listing_data["title"], 1)
#print("Found " + str(len(competitor_listings)) + " listings from competitors with term: " + seller_listing_data["title"])
sys.stdout.flush()
cheaper_listings = list()
for competitor_listing_url in competitor_listings:
# print(competitor_listing_url)
# print(shop_listing_url["epid"])
if seller_db.search(Query().epid == competitor_listing_url):
# print("Found listing from sellers shop --> ignore " + competitor_listing_url)
continue
# else:
# print("not from own shop")
competitor_listing_data = False
for retrieve_counter_competitor in range(42):
try:
# print("scraping : " + competitor_listing_url)
competitor_listing_data = sl.scrape_listing(
competitor_listing_url
)
break
except:
pass
# print("Unable to retrieve competitor listing data from: " + competitor_listing_url)
if competitor_listing_data:
# print(competitor_listing_data["price"])
if (competitor_listing_data["category"] != seller_listing_data["category"]):
#print("Found competitor_listing is not in same category!")
continue
if competitor_listing_data["directbuy"] != True:
#print("Found competitor_listing is not direct buy!")
continue
if (competitor_listing_data["price"] < seller_listing_data["price"]):
# print("found cheaper competitor: " + str(competitor_listing_data["price"]) + "€ instead: " + str(seller_listing_data["price"]) + "€ ---> " + competitor_listing_url + " Type: "+ str(competitor_listing_data["directbuy"]))
cheaper_listings.append(
{
"title": competitor_listing_data["title"],
"price": competitor_listing_data["price"],
"image": competitor_listing_data["image"],
"url": competitor_listing_url,
}
)
for cheaper_listing in sorted(cheaper_listings, key=lambda d: d["price"]):
# print(cheaper_listing)
# print("found cheaper competitor: " + str(cheaper_listing["price"]) + "€ instead: " + str(seller_listing_data["price"]) + "€ ---> " + cheaper_listing["url"])
comparison_result["competitor_listings"].append(cheaper_listing)
if comparison_result["max_price_delta"] == 0.0:
comparison_result["max_price_delta"] = (
seller_listing_data["price"] - cheaper_listing["price"]
)
if cheaper_listings:
comparison_results.append(comparison_result)
pbar.update(1)
# break
pbar.close()
print(
"\nFinished comparing! Found "
+ str(len(comparison_results))
+ " possibly cheaper listings"
)
now = datetime.now() # current date and time
duration_compare = datetime.now() - compare_start_timestamp
hours, remainder = divmod(duration_compare.total_seconds(), 3600)
minutes, seconds = divmod(remainder, 60)
duration_compare = (
str(hours) + "h " + str(minutes) + "m " + str(round(seconds, 2)) + "s"
)
exp = exhtml.exporter("./html_out/")
for comparison in sorted(
comparison_results, key=lambda d: d["max_price_delta"], reverse=True
):
exp.export_comparison(
comparison["seller_listing"], comparison["competitor_listings"]
)
exp.export_startpage(
str(database_length),
len(comparison_results),
duration_compare,
now.strftime("%m/%d/%Y, %H:%M:%S"),
)