Created
November 28, 2019 06:51
-
-
Save Radicals27/5e10a9717adee696bfdf3d6c01ebcd28 to your computer and use it in GitHub Desktop.
This is an eBay price scraper for Nvidia RTX2080 cards.
It collects the prices and links to the items in a .csv file.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import csv | |
import urllib.request | |
from bs4 import BeautifulSoup | |
import time | |
item_links = [] | |
price_links = [] | |
website = "https://www.ebay.com.au/sch/i.html?_from=R40&_trksid=m570.l1313&_nkw=rtx+2080&_sacat=0&LH_TitleDesc=0&_osacat=0&_odkw=gtx+2080" | |
print(website) | |
try: | |
page = urllib.request.urlopen(website) | |
except (http.client.IncompleteRead) as e: | |
page = e.partial | |
soup = BeautifulSoup(page, 'lxml') | |
all_a_tags = soup.find_all("a") | |
all_span_tags = soup.find_all("span") | |
for link in all_a_tags: | |
try: | |
tester = link.get("href") | |
if "https://www.ebay.com.au/itm/" in link.get("href"): | |
if link.get("href") in item_links: | |
print("duplicate found") | |
else: | |
item_links.append(link.get("href")) | |
print(link.get("href")) | |
raw_filename = link.get("href") | |
except: | |
tester = None | |
time.sleep(3) | |
for link in all_span_tags: | |
try: | |
tester = link.get("class") | |
if "item__price" in str(link): | |
split_link = str(link).split('>') | |
split_link = split_link[1].split('<') | |
price_links.append(split_link[0]) | |
print(split_link[0]) | |
raw_price = link | |
except: | |
tester = None | |
print("Items collected: ", len(item_links)) | |
print("Prices collected: ", len(price_links)) | |
with open('All_items.csv', 'a', newline='\n') as csvFile: #append each fileshare link to a new row | |
writer = csv.writer(csvFile, delimiter=',', quotechar='"', quoting=csv.QUOTE_MINIMAL, dialect='excel') | |
for i in item_links: | |
writer.writerow([i, price_links[item_links.index(i)]]) | |
csvFile.close() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment