Created
December 3, 2015 07:21
-
-
Save fadere/fe9d471fb605d7975ee3 to your computer and use it in GitHub Desktop.
python code to scrape ebay historical auction results
This file contains 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 requests | |
import bs4 | |
import argparse | |
# parser = argparse.ArgumentParser(description='Process a list of search terms.') | |
# parser.add_argument('terms', metavar='N', type=str, nargs='+', | |
# help='comma separated list of terms to search for') | |
# args = parser.parse_args() | |
# print args.accumulate(args.terms) | |
# enter multiple phrases separated by '', | |
phrases =['nixon autograph'] | |
for phrase in phrases: | |
site = 'http://www.ebay.com/sch/i.html?_from=R40&_nkw='+phrase+'&_in_kw=1&_ex_kw=&_sacat=0&LH_Sold=1&_udlo=&_udhi=&LH_Auction=1&_samilow=&_samihi=&_sadis=15&_stpos=90278-4805&_sargn=-1%26saslc%3D1&_salic=1&_sop=13&_dmd=1&_ipg=200&LH_Complete=1' | |
res = requests.get(site) | |
res.raise_for_status() | |
soup = bs4.BeautifulSoup(res.text, "lxml") | |
# grab the date/time stamp of each auction listing | |
dte = [e.span.contents[0].split(' ')[0] for e in soup.find_all(class_="tme")] | |
# grab all the links and store its href destinations in a list | |
titles = [e.contents[0] for e in soup.find_all(class_="vip")] | |
# grab all the links and store its href destinations in a list | |
links = [e['href'] for e in soup.find_all(class_="vip")] | |
# grab all the bid spans and split its contents in order to get the number only | |
bids = [e.span.contents[0].split(' ')[0] for e in soup.find_all("li", "lvformat")] | |
# grab all the prices and store those in a list | |
prices = [e.contents[0] for e in soup.find_all("span", "bold bidsold")] | |
# zip each entry out of the lists we generated before in order to combine the entries | |
# belonging to each other and write the zipped elements to a list | |
l = [e for e in zip(dte, titles, links, prices, bids)] | |
# write each entry of the rowlist `l` to the csv output file | |
with open('%s.csv' % phrase, 'wb') as csvfile: | |
w = csv.writer(csvfile) | |
for e in l: | |
w.writerow(e) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Did you ever run into the issue of the web scraper, scraping data twice? I am currently trying to figure out what is going wrong with my code.