InterfaceLIFT Scraper

gistfile1.py

import os, math, re, urllib
scraping = "http://interfacelift.com/wallpaper/downloads/date/widescreen/1440x900/"
goal = 10
done = 0
tag = re.compile(r"<a href=\"(?P<url>[^\"]+)\"><img src=\"/img_NEW/button_download\.png\"")
if not os.path.exists("scraped") :
	os.makedirs("scraped")
for page in range(1, 1 + int(math.ceil(goal / 10.0))):
	list = tag.finditer(urllib.urlopen(scraping + "index" + str(page) + ".html").read())
	for i in list:
		if done < goal :
			print("scraping " + str(done + 1) + " of " + str(goal))
			wurl = "http://interfacelift.com/" + i.group("url")
			urllib.urlretrieve(wurl, "scraped/" + str(done) + ".jpg")
			done += 1