Created
August 1, 2014 09:53
-
-
Save DecKen/28dea5a2553190223ca6 to your computer and use it in GitHub Desktop.
crawl
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
#!/usr/bin/env python | |
# -*- coding:utf-8 -*- | |
from urlparse import urljoin | |
from pyquery import PyQuery as pq | |
url = "http://www.szeros-wedding.com/html/service/804.html" | |
area = pq(url)('.pic img') | |
urllist = [] | |
area.each(lambda index, element: urllist.append(urljoin(url, pq(element).attr('src')))) | |
for url in urllist: | |
print url |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment