Python Tips - 获得网页超链接

获得网页所有超级链接

get all hyperlinks

#!/usr/bin/env python
# get all hyperlinks

from re import compile as reComp
from urllib import urlopen, basejoin

def getURL(http, num=10):
""" get all hyperlinks and print the first num"""
data = urlopen(http).read()
regex = reComp(r'href="([^"]+)"')
urls = regex.findall(data)
for url in urls[:num]:
print basejoin(http, url)
#print url

def main():
getURL("http://52xenos.blogspot.com",5)

if __name__ == '__main__': main()

输出结果如下:

Results:

http://52xenos.blogspot.com/feeds/posts/default
http://52xenos.blogspot.com/feeds/posts/default?alt=rss
http://www.blogger.com/feeds/7524190211354587233/posts/default
http://www.blogger.com/rsd.g?blogID=7524190211354587233
http://www.blogger.com/profile/07043019578098595151