（转）Python:正则表达式找出网页上所有链接

转自：http://www.linuxany.com/archives/596.html

import re
import urllib
def test(html,rex):
    alist = []
    r = re.compile(rex)
    matchs = r.findall(html)
    if matchs != None:
        for found in matchs:
            if found not in alist:
                alist.append(found)         
    return alist
             
rex = r'<a\s*href=\"(.*?)\"'
page=urllib.urlopen('http://hi.baidu.com')
html=page.read()
page.close()
 
print test(html,rex)

 

转载于:https://www.cnblogs.com/youthdream/p/3527787.html