htmllib.HTMLParser
#!/usr/bin/env python
import cStringIO
import formatter
from htmllib import HTMLParser
import urllib
url = "http://blog.csdn.net/Lyq3413/article/details/76577465"
user_name = "proxy_account"
passwd = "proxy_pwd"
proxy_base = "proxy.example.net:8080"
proxy = "http://%s:%s@%s" % (user_name, passwd, proxy_base)
proxies = {
"http": proxy, "https": proxy}
f = urllib.urlopen(url, proxies=proxies) #需要代理
#f = urllib.urlopen(