先上我的代码。参考了上面链接的文章# -*- coding: utf-8 -*-
# !/usr/bin/python
import os
import urllib2
import urllib
import cookielib
import re
import sys
from bs4 import BeautifulSoup
‘‘‘
编码方式的设置,在中文使用时用到中文时的处理方式
‘‘‘
default_encoding = "utf-8"
if sys.getdefaultencoding() != default_encoding:
reload(sys)
sys.setdefaultencoding("utf-8")
def getHtml(url,data={}):
if(data=={}):
req=urllib2.Request(url)
else:
req=urllib2.Request(url,urllib.urlencode(data))
html=urllib2.urlopen(req).read()
return html
try:
cookie = cookielib.CookieJar()
cookieProc = urllib2.HTTPCookieProcessor(cookie)
except:
raise
else:
opener = urllib2.build_opener(cookieProc)
open