python 爬虫cookie的简单使用

来源：互联网发布：电脑怎样编程软件编辑：程序博客网时间：2024/05/21 06:25

#coding=utf-8

import urllib

import urllib2

import cookielib

from bs4 import BeautifulSoup

url ="http://www.baidu.com"

values = {

'userName':'aaaaaa',

'password':'bbbbbb'

}

postdata =urllib.urlencode(values)

user_agent = "Mozilla/5.0(Windows NT 6.1; WOW64)"

headers ={"User-Agent":user_agent}

#以下为创建opener

file_name = 'cookie.txt'

cookie =cookielib.MozillaCookieJar(file_name)

handler =urllib2.HTTPCookieProcessor(cookie)

opener =urllib2.build_opener(handler)

#请求url

try:

request = urllib2.Request(url, data = None,headers=headers)

response = opener.open(request, timeout =2)

except urllib2.HTTPError, e:

print e.code

except urllib2.URLError, e:

print e.reason

except:

print "Error"

#保存cookie到文件中

cookie.save(ignore_discard=True,ignore_expires=True)

data = response.read()

soup = BeautifulSoup(data,"lxml")

for link in soup.find_all('a'):

print link

更多详细内容请参考 http://cuiqingcai.com/1052.html

1 0