python 的cookie处理操作

文章来源：http://blog.csdn.net/yatere/article/details/6649139

• 使用已有的cookie访问网站

import cookielib, urllib2

ckjar = cookielib.MozillaCookieJar(os.path.join(’C:\Documents and Settings\tom\Application Data\Mozilla\Firefox\Profiles\h5m61j1i.default’, ‘cookies.txt’))

req = urllib2.Request(url, postdata, header)

req.add_header(’User-Agent’, \ 
‘Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1)’)

opener = urllib2.build_opener(urllib2.HTTPCookieProcessor(ckjar) )

f = opener.open(req) 
htm = f.read() 
f.close()

• 访问网站获得cookie，并把获得的cookie保存在cookie文件中

import cookielib, urllib2

req = urllib2.Request(url, postdata, header) 
req.add_header(’User-Agent’, \ 
‘Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1)’)

ckjar = cookielib.MozillaCookieJar(filename) 
ckproc = urllib2.HTTPCookieProcessor(ckjar)

opener = urllib2.build_opener(ckproc)

f = opener.open(req) 
htm = f.read() 
f.close()

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

• 使用指定的参数生成cookie,并用这个cookie访问网站

import urllib.request as ur
import urllib.parse as up
#import http.cookiejar as cj
#coding:gbk

charset='utf8'

#组件信息
#cookiejar = cj.CookieJar()
#urlopener = ur.build_opener(ur.HTTPCookieProcessor(cookiejar))
urlopener = ur.build_opener(ur.HTTPCookieProcessor())

#jiayuan配置信息
name='Yatere'
uid='22017518'

#http头
headers={'User-Agent':'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 5.1; Trident/4.0; .NET CLR 2.0.50727; .NET CLR 3.0.04506.30)'}
seachhead={'User-Agent':'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 5.1; Trident/4.0; .NET CLR 2.0.50727; .NET CLR 3.0.04506.30)',
           'Referer':'',
           'Origin':''}

#用户登入data
values = {'password':'198398','name':'[e-mail]'}


#搜索data
searchdata={
    '***':'f',
    'work_location':'42',
    'work_sublocation':'4201',
    'min_age':'22',
    'max_age':'26',
    'min_height':'160',
    'max_height':'180',
    'education':'20',
    'edu_more_than':'on',
    'astro':'0',
    'animal':'',
    'bloodtype':'0',
    'income':'0',
    'house':'0',
    'auto':'0',
    'marriage':'1',
    'children':'0',
    'level':'0',
    'industry':'0',
    'company':'0',
    'home_location':'42',
    'home_sublocation':'4201',
    'nation':'0',
    'belief':'0',
    'ques_love':'0',
    'avatar':'on',
    'save_name':''}


#post数据转换程序
def data(values):
    data=up.urlencode(values).encode()
    return data


#访问指定页面
def geturlcon(url,data=None,headers=headers):
    request = ur.Request(url,data,headers)
    url = urlopener.open(request)
    page=url.read().decode('utf8','ignore')
    return page

#检测是否登入成功
def checklogin(page):
    if page.find(name)>0:
        return True
    elif page.find(uid)>0:
        return True
    else:
        return False


#访问登陆页面（获得cookie）
url1=''
geturlcon(url1,data(values),headers)



#登入后访问其他页面
url2=''
page=geturlcon(url2)
if checklogin(page):
    print ('登入成功')
else:
    print ('登入失败')

url3=''
page=geturlcon(url3)

if checklogin(page):
    print (url3,'登入成功')
else:
    print ('登入失败')


#查看搜索结果
url3='result.php?t=10&m=1'
page=geturlcon(url3,data(searchdata),seachhead)

if checklogin(page):
    print (url3,'登入成功')
else:
    print ('登入失败')