爬虫----表单登录

1.post提交表单

# -*- coding:utf-8 -*-

import urllib, urllib2
import COOKIElib
import lxml.html

from lxml import etree

def getCOOKIE():
    cj = COOKIElib.COOKIEJar()
    opener = urllib2.build_opener(urllib2.HTTPCOOKIEProcessor(cj))
    return opener

def get_data(html):
    tree = lxml.html.fromstring(html)
    data = {}
    for i in tree.cssselect('form input'):
        if i.get('name'):
            data[i.get('name')] = i.get('value')
    return data

def main():
    url = 'https://www.douban.com/accounts/login?source=main'
    html = urllib2.urlopen(url).read()
    data = get_data(html)
    data['login'] = 'login'
    data['form_email'] = '1111111111@qq.com'
    data['form_password'] = 'admin'
    encode_data = urllib.urlencode(data)
    request = urllib2.Request(url, encode_data)
    opener = getCOOKIE()
    respOnse= opener.open(request)

    print response.geturl()



if __name__ == "__main__":
    main()

2.高级模块mechanize

# -*- coding:utf-8 -*-
import mechanize
import sys
reload(sys)
sys.setdefaultencoding('utf-8')


def main():
    url = 'https://www.douban.com/accounts/login?source=main'
    br = mechanize.Browser()
    br.open(url)
    # for form in br.forms():
    #     print form
    br.select_form(nr=0)
    br['form_email'] = '1111111111@qq.com'
    br['form_password'] = 'admin'
    respOnse= br.submit()
    print response.geturl()


if __name__ == '__main__':
    main()