python-微博模擬登錄

微博的的模擬登錄是比較坑的，看了網上不少大神的帖子，本身又看了微博的登錄時的json數據：一、發現登錄時在輸入帳號時用chrome能夠看到會有一個prelogin之類的網址，網址後面會有大串的隨機數。我測試了下，發如今沒有隨機數的狀況下的網址也能獲得所須要的severtime、nonce、等幾個數據。二、經過chrome查看json數據就能夠看到用戶名和密碼的加密方式，再找了網上大神的資料就能夠獲得用戶名su、和密碼sp。再把數據post 上去就能夠獲得一個重定向的微博登錄網址。三、將這個網址用正則表達式提取出來，再帶上cookie數據就能夠登錄了。而後你想幹什麼就幹什

# _*_coding:utf-8 _*_

import base64
import urllib
import urllib2
import re
import rsa
import cookielib


class Weibo(object):

    def __init__(self, username, password):
        self.user = base64.b64encode(username)
        self.pwd = password

    @property
    def get_pre_url_values(self):
        values_dict = {}
        su = self.user
        pre_url = 'https://login.sina.com.cn/sso/prelogin.php?entry=weibo&callback=sinaSSOController.preloginCallBack&su=' \
                       + str(su[:-1]) + '%3D&rsakt=mod&checkpin=1&client=ssologin.js(v1.4.18)'
        header = {
            'User-Agent': 'Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/35.0.1916.153 Safari/537.36'
        }

        request = urllib2.Request(pre_url, headers=header)
        html = urllib2.urlopen(request).read().decode('utf-8')

        p = re.compile(r'"servertime":(.*?),')
        values_dict['servertime'] = p.search(html).group(1).strip('\"')

        p1 = re.compile(r'"pcid":(.*?),')
        values_dict['pcid'] = p1.search(html).group(1).strip('\"')

        p2 = re.compile(r'"nonce":(.*?),')
        values_dict['nonce'] = p2.search(html).group(1).strip('\"')

        p3 = re.compile(r'"pubkey":(.*?),')
        values_dict['pubkey'] = p3.search(html).group(1).strip('\"')

        p4 = re.compile(r'"rsakv":(.*?),')
        values_dict['rsakv'] = p4.search(html).group(1).strip('\"')

        return values_dict

    def get_password(self, blog_values):
        '''
            這個函數是微博的json數據和網上的大神方法的出來的（抄來的）^_^
        '''

        rsapubkey = int(blog_values['pubkey'], 16)
        key = rsa.PublicKey(rsapubkey, 65537)
        massage = str(blog_values['servertime']) + '\t' + str(blog_values['nonce']) + '\n' + str(self.pwd)
        password = rsa.encrypt(massage, key)
        sp = password.encode('hex')
        return sp

    def login_weibo(self, blog_values, sp):

        values = {
            'entry': "weibo",
            'gateway': '1',
            'from': '',
            'savestate': '7',
            'userticket': '1',
            'pagerefer': "",
            'cfrom': '1',
            'vsnf': '1',
            'su': self.user,
            'service': 'miniblog',
            'servertime': blog_values['servertime'],
            'nonce': blog_values['nonce'],
            'pwencode': 'rsa2',
            'rsakv': blog_values['rsakv'],
            'sp': sp,
            'sr': "1440*900",
            'encoding': 'UTF-8',
            'prelt': '503',
            'url': 'http://weibo.com/ajaxlogin.php?framelogin=1&callback=parent.sinaSSOController.feedBackUrlCallBack',
            'returntype': 'META'
        }

        header = {
            'User-Agent': 'Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/35.0.1916.153 Safari/537.36'
        }
        url = 'http://login.sina.com.cn/sso/login.php?client=ssologin.js(v1.4.18)'

        '''獲取cookie信息 '''
        cj = cookielib.CookieJar()
        cj_support = urllib2.HTTPCookieProcessor(cj)
        opener = urllib2.build_opener(cj_support)

        data = urllib.urlencode(values)
        try:
            response = urllib2.Request(url, headers=header, data=data)
            html = opener.open(response).read().decode('gbk')
        except Exception, e:
            print e.message

        p = re.compile(r'location\.replace\(\'(.*?)\'\)')
        url = p.search(html).group(1)
        try:
            url_request = urllib2.Request(url)
            response_url = opener.open(url_request)
            page = response_url.read().decode('utf-8')
            p2 = re.compile(r'"userdomain":"(.*?)"')
            dom = p2.search(page).group(1)

            login_url = 'http://weibo.com/' + dom
            request_login_url = urllib2.Request(login_url)
            response_login_url = opener.open(request_login_url)
            per_html = response_login_url.read().decode('utf-8')
        except Exception:
            per_html = '登錄失敗'

        return per_html


if __name__ == '__main__':
    
    wbobj = Weibo('用戶名', '密碼')
    sp = wbobj.get_password(wbobj.get_pre_url_values)
    html = wbobj.login_weibo(blog_values=wbobj.get_pre_url_values, sp=sp)
    print html

 

麼，好比：把女神的照片全要了、自動查看女神的微博並將郵件發給你，下次再來弄這個。最近失眠的厲害，快點找到工做吧！！