python关于模拟登陆微博（PC）
微博模拟登陆
1.基类对象的方法
建立一个类
__init__初始化方法,接收username和password。
class launcher():
def __init__(self, username, password):
self.password = password
self.username = username
2.定义一个函数，目的用于取到nonce , servertime , pubkey信息
伪造一个request用于获取预登陆信息
def get_prelogin_args(self):
json_pattern = re.compile('\((.*)\)') 这个是我输入账号但是没登录得到的一个json文件
url = 'https://login.sina.com.cn/sso/prelogin.php?entry=weibo&callback=sinaSSOController.preloginCallBack&su=&' + self.get_encrypted_name() + '&rsakt=mod&checkpin=1&client=ssologin.js(v1.4.19)'
try:
request = urllib.request.Request(url)
response = urllib.request.urlopen(request)
raw_data = response.read().decode('utf-8')
json_data = json_pattern.search(raw_data).group(1)
data = json.loads(json_data)
return data
except urllib.error as e:
print("%d" % e.code)
return None
3.定义一个方法，解密rsa加密的密码，其中必须的pubkey , nonce , rsakv等关键字使用一个字典data 传入
def get_encrypted_pw(self, data):
rsa_e = 65537 # 0x10001（转换成10进制）
pw_string = str(data['servertime']) + '\t' + str(data['nonce']) + '\n' + str(self.password)
key = rsa.PublicKey(int(data['pubkey'], 16), rsa_e)
pw_encypted = rsa.encrypt(pw_string.encode('utf-8'), key)
self.password = '' # 清空password
passwd = binascii.b2a_hex(pw_encypted) #换成16进制
print(pw_encypted)
print(passwd)
return passwd
4.定义一个方法，解密base64加密的账号（手机账号会被混淆，%3D是=号，邮箱账号@会变成%40）
def get_encrypted_name(self):
username_urllike = urllib.request.quote(self.username)
username_encrypted = base64.b64encode(bytes(username_urllike, encoding='utf-8'))
return username_encrypted.decode('utf-8')
5.建立一个cookie容器用于整个登录过程的cookie的绑定
def enableCookies(self):
# 建立一个cookies 容器
cookie_container = http.cookiejar.CookieJar()
# 将一个cookies容器和一个HTTP的cookie的处理器绑定
cookie_support = urllib.request.HTTPCookieProcessor(cookie_container)
# 创建一个opener,设置一个handler用于处理http的url打开
opener = urllib.request.build_opener(cookie_support, urllib.request.HTTPHandler)
# 安装opener，此后调用urlopen()时会使用安装过的opener对象
urllib.request.install_opener(opener)
6.POST表单提交
def build_post_data(self, raw):
post_data = {
"entry": "weibo",
"gateway": "1",
"from": "",
"savestate": "7",
"useticket": "1",
"pagerefer": "https://www.baidu.com/link?url=2m74RGf8hzJIXFwGexWMuQWqqmvcpu-nMjK8cyuZIcC&wd=&eqid=85fee59800006e0c000000025a4cbc7b",
"vsnf": "1",
"su": self.get_encrypted_name(),
"service": "miniblog",
"servertime": raw['servertime'],
"nonce": raw['nonce'],
"pwencode": "rsa2",
"rsakv": raw['rsakv'],
"sp": self.get_encrypted_pw(raw),
"sr": "1366*768",
"encoding": "UTF-8",
"prelt": "854",
"url": "https://weibo.com/ajaxlogin.php?framelogin=1&callback=parent.sinaSSOController.feedBackUrlCallBack",
"returntype": "MENT"
}
data = urllib.parse.urlencode(post_data).encode('utf-8')
return data
7.开始登录
def login(self):
url = 'http://login.sina.com.cn/sso/login.php?client=ssologin.js(v1.4.19)'
self.enableCookies()
data = self.get_prelogin_args()
post_data = self.build_post_data(data)
headers = {
"User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/49.0.2623.87 Safari/537.36"
}
try:
request = urllib.request.Request(url=url, data=post_data, headers=headers)
response = urllib.request.urlopen(request)
html = response.read().decode('GBK')
print(html)
except urllib.error as e:
print('-------------------------')
print(e.code)
打印出
html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=GBK" />
<title>新浪通行证</title>
<script charset="utf-8" src="https://i.sso.sina.com.cn/js/ssologin.js"></script>
</head>
<body>
正在登录 ...
<script>
try{sinaSSOController.setCrossDomainUrlList({"retcode":0,"arrURL":["https:\/\/passport.97973.com\/sso\/crossdomain?action=login&savestate=1546602068","https:\/\/passport.krcom.cn\/sso\/crossdomain?service=krvideo&savestate=1&ticket=ST-NTgxNjY5MjI5NQ%3D%3D-1515066068-tc-85B8AE28E184F1A1E0435DA6D4DFBBA3-1&ssosavestate=1546602068","https:\/\/passport.weibo.cn\/sso\/crossdomain?action=login&savestate=1"]});}
catch(e){
var msg = e.message;
var img = new Image();
var type = 1;
img.src = 'https://login.sina.com.cn/sso/debuglog?msg=' + msg +'&type=' + type;
}try{sinaSSOController.crossDomainAction('login',function(){location.replace('https://passport.weibo.com/wbsso/login?ssosavestate=1546602068&url=https%3A%2F%2Fweibo.com%2Fajaxlogin.php%3Fframelogin%3D1%26callback%3Dparent.sinaSSOController.feedBackUrlCallBack&display=0&ticket=ST-NTgxNjY5MjI5NQ==-1515066068-tc-240ED98A102AB2CF543CA399EF087D0C-1&retcode=0');});}
catch(e){
var msg = e.message;
var img = new Image();
var type = 2;
img.src = 'https://login.sina.com.cn/sso/debuglog?msg=' + msg +'&type=' + type;
}
</script>
</body>
</html>
8.第一次重定向
p = re.compile('location\.replace\([\'"](.*?)[\'"]\)')
try:
login_url = p.search(html).group(1)
print(login_url)
request = urllib.request.Request(login_url)
response = urllib.request.urlopen(request)
page = response.read().decode('GBK')
print(page)
打印出
<html><head><script language='javascript'>parent.sinaSSOController.feedBackUrlCallBack({"result":true,"userinfo":{"uniqueid":"5816692295","userid":null,"displayname":null,"userdomain":"?wvr=5&lf=reg"}});</script></head><body></body></html>
9.第二次重定向
p2 = re.compile(r'"userdomain":"(.*?)"')
try:
login_url = 'http://weibo.com/' + p2.search(page).group(1)
print(login_url)
request = urllib.request.Request(login_url)
response = urllib.request.urlopen(request)
final = response.read().decode('utf-8')
print(final)
完整代码
import urllib.error
import urllib.request
import re
import rsa
import http.cookiejar # 从前的cookielib
import base64
import json
import urllib
import urllib.parse
import binascii
# 用于模拟登陆新浪微博
class launcher():
def __init__(self, username, password):
self.password = password
self.username = username
def get_prelogin_args(self):
'''
该函数用于模拟预登录过程,并获取服务器返回的 nonce , servertime , pub_key 等信息
'''
json_pattern = re.compile('\((.*)\)')
url = 'https://login.sina.com.cn/sso/prelogin.php?entry=weibo&callback=sinaSSOController.preloginCallBack&su=&' + self.get_encrypted_name() + '&rsakt=mod&checkpin=1&client=ssologin.js(v1.4.19)'
try:
request = urllib.request.Request(url)
response = urllib.request.urlopen(request)
raw_data = response.read().decode('utf-8')
json_data = json_pattern.search(raw_data).group(1)
data = json.loads(json_data)
return data
except urllib.error as e:
print("%d" % e.code)
return None
def get_encrypted_pw(self, data):
rsa_e = 65537 # 0x10001
pw_string = str(data['servertime']) + '\t' + str(data['nonce']) + '\n' + str(self.password)
key = rsa.PublicKey(int(data['pubkey'], 16), rsa_e)
pw_encypted = rsa.encrypt(pw_string.encode('utf-8'), key)
self.password = '' # 清空password
passwd = binascii.b2a_hex(pw_encypted)
print(pw_encypted)
print(passwd)
return passwd
def get_encrypted_name(self):
username_urllike = urllib.request.quote(self.username)
username_encrypted = base64.b64encode(bytes(username_urllike, encoding='utf-8'))
return username_encrypted.decode('utf-8')
def enableCookies(self):
# 建立一个cookies 容器
cookie_container = http.cookiejar.CookieJar()
# 将一个cookies容器和一个HTTP的cookie的处理器绑定
cookie_support = urllib.request.HTTPCookieProcessor(cookie_container)
# 创建一个opener,设置一个handler用于处理http的url打开
opener = urllib.request.build_opener(cookie_support, urllib.request.HTTPHandler)
# 安装opener，此后调用urlopen()时会使用安装过的opener对象
urllib.request.install_opener(opener)
def build_post_data(self, raw):
post_data = {
"entry": "weibo",
"gateway": "1",
"from": "",
"savestate": "7",
"useticket": "1",
"pagerefer": "https://www.baidu.com/link?url=2m74RGf8hzJIXFwGexWMuQWqqmvcpu-nMjK8cyuZIcC&wd=&eqid=85fee59800006e0c",
"vsnf": "1",
"su": self.get_encrypted_name(),
"service": "miniblog",
"servertime": raw['servertime'],
"nonce": raw['nonce'],
"pwencode": "rsa2",
"rsakv": raw['rsakv'],
"sp": self.get_encrypted_pw(raw),
"sr": "1366*768",
"encoding": "UTF-8",
"prelt": "854",
"url": "https://weibo.com/ajaxlogin.php?framelogin=1&callback=parent.sinaSSOController.feedBackUrlCallBack",
"returntype": "MENT"
}
data = urllib.parse.urlencode(post_data).encode('utf-8')
return data
def login(self):
url = 'http://login.sina.com.cn/sso/login.php?client=ssologin.js(v1.4.19)'
self.enableCookies()
data = self.get_prelogin_args()
post_data = self.build_post_data(data)
headers = {
"User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/49.0.2623.87 Safari/537.36"
}
try:
request = urllib.request.Request(url=url, data=post_data, headers=headers)
response = urllib.request.urlopen(request)
html = response.read().decode('GBK')
print(html)
except urllib.error as e:
print('-------------------------')
print(e.code)
p = re.compile('location\.replace\([\'"](.*?)[\'"]\)')
p2 = re.compile(r'"userdomain":"(.*?)"')
try:
login_url = p.search(html).group(1)
print(login_url)
request = urllib.request.Request(login_url)
response = urllib.request.urlopen(request)
page = response.read().decode('GBK')
print(page)
login_url = 'http://weibo.com/' + p2.search(page).group(1)
print(login_url)
request = urllib.request.Request(login_url)
response = urllib.request.urlopen(request)
final = response.read().decode('utf-8')
print(final)
except Exception as err:
print(err)
# return 0
if __name__ == '__main__':
launcher = launcher('', '') # 邮箱（账号）、密码
if launcher.login() == True:
print("登陆成功！")
