在心力憔悴的時候,絕處逢生!搞了幾天,成功了,哈哈哈啊哈哈!
import requests
import time
import json
import re
import base64
import rsa
import binascii
import execjs
# 模擬新浪微博登錄的完整請求過程,包括預(yù)登錄,重定向,和最后返回個人主頁;
# 該項目的難點再與破解js加密的post數(shù)據(jù),在此基礎(chǔ)上,還需要多次對服務(wù)器發(fā)起多個請求,
# 完整的流程走下來,微博才鞥夠成功的登錄上
# 整體的框架梳理: 全程用session保存cookie 哦
# 第一:通過抓包可以發(fā)現(xiàn),我們在登錄微博首頁的時候,客戶端向服務(wù)器發(fā)起的請求并不是首頁的地址,而是/vistor/vistor
# 為了全真模擬,那么我們也必須先請求這個地址,然后再;
# 第二:請求微博的首頁,似乎沒什么意思,就是要走這個流程,也許不需要,代碼還沒有優(yōu)化;
# 第三:預(yù)登錄,這一步就很重要了,因為在后面的post登錄請求中會有很多的表單數(shù)據(jù),預(yù)登錄的響應(yīng)信息有很多我們想要的;
# 第四:找到加密password等數(shù)據(jù)的加密js,在js中找到加密的方式,破解加密;
# 第五:發(fā)起post登錄請求;
# 第六:發(fā)起多次的重定向請求
# 第七:打開個人首頁,到此便大功告成;perfect?。。。?!
class WeiBo:
def __init__(self,name,password):
self.start_url = 'https://passport.weibo.com/visitor/visitor'
self.user_name = name
self.user_password = password
def vister(self):
headers1 = {
"User-Agent": "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.181 Safari/537.36",
}
data1 = {
"entry": "miniblog",
"a": "enter",
"url": "https://weibo.com/",
"domain": ".weibo.com",
"ua": "php-sso_sdk_client-0.6.23",
"_rand": round(time.time(), 4),
}
self.ss = requests.Session()
self.r = self.ss.get(self.start_url,headers = headers1,params = data1)
self.url = self.r.url
def first(self):
# 打開微博首頁;
first_page_url = 'https://weibo.com/'
headers2 = {
"User-Agent": "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.181 Safari/537.36",
"Referer": self.url,
}
content = self.ss.get(first_page_url,headers = headers2)
def prelogin(self):
# 預(yù)登陸,拿到服務(wù)器返回的加密信息;
prelogin_url = 'https://login.sina.com.cn/sso/prelogin.php'
params = {
"entry": "weibo",
"callback": "sinaSSOController.preloginCallBack",
'su': '',
"rsakt":"mod",
"client": "ssologin.js(v1.4.19)",
"_": int(time.time()*1000)
}
content = self.ss.get(prelogin_url,params=params)
try:
pattern = re.compile(r'sinaSSOController.preloginCallBack\((.+?)\)')
content = re.findall(pattern,content.text)[0]
js = json.loads(content)
self.servertime = js['servertime']
self.nonce = js['nonce']
self.pubkey = js['pubkey']
self.rsakv = js['rsakv']
self.exectime = js['exectime']
print('服務(wù)器返回的密碼提取成功!')
except:
print('json解析不了')
def password(self):
# 解密js加密后的用戶密碼;用python rsa庫加密用戶密碼(這是解密的第一種方式)
rsakey = rsa.PublicKey(int(self.pubkey,16),int('10001',16))
strall = str(self.servertime) + '\t' + self.nonce + '\n' + self.user_password
content = rsa.encrypt(strall.encode('utf-8'),rsakey)
self.sp = binascii.b2a_hex(content)
def password2(self):
# 解密的第二種方式,通過execjs 調(diào)用PhantomJs,直接執(zhí)行js代碼,難道函數(shù)的返回值(密碼);
with open('totall.js','r',encoding='utf-8') as f:
source = f.read()
phantom = execjs.get('PhantomJs')
phantom_compile = phantom.compile(source)
call = phantom_compile.call('get_pass', 'nishijiba22', self.nonce, self.servertime, self.pubkey)
return call
def login(self):
form_data = {
"entry": "weibo",
"gateway": "1",
'from':'',
"savestate": "7",
"qrcode_flag": "false",
"useticket": "1",
"pagerefer":self.url,
"su": base64.b64encode(self.user_name.encode('utf-8')),
"service": "miniblog",
"servertime": int(time.time()),
"nonce": self.nonce,
"pwencode": "rsa2",
"rsakv": self.rsakv,
"sp": self.password2(),
"sr": "1366*768",
"encoding": "UTF-8",
"prelt": int(time.time()*1000)-self.exectime,
"url":"https://weibo.com/ajaxlogin.php?framelogin=1&callback=parent.sinaSSOController.feedBackUrlCallBack",
"returntype": "META"
}
url = 'https://login.sina.com.cn/sso/login.php?client=ssologin.js(v1.4.19)'
headers = {
"Origin": "https://weibo.com",
"User-Agent": "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.181 Safari/537.36",
"Referer": "https://weibo.com/",
}
content = self.ss.post(url,headers=headers,data=form_data).content.decode('gbk')
pattern = re.compile(r'location.replace\("(.+?)"\)')
self.cross_url = re.findall(pattern,content)[0]
# 別急別急你得到的還不是最終結(jié)果,新浪就是這么變態(tài)
def home(self):
# 獲取個人主頁的地址
# 處理第一個重定向
headers = {
"User-Agent": "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.181 Safari/537.36",
}
content = self.ss.get(self.cross_url,headers=headers).content.decode('GBK')
url2 = re.findall(r"location.replace\('(.+?)'\)",content)[0]
self.ss.get(url2,headers=headers)
# 處理第二個重定向;
url = 'https://weibo.com/ajaxlogin.php?framelogin=1&callback=parent.sinaSSOController.feedBackUrlCallBack&sudaref=weibo.com'
content = self.ss.get(url,headers=headers).content.decode('gbk')
pattern = r'"uniqueid":"(\d+?)"'
try:
uuid = re.findall(pattern, content)[0]
except:
print('沒有匹配到uniquid')
else:
# 處理第三個重定向
url3 = 'https://weibo.com/nguide/interest'
self.ss.get(url3,headers=headers)
# 處理第四個重定向
url4= 'https://weibo.com/nguide/interests'
self.ss.get(url4,headers=headers)
# 拼接個人主頁
url = 'https://weibo.com/u/{}/home'.format(uuid)
headers = {
"User-Agent": "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.181 Safari/537.36",
"Referer": "https://weibo.com/",
}
home_page = self.ss.get(url,headers=headers).text
print('出結(jié)果了哦'*9)
print(home_page)
def main(self):
self.vister()
self.first()
self.prelogin()
# self.password()
self.login()
self.home()
if __name__ == '__main__':
name = 'your user name'
password = 'your password'
weibo = WeiBo(name,password)
weibo.main()
文章寫的不夠詳細(xì),如有不懂之處,歡迎留言探討;