超详细百度翻译js逆向（token 和 sign）

1.抓包看看需要什么参数选中的数据包有点可疑

请求的url和post的参数

并且返回了这个内容
我们用fiddler抓包看到具体的设置cookies等过程


第一次请求返回了一个setcookie,

第二次请求带上了第一次返回的cookies,有两个有用的BAIDUID , FG
其他的是浏览器设置的，不用理会

刷新就知道了，只有sign和token两个参数是变化的，query是每次请求的字符串， langdetect是检测语言的，
语言检测不用管，用python实现很容易

2.分析sign

全局搜索sign， 有点多，还是打断点吧，打一个xhr断点

输入内容会直接断下来，查看堆栈

设置断下的url是：https://fanyi.baidu.com/v2transapi?from=en&to=zh
查看堆栈，很明显send, ajax,这两个不是，


向上一看，


和请求的 完全一样
先追sign

点进去

把函数粘贴进去，运行，让他报错

在这打两个断点，然后看i是什么东西，
==不要在那直接框住，看i,==这样是错误的

可以多刷新几次，可以发现这玩应是个定值

运行，报错

n就在他上面，把他复制进去，放在e函数上面，

然后就发现就可以运行了，
sign就抠出来了，

3.token分析

发现他是在window.common.token
透露一下，window.common.token一般这种window.xxx.xxx一般是服务器返回的数据

总共有26个，不多，挨个找，
然后就会发现找不到！！！！
转全局搜素

发现在index页面，结合一开始的抓包分析
试着写一下代码

def user_agent():
    ua = ['Mozilla/5.0 (Windows NT 6.2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/28.0.1464.0 Safari/537.36',
          'Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/31.0.1650.16 Safari/537.36',
          'Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/35.0.3319.102 Safari/537.36',
          'Mozilla/5.0 (X11; CrOS i686 3912.101.0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/27.0.1453.116 Safari/537.36',
          'Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/27.0.1453.93 Safari/537.36',
          'Mozilla/5.0 (Windows NT 6.2; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/32.0.1667.0 Safari/537.36',
          'Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:17.0) Gecko/20100101 Firefox/17.0.6',
          'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/28.0.1468.0 Safari/537.36',
          'Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2224.3 Safari/537.36',
          'Mozilla/5.0 (X11; CrOS i686 3912.101.0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/27.0.1453.116 Safari/537.36']
    return random.choice(ua)

url = "https://fanyi.baidu.com/"
session = requests.session()
headers = {
    'User-Agent': user_agent(),
    'Host': 'fanyi.baidu.com',
    'sec-ch-ua': '" Not A;Brand";v="99", "Chromium";v="90", "Google Chrome";v="90",',
    'sec-ch-ua-mobile': '?0',
    'Sec-Fetch-Dest': 'document',
    'Sec-Fetch-Mode': 'navigate',
    'Sec-Fetch-User': '?1',
}
resp = session.get(url, headers=headers).content.decode()
res = session.get(url, headers=headers).content.decode()

第二个res,就可以返回数据了。而且里面有token
然后用正则提取一下

token = re.findall(r"token: '(.*)',", res, re.M)[0]

调用execjs获取sign

with open('baidufy.js', 'r', encoding='utf-8')as fp:
    js = fp.read()
    sign = execjs.compile(js).call('SDK', query)

检测输入的语言

query_lang = 'en' if 40 < ord(query[0:1]) < 91 or 96 < ord(query[0:1]) < 123 else 'zh'
trans_lang = 'en' if query_lang == 'zh' else 'zh'

构造data

data = {
    'from': query_lang,
    'to': trans_lang,
    'query': query,
    'transtype': 'realtime',
    'sign': sign,
    'token': token,
    'domain': 'common'
}

url = "https://fanyi.baidu.com/v2transapi?from={}&to={}".format(query_lang, trans_lang)
req = session.post(url, headers=headers, data=data)
decode = req.content.decode('gbk','ignore')
loads = json.loads(decode)
res = loads['trans_result']['data'][0]['dst']
print(decode)
print(res)

全部代码

#!usr/bin/env python
# coding:utf-8
"""
 @File  :baidufy.py
 @Author:小生
 @date  : 2021-05-15 11:57
"""
import json
import zlib

import requests
import re
import random
import execjs

query = "may"
def user_agent():
    ua = ['Mozilla/5.0 (Windows NT 6.2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/28.0.1464.0 Safari/537.36',
          'Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/31.0.1650.16 Safari/537.36',
          'Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/35.0.3319.102 Safari/537.36',
          'Mozilla/5.0 (X11; CrOS i686 3912.101.0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/27.0.1453.116 Safari/537.36',
          'Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/27.0.1453.93 Safari/537.36',
          'Mozilla/5.0 (Windows NT 6.2; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/32.0.1667.0 Safari/537.36',
          'Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:17.0) Gecko/20100101 Firefox/17.0.6',
          'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/28.0.1468.0 Safari/537.36',
          'Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2224.3 Safari/537.36',
          'Mozilla/5.0 (X11; CrOS i686 3912.101.0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/27.0.1453.116 Safari/537.36']
    return random.choice(ua)

url = "https://fanyi.baidu.com/"
session = requests.session()
headers = {
    'User-Agent': user_agent(),
    'Host': 'fanyi.baidu.com',
    'sec-ch-ua': '" Not A;Brand";v="99", "Chromium";v="90", "Google Chrome";v="90",',
    'sec-ch-ua-mobile': '?0',
    'Sec-Fetch-Dest': 'document',
    'Sec-Fetch-Mode': 'navigate',
    'Sec-Fetch-User': '?1',
}
resp = session.get(url, headers=headers).content.decode()
res = session.get(url, headers=headers).content.decode()
token = re.findall(r"token: '(.*)',", res, re.M)[0]
with open('baidufy.js', 'r', encoding='utf-8')as fp:
    js = fp.read()
    sign = execjs.compile(js).call('SDK', query)

query_lang = 'en' if 40 < ord(query[0:1]) < 91 or 96 < ord(query[0:1]) < 123 else 'zh'
trans_lang = 'en' if query_lang == 'zh' else 'zh'
data = {
    'from': query_lang,
    'to': trans_lang,
    'query': query,
    'transtype': 'realtime',
    'sign': sign,
    'token': token,
    'domain': 'common'
}

url = "https://fanyi.baidu.com/v2transapi?from={}&to={}".format(query_lang, trans_lang)
req = session.post(url, headers=headers, data=data)
decode = req.content.decode('gbk','ignore')
loads = json.loads(decode)
res = loads['trans_result']['data'][0]['dst']
print(decode)
print(res)

query里面放的是要查询的数据