首页 > > 网络编程 > 其它 >

破解百度翻译页面api参数加密

2019-02-25 16:14:29来源：博客园阅读 ()

我们的目标 https://fanyi.baidu.com/ 找到获取翻译的请求

是这个 https://fanyi.baidu.com/v2transapi

查看一下post提交的表单，是这个

其中的en表示英文，zh表示中文，query是我们输入的，transtype与semple_means_flag的内容是固定的。现在就是差sign和token。

首先查找sign，在全局搜索搜索sign。出现这样

可以发现里面有很多，找到正确的那个，像下面

我们发现这个可能就是我们要找的，点击进去。

可以看出来这是应该ajax请求，p里面的参数就是我们要找的参数。在5828和5831序号哪里点一下，然后打开断点。刷新页面，输入一个字母，就会和下面一样。

这样然后鼠标放在m上面悬停一下会出现一个跳转，点击可以跳转到他的函数哪里。跳转过后我们看到m函数是

 1     function n(r, o) {
 2         for (var t = 0; t < o.length - 2; t += 3) {
 3             var a = o.charAt(t + 2);
 4             a = a >= "a" ? a.charCodeAt(0) - 87 : Number(a),
 5             a = "+" === o.charAt(t + 1) ? r >>> a : r << a,
 6             r = "+" === o.charAt(t) ? r + a & 4294967295 : r ^ a
 7         }
 8         return r
 9     }
10     function e(r) {
11         var o = r.match(/[\uD800-\uDBFF][\uDC00-\uDFFF]/g);
12         if (null === o) {
13             var t = r.length;
14             t > 30 && (r = "" + r.substr(0, 10) + r.substr(Math.floor(t / 2) - 5, 10) + r.substr(-10, 10))
15         } else {
16             for (var e = r.split(/[\uD800-\uDBFF][\uDC00-\uDFFF]/), C = 0, h = e.length, f = []; h > C; C++)
17                 "" !== e[C] && f.push.apply(f, a(e[C].split(""))),
18                 C !== h - 1 && f.push(o[C]);
19             var g = f.length;
20             g > 30 && (r = f.slice(0, 10).join("") + f.slice(Math.floor(g / 2) - 5, Math.floor(g / 2) + 5).join("") + f.slice(-10).join(""))
21         }
22         var u = void 0
23           , l = "" + String.fromCharCode(103) + String.fromCharCode(116) + String.fromCharCode(107);
24         u = null !== i ? i : (i = window[l] || "") || "";
25         for (var d = u.split("."), m = Number(d[0]) || 0, s = Number(d[1]) || 0, S = [], c = 0, v = 0; v < r.length; v++) {
26             var A = r.charCodeAt(v);
27             128 > A ? S[c++] = A : (2048 > A ? S[c++] = A >> 6 | 192 : (55296 === (64512 & A) && v + 1 < r.length && 56320 === (64512 & r.charCodeAt(v + 1)) ? (A = 65536 + ((1023 & A) << 10) + (1023 & r.charCodeAt(++v)),
28             S[c++] = A >> 18 | 240,
29             S[c++] = A >> 12 & 63 | 128) : S[c++] = A >> 12 | 224,
30             S[c++] = A >> 6 & 63 | 128),
31             S[c++] = 63 & A | 128)
32         }
33         for (var p = m, F = "" + String.fromCharCode(43) + String.fromCharCode(45) + String.fromCharCode(97) + ("" + String.fromCharCode(94) + String.fromCharCode(43) + String.fromCharCode(54)), D = "" + String.fromCharCode(43) + String.fromCharCode(45) + String.fromCharCode(51) + ("" + String.fromCharCode(94) + String.fromCharCode(43) + String.fromCharCode(98)) + ("" + String.fromCharCode(43) + String.fromCharCode(45) + String.fromCharCode(102)), b = 0; b < S.length; b++)
34             p += S[b],
35             p = n(p, F);
36         return p = n(p, D),
37         p ^= s,
38         0 > p && (p = (2147483647 & p) + 2147483648),
39         p %= 1e6,
40         p.toString() + "." + (p ^ m)
41     }

这是sign的加密函数，我们可以发现传的值就是我们在输入框输入的值。

把这些保存在一个.js的文件保持起来。里面的i = window[l] 这个window对象是浏览器才有的，如果我们使用python的js2py或者execjs会报错

我们查看到这个值是320305.131321201

var u = void 0
     , l = "" + String.fromCharCode(103) + String.fromCharCode(116) + String.fromCharCode(107);
      u = null !== i ? i : (i = window[l] || "") || "";
修改为
var u = void 0, i = null;
u = null !== i ? i : (i = "320305.131321201" || "") || "";

这样执行就不会出错

接下来还差token值了，我们搜索token发现如下

发现就在第一个，点进去

就在请求的html里面。现在需要的参数都找到了。

 1 import requests
 2 import js2py
 3 import re
 4 
 5 
 6 class BaiDuTranslateAPI(object):
 7     headers = {
 8         'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.181 Safari/537.36'
 9     }
10     def __init__(self):
11         super(BaiDuTranslateAPI).__init__()
12         self.GetReady()
13     def GetReady(self):
14         url_index = 'https://www.baidu.com'
15         self.session = requests.session()
16         self.session.get(url=url_index, headers=self.headers)
17         self.headers['Referer'] = url_index
18         url_html = 'https://fanyi.baidu.com/translate?aldtype=16047&query=&keyfrom=baidu&smartresult=dict&lang=auto2zh'
19         html = self.session.get(url=url_html, headers=self.headers)
20         comm = re.compile('token: \'(\w+)\'')
21         self.token = comm.search(html.text).group(1)
22         self.headers['Referer'] = url_html
23 
24     def Get_Js(self):
25         with open(r'D:\vim\hello_data(1)\panyi.js', 'r', encoding='utf-8') as f:
26             return f.read()
27     def Translate(self,file):
28         files = False
29         file = str(file)
30         for i in file:
31             if '\u4e00' <= i.encode().decode('utf-8') <= '\u9fff':
32                 files = True
33             else:
34                 files = False
35             if files == False:
36                 break
37         return files
38 
39     def BaiDu(self,file):
40         run_js = js2py.EvalJs({})
41         run_js.execute(self.Get_Js())
42         sign = run_js.e(file)
43         url_api = 'https://fanyi.baidu.com/v2transapi'
44         is_it = self.Translate(file)
45         if is_it:
46             iia = 'zh'
47             iib = 'en'
48         else:
49             iia = 'en'
50             iib = 'zh'
51         data = {
52             'from': iia,
53             'to': iib,
54             'query': file,
55             'transtype': 'realtime',
56             'simple_means_flag': '3',
57             'sign': sign,
58             'token': self.token
59         }
60         html = self.session.post(url=url_api, headers=self.headers, data=data).json()
61         return (html['trans_result']['data'][0]['dst'])
62     def Start(self,file='i'):
63         try:
64             int(file)
65             return file
66         except:
67             # self.zhunbei()
68             files = self.BaiDu(file)
69             return files
70 
71 if __name__ == '__main__':
72     a = BaiDuTranslateAPI()
73     print(a.Start('i'))
74     print(a.Start('love'))
75     print(a.Start('you'))