最新消息:七维网络改版啦,域名www.7dwww.com

百度图片JSON中的objURL解密

网络技术 sevennet 3408浏览

在抓取百度图片数据时,JSON数据里的objURL是经过加密的,我们需要进行解密来得来真正的url。

有关百度图片抓取接口,请看我上一篇文章关于百度图片api,分类图片API,搜索图片API

我们来看一下objURL的格式:

“objURL”: “ippr_z2C$qAzdH3FAzdH3Ft42f6v_z&e3Bkwt17_z&e3Bv54AzdH3Ft42w1AzdH3FrtvAzdH3Ftpj4AzdH3F0wu9aw18md1lud1ncjmuadnkwnjvbw8nmdd0vvjn_z&e3B3r2”,

“fromURL”: “ippr_z2C$qAzdH3FAzdH3Fooo_z&e3Bp7h7vitgw_z&e3BvgAzdH3F6AzdH3Fri5p5AzdH3FetjoAzdH3Ft1AzdH3Fddccad0m99AzdH3F”,

解密方法很简单,秘钥是一个字符的对应关系,有2种映射:

(1)多个字符映射为一个字符,’_z2C$q’=>’:’,’_z&e3B’=>’.’,’AzdH3F’=>’/’,

(2)单个字符映射为单字符。根据这个关系可将密文解密为明文,实现并不困难。

下面为大家提供几种解密的代码

一、PHP版

<?PHP
$f = array('w'=>'a','k'=>'b','v'=>'c','1'=>'d','j'=>'e','u'=>'f','2'=>'g','i'=>'h','t'=>'i','3'=>'j','h'=>'k','s'=>'l','4'=>'m','g'=>'n','5'=>'o','r'=>'p','q'=>'q','6'=>'r','f'=>'s','p'=>'t','7'=>'u','e'=>'v','o'=>'w','8'=>'1','d'=>'2','n'=>'3','9'=>'4','c'=>'5','m'=>'6','0'=>'7','b'=>'8','l'=>'9','a'=>'0','_z2C$q'=>':','_z&e3B'=>'.','AzdH3F'=>'/');
 
$url = 'ippr_z2C$qAzdH3FAzdH3Ft4f_z&e3Bw6ptg2nmc_z&e3Bv54AzdH3Fg51jAzdH3F8da90bAzdH3F'; // 这里需要用单引号
 
$url = preg_replace_callback('/_z2C$q|_z&e3B|AzdH3F/', function($matches){ global $f; return $f[$matches[0]]; }, $url); 
$url = preg_replace_callback('/[a-wd]/', function($matches){ global $f; return $f[$matches[0]]; }, $url); 
echo $url;
?>

二、JS版

<script type="text/javascript">
  var f = {   w: "a",   k: "b",   v: "c",   1: "d",   j: "e",   u: "f",   2: "g",   i: "h",   t: "i",   3: "j",   h: "k",   s: "l",   4: "m",   g: "n",   5: "o",   r: "p",   q: "q",   6: "r",   f: "s",   p: "t",   7: "u",   e: "v",   o: "w",   8: "1",   d: "2",   n: "3",   9: "4",   c: "5",   m: "6",   0: "7",   b: "8",   l: "9",   a: "0",   _z2C$q: ":",   "_z&e3B": ".",   AzdH3F: "/"   };
 
  var url = "ippr_z2C$qAzdH3FAzdH3Fjgp_z&e3Bvg6_z&e3BvgAzdH3FstfpAzdH3Fda8candnAzdH3FWada8candnn98c9lndadl9_z&e3B3r2";
 
  var h = /(_z2C$q|_z&e3B|AzdH3F)/g;
  var e = url.replace(h, function(t, e) { return f[e] });
  
  var s = /([a-wd])/g;
  e = e.replace(s, function(t, e) { return f[e] });
  document.write(e);
</script>

三、Pathon版

#!/usr/bin/env python
# -*- coding: utf-8 -*-

str_table = {
    '_z2C$q': ':',
    '_z&e3B': '.',
    'AzdH3F': '/'
}

char_table = {
    'w': 'a',
    'k': 'b',
    'v': 'c',
    '1': 'd',
    'j': 'e',
    'u': 'f',
    '2': 'g',
    'i': 'h',
    't': 'i',
    '3': 'j',
    'h': 'k',
    's': 'l',
    '4': 'm',
    'g': 'n',
    '5': 'o',
    'r': 'p',
    'q': 'q',
    '6': 'r',
    'f': 's',
    'p': 't',
    '7': 'u',
    'e': 'v',
    'o': 'w',
    '8': '1',
    'd': '2',
    'n': '3',
    '9': '4',
    'c': '5',
    'm': '6',
    '0': '7',
    'b': '8',
    'l': '9',
    'a': '0'
}

# str 的translate方法需要用单个字符的十进制unicode编码作为key
# value 中的数字会被当成十进制unicode编码转换成字符
# 也可以直接用字符串作为value
char_table = {ord(key): ord(value) for key, value in char_table.items()}

def decode(url):
    # 先替换字符串
    for key, value in str_table.items():
        url = url.replace(key, value)
    # 再替换剩下的字符
    return url.translate(char_table)


if __name__ == '__main__':
    url = r"ippr_z2C$qAzdH3FAzdH3Ffl_z&e3Bftgwt42_z&e3BvgAzdH3F4omlaAzdH3Faa8W3ZyEpymRmx3Y1p7bb&mla"
    print(decode(url))

四、C语言版

#include <stdio.h>
#include <string.h>
 
// return length;
int Decode(const char *src, const char *table, char *dest) {
  char *d = dest;
  const char *p = src;
  while (*p != 0) {
    if (*p == '_') {
      if (strncmp(p, "_z2C$q", 6) == 0) {
        *dest++ = ':';
        p += 6;
      } else if (strncmp(p, "_z&e3B", 6) == 0) {
        *dest++ = '.';
        p += 6;
      } else {
        *dest++ = *p++;
      }
    } else if (*p == 'A') {
      if (strncmp(p, "AzdH3F", 6) == 0) {
        *dest++ = '/';
        p += 6;
      } else {
        *dest++ = *p++;
      }
    } else if (table[*p] == 0) {
      *dest++ = *p++;
    } else {
      *dest++ = table[*p++];
    }
  }
  *dest = 0;
  return dest - d;
}
 
int main(int argc, char **argv) {
  static char table[128] = {0};
  table['w'] = 'a';
  table['k'] = 'b';
  table['v'] = 'c';
  table['1'] = 'd';
  table['j'] = 'e';
  table['u'] = 'f';
  table['2'] = 'g';
  table['i'] = 'h';
  table['t'] = 'i';
  table['3'] = 'j';
  table['h'] = 'k';
  table['s'] = 'l';
  table['4'] = 'm';
  table['g'] = 'n';
  table['5'] = 'o';
  table['r'] = 'p';
  table['q'] = 'q';
  table['6'] = 'r';
  table['f'] = 's';
  table['p'] = 't';
  table['7'] = 'u';
  table['e'] = 'v';
  table['o'] = 'w';
  table['8'] = '1';
  table['d'] = '2';
  table['n'] = '3';
  table['9'] = '4';
  table['c'] = '5';
  table['m'] = '6';
  table['0'] = '7';
  table['b'] = '8';
  table['l'] = '9';
  table['a'] = '0';
 
  char *url = "ippr_z2C$qAzdH3FAzdH3Ft428_z&e3Bd0_z&e3BvgAzdH3Ft4w2jfAzdH3Fda8a8aAzdH3FddAzdH3F8db00d0dnd_9amln8aa_z&e3B3r2";
  char dest[1024];
  Decode(url, table, dest);
  printf("%sn", dest);
  return 0;
}

 

转载请注明:七维网络 » 百度图片JSON中的objURL解密