电脑版百度翻译接口python爬虫

js代码已失效

近来对爬虫比较感兴趣，然后本渣的英文的水平就是个渣渣，所以写了百度翻译网页版的爬虫。

本人技术有限大神勿喷，如有不当之处欢迎指出。

爬虫环境为 python3.x 如想运行在python2.7，请自行修改。

需要安装第三方的套件包：requests、execjs

建议直接如下安装

pip3 install requests
pip3 install pyexecjs

废话不多说贴代码。

#!/usr/bin/env python3
# encoding: utf-8
# 源码基于 csdn的HONGQUAN的代码修改而来


import re
import requests
import execjs
import urllib
import json


class Baidufanyi(object):
    def __init__(self):
        self.gtk = None
        self.token = None
        self.header = {
            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.108 Safari/537.36",
            "Cookie": "'locale=zh;BAIDUID=DB7712AF47C959AC2BF32ECFF8BD8F71:FG=1; from_lang_often=%5B%7B%22value%22%3A%22zh%22%2C%22text%22%3A%22%u4E2D%u6587%22%7D%2C%7B%22value%22%3A%22en%22%2C%22text%22%3A%22%u82F1%u8BED%22%7D%5D; REALTIME_TRANS_SWITCH=1; FANYI_WORD_SWITCH=1; HISTORY_SWITCH=1; SOUND_SPD_SWITCH=1; SOUND_PREFER_SWITCH=1;'"
        }
        self.html = requests.get('http://fanyi.baidu.com', headers=self.header)
        self.html.encoding = 'utf-8'
        self.signCode = 'function a(r,o){for(var t=0;t<o.length-2;t+=3){var a=o.charAt(t+2);a=a>="a"?a.charCodeAt(0)-87:Number(a),a="+"===o.charAt(t+1)?r>>>a:r<<a,r="+"===o.charAt(t)?r+a&4294967295:r^a}return r}var C=null;var hash=function(r,_gtk){var o=r.length;o>30&&(r=""+r.substr(0,10)+r.substr(Math.floor(o/2)-5,10)+r.substr(-10,10));var t=void 0,t=null!==C?C:(C=_gtk||"")||"";for(var e=t.split("."),h=Number(e[0])||0,i=Number(e[1])||0,d=[],f=0,g=0;g<r.length;g++){var m=r.charCodeAt(g);128>m?d[f++]=m:(2048>m?d[f++]=m>>6|192:(55296===(64512&m)&&g+1<r.length&&56320===(64512&r.charCodeAt(g+1))?(m=65536+((1023&m)<<10)+(1023&r.charCodeAt(++g)),d[f++]=m>>18|240,d[f++]=m>>12&63|128):d[f++]=m>>12|224,d[f++]=m>>6&63|128),d[f++]=63&m|128)}for(var S=h,u="+-a^+6",l="+-3^+b+-f",s=0;s<d.length;s++)S+=d[s],S=a(S,u);return S=a(S,l),S^=i,0>S&&(S=(2147483647&S)+2147483648),S%=1e6,S.toString()+"."+(S^h)}'
        try:
            # 获取 gtk
            match = re.search("window.gtk = '(.*?)';", self.html.text, re.S).group(1)
            self.gtk = match
            # print('gtk = ', gtk)
            # 正则匹配 token
            match = re.search("token: '(.*?)'", self.html.text, re.S).group(1)
            self.token = match
            # print('token = ', token)
        except Exception:
            print('没有获取到“gtk”，或者“token”')
            return

    def shuru(self, source):
        """判断第一个字符是否是中文"""
        if '\u4e00' <= source[0] <= '\u9fff':
            en = False
        else:
            en = True
        fromLanguage = 'en' if en else 'zh'
        toLanguage = 'zh' if en else 'en'
        return fromLanguage, toLanguage

    def sign(self, source):
        """计算sign"""
        sign = execjs.compile(self.signCode).call('hash', source, self.gtk)
        return sign

    def fanyi(self, fromLanguage, toLanguage, source, sign):
        v2transapi = 'http://fanyi.baidu.com/v2transapi?from=%s&to=%s&query=%s&transtype=translang&simple_means_flag=3&sign=%s&token=%s' % (
            fromLanguage, toLanguage, urllib.parse.quote(source), sign, self.token)
        translate_result = requests.get(v2transapi, headers=self.header)
        return translate_result

if __name__ == '__main__':
　　Baidu = Baidufanyi()
　　print('请输入要翻译的str(按 123 退出翻译）:')
　　while True:
　　　　source = input()
　　　　if '123' == source:
　　　　　　break
　　　　elif '' == source:
　　　　　　continue
　　　　sign = Baidu.sign(source)
　　　　shuru = Baidu.shuru(source)
　　　　response = Baidu.fanyi(shuru[0], shuru[1], source, sign)
　　　　print(json.loads(response.text)['trans_result']['data'][0]['dst'])