google翻译破解大综合

最新推荐文章于 2024-09-11 16:37:07 发布

xiexiecn

最新推荐文章于 2024-09-11 16:37:07 发布

阅读量2k

点赞数

分类专栏： python 爬虫文章标签： google翻译 NLP

本文链接：https://blog.csdn.net/xiexiecn/article/details/94382959

版权

python 同时被 2 个专栏收录

6 篇文章 0 订阅

订阅专栏

爬虫

1 篇文章 0 订阅

订阅专栏

近期需要大量调用谷歌翻译，网上搜集了各种办法，最后还是经常被限制，朋友帮忙申请的300美金的免费额度也用完了，通过本地代理（没钱开那么多真的代理，网上找来的免费资源也不靠谱）绕一下也稍微起点作用，有点江郎才尽，最后发现网上的buildUrl代码有问题, s1, t1, h1换成sl, tl, hl总算可以一直调用了（天下文章一大抄，嘿嘿）。所有资源来自网上，懒得一一回溯了，总归都是感谢。当然，翻译调用几百次之后，最好还是随机delay几分钟，以免被封（不知道会不会，不测试了）。

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

import os
import sys
import time
import random
import requests
import json
#from googletrans import Translator
import googletrans
from translate import Translator
from bs4 import BeautifulSoup
import execjs #必须，需要先用pip 安装，用来执行js脚本
import pickle
from utils import safe_pickle_dump, strip_version, isvalidid, Config
from nltk import data
from nltk.tokenize import sent_tokenize
from google.cloud import translate
from googletrans.gtoken import TokenAcquirer

data.path.append(r"/root/nltk_data")

import urllib.request
from urllib.parse import quote
import http.cookiejar

# crackedjs, crackedpython, google
#translate_method = "google"
#translate_method = "crackedpython"
translate_method = "crackedjs"
#translate_method = "translate-shell"
#translate_method = "mmtranslator"

proxy_en = True
#proxy_en = False

# cracked google translate api
translator = googletrans.Translator()
mmtranslator= Translator(to_lang="zh")
# google translate api
translate_client = None

def get_google_cookie():
  headers={
      'authority':'translate.google.cn',
      'method':'GET',
      'path':'/',
      'scheme':'https',
      'accept':'*/*',
      'accept-encoding':'gzip, deflate, br',
      'accept-language':'zh-CN,zh;q=0.9',
      'cache-control': 'no-cache',
      'pragma': 'no-cache',
      'upgrade-insecure-requests': '1',
      'user-agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.169 Safari/537.36',
      'x-client-data': '替换成自己chrome浏览器里的捕捉的内容，可能并不重要'
  }

  cookie_file = './logs/cookie.txt'
  cookie_set = ''

  try:
    cookie = http.cookiejar.MozillaCookieJar(cookie_file)
    handler = urllib.request.HTTPCookieProcessor(cookie)
    opener = urllib.request.build_opener(handler)
    request = urllib.request.Request('https://translate.google.cn', headers=headers)
    response = opener.open(request)
    cookie_set = response.info()['Set-Cookie']
    cookie.save(ignore_discard=True, ignore_expires=True)
  except Exception as e:
    cookie_set=''
    print("错误信息:")
    print(e)
  finally:
    return cookie_set

class Py4Js():
  def __init__(self):
    self.ctx = execjs.compile("""
    function TL(a) {
    var k = "";
    var b = 406644;
    var b1 = 3293161072;
    var jd = ".";
    var $b = "+-a^+6";
    var Zb = "+-3^+b+-f";
    for (var e = [], f = 0, g = 0; g < a.length; g++) {
        var m = a.charCodeAt(g);
        128 > m ? e[f++] = m : (2048 > m ? e[f++] = m >> 6 | 192 : (55296 == (m & 64512) && g + 1 < a.length && 56320 == (a.charCodeAt(g + 1) & 64512) ? (m = 65536 + ((m & 1023) << 10) + (a.charCodeAt(++g) & 1023),
        e[f++] = m >> 18 | 240,
        e[f++] = m >> 12 & 63 | 128) : e[f++] = m >> 12 | 224,
        e[f++] = m >> 6 & 63 | 128),
        e[f++] = m & 63 | 128)
    }
    a = b;
    for (f = 0; f < e.length; f++) a += e[f],
    a = RL(a, $b);
    a = RL(a, Zb);
    a ^= b1 || 0;
    0 > a && (a = (a & 2147483647) + 2147483648);
    a %= 1E6;
    return a.toString() + jd + (a ^ b)
  };
  function RL(a, b) {
    var t = "a";
    var Yb = "+";
    for (var c = 0; c < b.length - 2; c += 3) {
        var d = b.charAt(c + 2),
        d = d >= t ? d.charCodeAt(0) - 87 : Number(d),
        d = b.charAt(c + 1) == Yb ? a >>> d: a << d;
        a = b.charAt(c) == Yb ? a + d & 4294967295 : a ^ d
    }
    return a
  }
 """)

  def getTk(self, text):
      return self.ctx.call("TL",text)

def buildUrl(text,tk):
  baseUrl='https://translate.google.cn/translate_a/single'
  baseUrl+='?client=webapp&'
  baseUrl+='sl=auto&'
  baseUrl+='tl=zh-CN&'
  baseUrl+='hl=zh-CN&'
  baseUrl+='dt=at&'
  baseUrl+='dt=bd&'
  baseUrl+='dt=ex&'
  baseUrl+='dt=ld&'
  baseUrl+='dt=md&'
  baseUrl+='dt=qca&'
  baseUrl+='dt=rw&'
  baseUrl+='dt=rm&'
  baseUrl+='dt=ss&'
  baseUrl+='dt=t&'
  baseUrl+='ie=UTF-8&'
  baseUrl+='oe=UTF-8&'
  baseUrl+='otf=1&'
  baseUrl+='pc=1&'
  baseUrl+='ssel=0&'
  baseUrl+='tsel=0&'
  baseUrl+='kc=2&'
  baseUrl+='tk='+str(tk)+'&'
  baseUrl+='q='+text
  return baseUrl

def translate_text(method, text, cookie_set):
  global translate_client

  if method == "translate-shell":
    with open('./logs/text.txt', "w") as f:
      f.write(text)
      f.close()

      cmd = 'trans -e google -brief :zh-CN file://./logs/text.txt'
      cmdobj = os.popen(cmd, 'r', 1)
      text_lines = cmdobj.readlines()
      cmdobj.close()
      text_cn = ''.join(text_lines)
      return text_cn
  elif method == "crackedpython":
    return translator.translate(line, dest='zh-CN').text
  elif method == "mmtranslator":
    text_cn = mmtranslator.translate(line)
    return '' if text_cn[0:16] == "MYMEMORY WARNING" else text_cn
  elif method == "google":
    if translate_client is None:
        translate_client = translate.Client()

    # Translates some text into Chinese
    translation = translate_client.translate(
        text,
        target_language='zh-CN')
    return translation['translatedText']

  headers={
    'authority': 'translate.google.cn',
    'method': 'GET',
    'path': '',
    'scheme': 'https',
    'accept': '*/*',
    'accept-encoding': 'gzip, deflate, br',
    'accept-language': 'zh-CN,zh;q=0.9',
    'cache-control': 'no-cache',
    'cookie': cookie_set,
    'pragma': 'no-cache',
    'upgrade-insecure-requests': '1',
    'user-agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.169 Safari/537.36',
    'x-client-data': '替换成自己chrome浏览器里的捕捉的内容，可能并不重要'
  }

  proxy_dict = {
    "http": "http://127.0.0.1:8080",
    "https": "http://127.0.0.1:8080"
  }

  url = buildUrl(quote(text), acquirer.do(text))
  #url = buildUrl(quote(text), js.getTk(text))
  headers['path'] = url[27:]
  res = ''

  try:
      r = requests.get(url, headers=headers, proxies=(proxy_dict if proxy_en else None))
      result=json.loads(r.text)
      if result[7]!=None:
      # 如果我们文本输错，提示你是不是要找xxx的话，那么重新把xxx正确的翻译之后返回
        try:
              correctText=result[7][0].replace('<b><i>',' ').replace('</i></b>','')
              print(correctText)
              correctUrl=buildUrl(correctText,js.getTk(correctText))
              headers['path'] = correctUrl[27:]
              correctR = requests.get(correctUrl, headers=headers, proxies=(proxy_dict if proxy_en else None))

              newResult=json.loads(correctR.text)
              res=newResult[0][0][0]
        except Exception as e:
              print(e)
              res=result[0][0][0]
      else:
          res=result[0][0][0]
  except Exception as e:
      res=''
      print(url)
      print("翻译"+text+"失败")
      print("错误信息:")
      print(e)
  finally:
      return res

if __name__ == '__main__':
  total = 0

  if len(sys.argv) > 1:
    total = int(sys.argv[1])

  if len(sys.argv) > 2:
    translate_method = sys.argv[2]

  cookie_set = get_google_cookie()

  if cookie_set == '':
    if os.path.exists('./logs/cookie_set.txt'):
      with open('./logs/cookie_set.txt', 'r') as f:
        cookie_set = f.read()
    else:
      print("Get google cookie failed!")

      if translate_method == "crackedjs":
        print("exit, no cookie for cracked js")
        sys.exit(0)
  else:
    with open('./logs/cookie_set.txt', 'w') as f:
      f.write(cookie_set)

  js=Py4Js()

  acquirer = TokenAcquirer()

  print('loading the paper database', Config.db_path)
  db = pickle.load(open(Config.db_path, 'rb'))

  translate_text(translate_method, 'The quick brown fox jumps over the lazy dog.', cookie_set)