Ohatra ny python Google handika ny rakitra html lahatsoratra

py -m pip install beautifulsoup4

HTML novokarina tamin'ny fampiasana hilite.me

#!/usr/bin/env python
# -*- encoding: utf-8 -*-
'''
@File    :  google_trans.py
@Time    :  2020/5/15 9:29
@Author  :  hxluo
@Version :  1.0
@Contact :  465801795@qq.com
@Desc    :  google translate

'''
# import lib
import requests
import json
from bs4 import BeautifulSoup
import execjs
from urllib import parse
import re
import os

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)
class Translate_as_google(object):
    def __init__(self, to_language, this_language='auto', read=False):
        '''
            to_language:???????
            this_language:??????,???auto??
            read:???????text?????
        '''
        self.this_language = this_language
        self.to_language = to_language
        self.read = read

    def open_url(self, url):
        '''??'''
        headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:23.0) Gecko/20100101 Firefox/23.0'}
        req = requests.get(url=url, headers=headers , timeout=8)

        return req

    def buildUrl(self):
        '''????url
            sl:?????? tl:??????? q??????'''
        baseUrl = 'http://translate.google.cn/translate_a/single'
        baseUrl += '?client=webapp&'
        baseUrl += 'sl=%s&' % self.this_language
        baseUrl += 'tl=%s&' % self.to_language
        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 += 'clearbtn=1&'
        baseUrl += 'otf=1&'
        baseUrl += 'pc=1&'
        baseUrl += 'srcrom=0&'
        baseUrl += 'ssel=0&'
        baseUrl += 'tsel=0&'
        baseUrl += 'kc=2&'
        baseUrl += 'tk=' + str(self.tk) + '&'
        baseUrl += 'q=' + parse.quote(self.text)
        return baseUrl

    def read_go(self, args):
        '''????
        upload:??????????
        return_language:???????
        '''
        upload, return_language = args[0], args[1]
        read_translate_url = 'http://translate.google.cn/translate_tts?ie=UTF-8&q=%s&tl=%s&total=1&idx=0&textlen=3&tk=%s&client=webapp&prev=input' % (
            self.text, return_language, self.tk)
        data = self.open_url(read_translate_url) #?????????
        with open(upload, 'wb') as f:
            f.write(data.content)

    def translate(self,text):
        '''????'''
        self.text = text
        js = Py4Js()
        self.tk = js.getTk(self.text)

        if len(self.text) > 4891:
            raise ("The length of the translation exceeds the limit!!!")
        url = self.buildUrl()
        # print(url)
        _result = self.open_url(url)
        data = _result.content.decode('utf-8')

        tmp = json.loads(data)
        jsonArray = tmp[0]
        result = None
        for jsonItem in jsonArray:
            if jsonItem[0]:
                if result:
                    result = result + " " + jsonItem[0]
                else:
                    result = jsonItem[0]
        return result

if __name__ == '__main__':

    source = 'ro' # put the language from the text file
    target = 'en' # put the language in which you want to translate
    directory = r'c:\\Folder1'
    translate_directory = directory + r'\\translated'
    for filename in os.listdir(directory):
        if filename.endswith(".txt"): #or filename.endswith(".png"):
            with open(os.path.join(directory, filename), encoding='utf-8') as f:
                file_text = f.read()
                ts = Translate_as_google(target, source)
                translated_text = ts.translate(file_text)
                print(translated_text)
                path_to_file = translate_directory + filename.split('.')[0] + '_' + target + r'.' + filename.split('.')[1]
                with open(path_to_file, 'w+', encoding='utf-8') as f:
                    f.write(translated_text)
        else:
            continue