Python Google Translate BeautifulSoup Library + Tallenna otsikkotunniste HTML Linkiksi

py -m pip install "googletrans"
py -m pip install googletrans==4.0.0rc1
py -m pip install beautifulsoup4

Myös Python-koodi kääntää myös seuraavien tunnisteiden (tekstin) sisällön, mutta vain, jos nämä tunnisteet kehystäänja HTML kommentit. Tietenkin sinun on korvattava nämä tunnisteet omilla tunnisteillesi.

 class="den_articol" itemprop="name">Your Text
 class="text_obisnuit">Your Text

 class="text_obisnuit2">Your Text

 class="text_obisnuit2">Your Text
 class="text_obisnuit">Your Text
 class="text_obisnuit">Your Text
 class="linkMare" href="https://neculaifantanaru.com/fi/">Your Text
 class="text_obisnuit2>Your Text
text_obisnuit2>Your Text
 class="text_obisnuit2>Your Text


              

from bs4 import BeautifulSoup
from bs4.formatter import HTMLFormatter
import requests
import re
import execjs
from urllib import parse
import json

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:The language to be translated into
            this_language:The text to be converted, the default is auto
            read:Generate a text reading file at the specified location
        '''
        self.this_language = this_language
        self.to_language = to_language
        self.read = read

    def open_url(self, url):
        '''请求'''
        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):
        '''封装请求url
            sl:The text to be converted tl:The result type of the conversion qThe text to be entered'''
        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):
        '''Speaking interception
        upload:Download to path and file name
        return_language:Language type returned
        '''
        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) #Return all data requested
        with open(upload, 'wb') as f:
            f.write(data.content)

    def translate(self,text):
        '''Translation interception'''
        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

class UnsortedAttributes(HTMLFormatter):
    def attributes(self, tag):
        for k, v in tag.attrs.items():
            yield k, v

files_from_folder = r"c:\Folder1\translated\test"

use_translate_folder = True

destination_language = 'fr'

ts = Translate_as_google(destination_language)

extension_file = ".html"

import os

directory = os.fsencode(files_from_folder)

def recursively_translate(node):
    for x in range(len(node.contents)):
        if isinstance(node.contents[x], str):
            if node.contents[x].strip() != '':
                try:
                    node.contents[x].replaceWith(ts.translate(node.contents[x]))
                except Exception as e:
                    print(e)
        elif node.contents[x] != None:
            recursively_translate(node.contents[x])

amount = 1
for file in os.listdir(directory):
    filename = os.fsdecode(file)
    print(filename)
    if filename == 'y_key_e479323ce281e459.html' or filename == 'directory.html':
        continue
    if filename.endswith(extension_file):
        with open(os.path.join(files_from_folder, filename), encoding='utf-8') as html:
            soup = BeautifulSoup('
' + html.read() + '
', 'html.parser')
            for title in soup.findAll('title'):
                print("Continut titlu: ", title.get_text())
                recursively_translate(title)

            for meta in soup.findAll('meta', {'name':'description'}):
                try:
                    meta['content'] = ts.translate(meta['content'])
                except:
                    pass

            for h1 in soup.findAll('h1', {'itemprop':'name'}, class_='den_articol'):
                begin_comment = str(soup).index('')
                end_comment = str(soup).index('')
                if begin_comment < str(soup).index(str(h1)) < end_comment:
                    recursively_translate(h1)

            for p in soup.findAll('p', class_='text_obisnuit'):
                begin_comment = str(soup).index('')
                end_comment = str(soup).index('')
                if begin_comment < str(soup).index(str(p)) < end_comment:
                    recursively_translate(p)

            for p in soup.findAll('p', class_='text_obisnuit2'):
                begin_comment = str(soup).index('')
                end_comment = str(soup).index('')
                if begin_comment < str(soup).index(str(p)) < end_comment:
                    recursively_translate(p)

            for span in soup.findAll('span', class_='text_obisnuit2'):
                begin_comment = str(soup).index('')
                end_comment = str(soup).index('')
                if begin_comment < str(soup).index(str(span)) < end_comment:
                    recursively_translate(span)

            for li in soup.findAll('li', class_='text_obisnuit'):
                begin_comment = str(soup).index('')
                end_comment = str(soup).index('')
                if begin_comment < str(soup).index(str(li)) < end_comment:
                    recursively_translate(li)

            for a in soup.findAll('a', class_='linkMare'):
                begin_comment = str(soup).index('')
                end_comment = str(soup).index('')
                if begin_comment < str(soup).index(str(a)) < end_comment:
                    recursively_translate(a)

            for h4 in soup.findAll('h4', class_='text_obisnuit2'):
                begin_comment = str(soup).index('')
                end_comment = str(soup).index('')
                if begin_comment < str(soup).index(str(h4)) < end_comment:
                    recursively_translate(h4)

            for h5 in soup.findAll('h5', class_='text_obisnuit2'):
                begin_comment = str(soup).index('')
                end_comment = str(soup).index('')
                if begin_comment < str(soup).index(str(h5)) < end_comment:
                    recursively_translate(h5)

            for h1 in soup.findAll('h1', {'itemprop':'name'}, class_='den_webinar'):
                begin_comment = str(soup).index('')
                end_comment = str(soup).index('')
                if begin_comment < str(soup).index(str(h1)) < end_comment:
                    recursively_translate(h1)

        # SAve Title tag as html link

        print(f'{filename} translated ({amount})')
        amount += 1
        soup = soup.encode(formatter=UnsortedAttributes()).decode('utf-8')
        new_filename = title.get_text() 
        new_filename = new_filename.lower()
        words = re.findall(r'\w+', new_filename)
		#words = re.findall(r'\b\w+\b(?=[\w\s]+\|)', new_filename)  #This will save words until | (linebreak) if you have one
        new_filename = '-'.join(words)
        new_filename = new_filename + '.html'
        print(new_filename)

        #print("Encode: ", new_filename.encode('ascii', 'ignore'))
        if use_translate_folder:
            try:
                with open(os.path.join(files_from_folder+r'\translated', new_filename), 'w', encoding='utf-8') as new_html:
                    new_html.write(soup[5:-6])
            except:
                os.mkdir(files_from_folder+r'\translated')
                with open(os.path.join(files_from_folder+r'\translated', new_filename), 'w', encoding='utf-8') as new_html:
                    new_html.write(soup[5:-6])
        else:
            with open(os.path.join(files_from_folder, new_filename), 'w', encoding='utf-8') as html:
                html.write(soup[5:-6])