G.TR.API

Romanian: https://neculaifantanaru.com/example-google-translate-api-key-python-code-beautifulsoup.html
English: https://neculaifantanaru.com/en/example-google-translate-api-key-python-code-beautifulsoup.html


from bs4 import BeautifulSoup
from bs4.formatter import HTMLFormatter
import requests
import json
import os
import six
from google.cloud import translate_v2 as translate

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

def translate_text(target, text):
    """Translates text into the target language.

    Target must be an ISO 639-1 language code.
    See https://g.co/cloud/translate/v2/translate-reference#supported_languages
    """

    os.environ["GOOGLE_APPLICATION_CREDENTIALS"] = "secret.json"

    translate_client = translate.Client()

    if isinstance(text, six.binary_type):
        text = text.decode("utf-8")

    # Text can also be a sequence of strings, in which case this method
    # will return a sequence of results for each text.
    result = translate_client.translate(text, target_language=target)

    return result["translatedText"]

files_from_folder = r"C:\test"
source_language = 'EN'

use_translate_folder = False

destination_language = 'ZH'

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:
                    newtext = translate_text(destination_language, node.contents[x])
                    node.contents[x].replaceWith(newtext)
                except:
                    pass
        elif node.contents[x] != None:
            recursively_translate(node.contents[x])

for file in os.listdir(directory):
    filename = os.fsdecode(file)
    print(filename)
    if filename == 'y_key_e479323ce281e459.html' or filename == 'TS_4fg4_tr78.html':
        continue
    if filename.endswith(extension_file):
        with open(os.path.join(files_from_folder, filename), encoding='utf-8') as html:
            soup = BeautifulSoup('<pre>' + html.read() + '</pre>', 'html.parser')
            for title in soup.findAll('title'):
                recursively_translate(title)

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

            for h1 in soup.findAll('h1', {'itemprop':'name'}, class_='den_articol'):
                begin_comment = str(soup).index('<!-- ARTICOL START -->')
                end_comment = str(soup).index('<!-- ARTICOL FINAL -->')
                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('<!-- ARTICOL START -->')
                end_comment = str(soup).index('<!-- ARTICOL FINAL -->')
                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('<!-- ARTICOL START -->')
                end_comment = str(soup).index('<!-- ARTICOL FINAL -->')
                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('<!-- ARTICOL START -->')
                end_comment = str(soup).index('<!-- ARTICOL FINAL -->')
                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('<!-- ARTICOL START -->')
                end_comment = str(soup).index('<!-- ARTICOL FINAL -->')
                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('<!-- ARTICOL START -->')
                end_comment = str(soup).index('<!-- ARTICOL FINAL -->')
                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('<!-- ARTICOL START -->')
                end_comment = str(soup).index('<!-- ARTICOL FINAL -->')
                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('<!-- ARTICOL START -->')
                end_comment = str(soup).index('<!-- ARTICOL FINAL -->')
                if begin_comment < str(soup).index(str(h5)) < end_comment:
                    recursively_translate(h5)

        print(f'{filename} translated')
        soup = soup.encode(formatter=UnsortedAttributes()).decode('utf-8')
        new_filename = f'{filename.split(".")[0]}_{destination_language}.html'
        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])