Keywords+Regex

Explanation here:
Romanian: https://neculaifantanaru.com/regex-python-translate-beautifulsoup-googletrans-html-tags-contains-keywords.html
English: https://neculaifantanaru.com/en/regex-python-translate-beautifulsoup-googletrans-html-tags-contains-keywords.html



from bs4 import BeautifulSoup
from bs4.formatter import HTMLFormatter
from googletrans import Translator
import requests
import re

translator = Translator()

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

files_from_folder = r"c:\Users\Castel\Videos\Captures"

use_translate_folder = False

destination_language = 'nl'

extension_file = ".html"
pattern1 = r'<p class="text_obisnuit">.*(( the | you | which | have | had | then | that | must | make | from | else | does | get | will | make | made | yours | can | your | doesn | their | could | from | at | of | my | an | by | with | are | his | him | she | he | it | may | seem | and | for | else | while | which | be | these | let | ask | has | as | won | keep | but | everything | without | thinking | about | just | to | doesn | if | each | try | I’m | them | one | more | much | on | all | even | over | seems ).*){3,}.*</p>'
pattern2 = r'<p class="text_obisnuit2">.*(( the | you | which | have | had | then | that | must | make | from | else | does | get | will | make | made | yours | can | your | doesn | their | could | from | at | of | my | an | by | with | are | his | him | she | he | it | may | seem | and | for | else | while | which | be | these | let | ask | has | as | won | keep | but | everything | without | thinking | about | just | to | doesn | if | each | try | I’m | them | one | more | much | on | all | even | over | seems ).*){3,}.*</p>'
pattern3 = r'<title>.*(( the | you | which | have | had | then | that | must | make | from | else | does | get | will | make | made | yours | can | your | doesn | their | could | from | at | of | my | an | by | with | are | his | him | she | he | it | may | seem | and | for | else | while | which | be | these | let | ask | has | as | won | keep | but | everything | without | thinking | about | just | to | doesn | if | each | try | I’m | them | one | more | much | on | all | even | over | seems ).*){3,}.*</title>'
pattern4 = r'<meta name="description" content=.*(( the | you | which | have | had | then | that | must | make | from | else | does | get | will | make | made | yours | can | your | doesn | their | could | from | at | of | my | an | by | with | are | his | him | she | he | it | may | seem | and | for | else | while | which | be | these | let | ask | has | as | won | keep | but | everything | without | thinking | about | just | to | doesn | if | each | try | I’m | them | one | more | much | on | all | even | over | seems ).*){3,}.*>'

patterns = [pattern1, pattern2, pattern3, pattern4]
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:
                    translation = translator.translate(node.contents[x], dest=destination_language).text
                    node.contents[x].replaceWith(translation)
                except Exception as e:
                    print(e)
        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:
            page = html.read()
            updated = False
            for pattern in patterns:
                for x in re.finditer(pattern, page):
                    updated = True
                    new = x.group(0)
                    soup = BeautifulSoup(new, 'html.parser')
                    if pattern != pattern4:
                        recursively_translate(soup)
                    else:
                        meta = soup.find('meta')
                        meta['content'] = translator.translate(meta['content'], dest=destination_language).text
                    soup = soup.encode(formatter=UnsortedAttributes()).decode('utf-8')
                    page = page.replace(new, soup)
        if updated:
            print(f'{filename} translated')
            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(page)
                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(page)
            else:
                with open(os.path.join(files_from_folder, new_filename), 'w', encoding='utf-8') as html:
                    html.write(page)