Translate Last

import os
import re
import textwrap
import html

#-------------------------------------------------------------------------------
# aici pui numlele librarii folosita pentru traducere: ai optiunile google_trans_new sau googletrans
librarie_folosita = "googletrans"
# calea catre folder-ul cu documente de tradus
fisiere_din_folder = r"c:\test"
source_language = 'en'
# in ce limba vreau sa traduc
# {'af': 'afrikaans', 'sq': 'albanian', 'am': 'amharic', 'ar': 'arabic', 'hy': 'armenian', 'az': 'azerbaijani', 'eu': 'basque', 'be': 'belarusian', 'bn': 'bengali', 'bs': 'bosnian', 'bg': 'bulgarian', 'ca': 'catalan', 'ceb': 'cebuano', 'ny': 'chichewa', 'zh-cn': 'chinese (simplified)', 'zh-tw': 'chinese (traditional)', 'co': 'corsican', 'hr': 'croatian', 'cs': 'czech', 'da': 'danish', 'nl': 'dutch', 'en': 'english', 'eo': 'esperanto', 'et': 'estonian', 'tl': 'filipino', 'fi': 'finnish', 'fr': 'french', 'fy': 'frisian', 'gl': 'galician', 'ka': 'georgian', 'de': 'german', 'el': 'greek', 'gu': 'gujarati', 'ht': 'haitian creole', 'ha': 'hausa', 'haw': 'hawaiian', 'iw': 'hebrew', 'hi': 'hindi', 'hmn': 'hmong', 'hu': 'hungarian', 'is': 'icelandic', 'ig': 'igbo', 'id': 'indonesian', 'ga': 'irish', 'it': 'italian', 'ja': 'japanese', 'jw': 'javanese', 'kn': 'kannada', 'kk': 'kazakh', 'km': 'khmer', 'ko': 'korean', 'ku': 'kurdish (kurmanji)', 'ky': 'kyrgyz', 'lo': 'lao', 'la': 'latin', 'lv': 'latvian', 'lt': 'lithuanian', 'lb': 'luxembourgish', 'mk': 'macedonian', 'mg': 'malagasy', 'ms': 'malay', 'ml': 'malayalam', 'mt': 'maltese', 'mi': 'maori', 'mr': 'marathi', 'mn': 'mongolian', 'my': 'myanmar (burmese)', 'ne': 'nepali', 'no': 'norwegian', 'ps': 'pashto', 'fa': 'persian', 'pl': 'polish', 'pt': 'portuguese', 'pa': 'punjabi', 'ro': 'romanian', 'ru': 'russian', 'sm': 'samoan', 'gd': 'scots gaelic', 'sr': 'serbian', 'st': 'sesotho', 'sn': 'shona', 'sd': 'sindhi', 'si': 'sinhala', 'sk': 'slovak', 'sl': 'slovenian', 'so': 'somali', 'es': 'spanish', 'su': 'sundanese', 'sw': 'swahili', 'sv': 'swedish', 'tg': 'tajik', 'ta': 'tamil', 'te': 'telugu', 'th': 'thai', 'tr': 'turkish', 'uk': 'ukrainian', 'ur': 'urdu', 'uz': 'uzbek', 'vi': 'vietnamese', 'cy': 'welsh', 'xh': 'xhosa', 'yi': 'yiddish', 'yo': 'yoruba', 'zu': 'zulu', 'fil': 'Filipino', 'he': 'Hebrew'}
destination_language = 'ru'
delimitatori_text_exterior_articol = [['<title','Neculai Fantanaru (en)</title>']]
delimitatori_text_interior_articol = [['<h1 class="den_articol" itemprop="name', '</h1>'], ['<p class="text_obisnuit', '</p>'], ['<span class="text', '</span>'], ['<li class="text_obisnuit', '</li>'], ['<h3 class="text_obisnuit2', '</h3>'], ['<h4 class="text_obisnuit2', '</h4>'], ['<h2', '</h2>'], ['<h1 class="den_webinar', '</h1>'],['<p class="alertHd','</p>'],['<span class="den_articol','</span>']]

extensie_fisier = ".html"
#-------------------------------------------------------------------------------

if (librarie_folosita == "google_trans_new"):
    from google_trans_new import google_translator
    translator = google_translator()
elif (librarie_folosita == "googletrans"):
    from googletrans import Translator
    translator = Translator()
elif (librarie_folosita == "translators"):
    import translators as ts

lista_cale_fisiere = []

VAR, REPL = re.compile(r'(<.*?>)'), re.compile(r'_____(\d+)_____')
varlist = []
def replace(matchobj):
  varlist.append(matchobj.group())
  return "_____%d_____" %(len(varlist)-1)
def restore(matchobj):
    try:
        return varlist[int(matchobj.group(1))]
    except:
        a=9

def traducere_text(text):
    result = ""
    for txt in (textwrap.wrap(text, 4500, break_long_words=False)):     # impart in maxim 4500 de caractere uitandu-ma dupa spatii
        txt = html.unescape(txt)      # Convert all named and numeric character references (e.g. &gt;, &#62;, &#x3e;) in the string s to the corresponding Unicode characters.
        if (librarie_folosita == "google_trans_new"):
            while (re.search(r'(<.*?>)', txt)) :
                txt = VAR.sub(replace, txt)
            translation = translator.translate(txt, lang_tgt=destination_language)
            while (re.search(r'_____[0-9 ]+ _____', translation)):
                rep = re.search(r'_____[0-9 ]+ _____', translation).group(0)
                translation = translation.replace(rep, rep.replace(r' ', r''))
            while (re.search(r'_____ [0-9 ]+_____', translation)):
                rep = re.search(r'_____ [0-9 ]+_____', translation).group(0)
                translation = translation.replace(rep, rep.replace(r' ', r''))
            translation = REPL.sub(restore, translation)
            result = result + translation
        elif (librarie_folosita == "googletrans"):
            while (re.search(r'(<.*?>)', txt)) :
                txt = VAR.sub(replace, txt)
            translation = translator.translate(txt, dest=destination_language).text
            while (re.search(r'_____[0-9 ]+ _____', translation)):
                rep = re.search(r'_____[0-9 ]+ _____', translation).group(0)
                translation = translation.replace(rep, rep.replace(r' ', r''))
            while (re.search(r'_____ [0-9 ]+_____', translation)):
                rep = re.search(r'_____ [0-9 ]+_____', translation).group(0)
                translation = translation.replace(rep, rep.replace(r' ', r''))
            translation = REPL.sub(restore, translation)
            result = result + translation
        elif (librarie_folosita == "translators"):
            while (re.search(r'(<.*?>)', txt)) :
                txt = VAR.sub(replace, txt)
            translation = translator.translate(txt, dest=destination_language).text
            while (re.search(r'_____[0-9 ]+ _____', translation)):
                rep = re.search(r'_____[0-9 ]+ _____', translation).group(0)
                translation = translation.replace(rep, rep.replace(r' ', r''))
            while (re.search(r'_____ [0-9 ]+_____', translation)):
                rep = re.search(r'_____ [0-9 ]+_____', translation).group(0)
                translation = translation.replace(rep, rep.replace(r' ', r''))
            translation = REPL.sub(restore, translation)
            result = result + translation
    return result

def selectare_traducere_continut(cont, delimitatori):
    for delimitator in delimitatori:
        start_delim = delimitator[0]                                            # '<title'
        stop_delim  = delimitator[1]                                            # '</title>'
        start_position = 0
        stop_position = len(cont)-1
        while cont[start_position:stop_position].find(start_delim)>0:
            temp_st = cont[start_position:stop_position].find(start_delim) + len(start_delim) + start_position
            temp = temp_st + cont[temp_st:stop_position].find('>')
            if (cont[temp-1] == '/'):
                start_position = temp
            else:
                start_position = temp+1
                st = cont[start_position:stop_position].find(stop_delim) + start_position
                extracted_text = cont[start_position:st]
                translated_text = traducere_text(extracted_text)
                cont = cont[:start_position] + translated_text + cont[st:]
                start_position = start_position + len(translated_text)
    return cont

def selectare_text():
    for file in os.listdir(fisiere_din_folder):
        if file.endswith(extensie_fisier):
            lista_cale_fisiere.append(os.path.join(fisiere_din_folder, file))

    for fisier in lista_cale_fisiere:

        f = open(fisier, 'r')

        if f.mode == 'r':
            contents = f.read()
            #contents = html.unescape(contents)      # Convert all named and numeric character references (e.g. &gt;, &#62;, &#x3e;) in the string s to the corresponding Unicode characters.
            print ("Acum lucrez la fisierul :", fisier)

            continut = []
            if (contents.find('<meta name="description" content="')>0):       # am gasit '<!-- ARTICOL START -->' in pagina
                pozitia1 = contents.find('<meta name="description" content="') + len('<meta name="description" content="')
                pozitia2 = pozitia1 + contents[pozitia1+1:].find(">") - 1
                selectie = contents[pozitia1:pozitia2]
                trad = traducere_text(selectie)
                contents = contents[:pozitia1] + trad + contents[pozitia2:]
            if (contents.find('<!-- ARTICOL START -->')>0):       # am gasit '<!-- ARTICOL START -->' in pagina
                poz1 = contents.find('<!-- ARTICOL START -->') + len('<!-- ARTICOL START -->')
                poz2 = contents.find('<!-- ARTICOL FINAL -->') + len('<!-- ARTICOL FINAL -->')
                inceput = contents[:poz1]
                articol = contents[poz1:poz2]
                final = contents[poz2:]
                continut.append(inceput)
                continut.append(articol)
                continut.append(final)
            else:
                continut.append(contents)
            continut_tradus = ''
            if (len(continut) == 3):
                continut_tradus = continut_tradus + selectare_traducere_continut(continut[0], delimitatori_text_exterior_articol) # inceput
                continut_tradus = continut_tradus + selectare_traducere_continut(continut[1], delimitatori_text_interior_articol) # articol
                continut_tradus = continut_tradus + selectare_traducere_continut(continut[2], delimitatori_text_exterior_articol) # exterior
            elif (len(continut) == 1):
                continut_tradus = continut_tradus + selectare_traducere_continut(continut[0], delimitatori_text_exterior_articol)
            else:
                print ("S-a produs o eroare cand am vrut sa citesc articolul sau exteriorul lui !")
        print("Am citit un fisier si incep traducerea!\n")

        with open(fisier[:len(fisier)-len(extensie_fisier)]+"_"+destination_language+extensie_fisier, 'w', encoding="utf-8") as f:
            f.write(continut_tradus)
    print("Am terminat traducerea !")

selectare_text()