-
-
Save Happy-Ferret/b96b72ad04c4ee77ac684584add0e0fb to your computer and use it in GitHub Desktop.
Script to translate JSON strings with googletrans library in python. Useful for web language localization
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import json | |
import googletrans | |
import os | |
from googletrans import Translator | |
def translateString(data, destLangCode): | |
global translator | |
if isinstance(data, dict): | |
return {k: translateString(v, destLangCode) for k, v in data.items()} | |
else: | |
return translator.translate(data, src='en', dest=destLangCode).text | |
# Main Code | |
all_languages = {'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', 'he': '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', 'or': 'odia', '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', 'ug': 'uyghur', 'uz': 'uzbek', 'vi': 'vietnamese', 'cy': 'welsh', 'xh': 'xhosa', 'yi': 'yiddish', 'yo': 'yoruba', 'zu': 'zulu'} | |
dirname = os.path.dirname(__file__) | |
src_filename = os.path.join(dirname, 'english.json') | |
destLangCodeList = [ | |
'hi', | |
'kn', | |
'or', | |
'bn', | |
'gu', | |
'pa', | |
'ml', | |
'ta', | |
'te' | |
] | |
translator = Translator() | |
for destLangCode in destLangCodeList: | |
print('Starting translation for {:} ... '.format(all_languages[destLangCode]), end="") | |
with open(src_filename, 'r', encoding="utf-8") as fin: | |
data = json.load(fin) | |
translated_json = translateString(data, destLangCode) | |
dest_filename = os.path.join(dirname, all_languages[destLangCode]+'.json') | |
with open(dest_filename, 'w', encoding="utf-8") as fout: | |
json_dumps_str = json.dumps(translated_json, indent=4, ensure_ascii=False) | |
fout.write(json_dumps_str) | |
print('done') |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment