Last active
March 28, 2019 15:00
-
-
Save MawCeron/2ef2d4bee8006e045a94b52cdcdd0b8a to your computer and use it in GitHub Desktop.
Express subtitle translation using Google Translator
This file contains hidden or 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
| #!/usr/bin/env python | |
| # -*- coding: utf-8 -*- | |
| # | |
| # Express subtitle translation using Google Translator | |
| # | |
| # Notes: | |
| # - python fansub.py [file] [from language] [to languaje] // i.e.(python fansub.py mySubs.ass en es) | |
| # - Only for ASS Subtitle files | |
| # - Just for fun | |
| # - Too slow | |
| # - Translation is very bad in most cases | |
| # | |
| # (c) 2019 Mauricio Cerón <maw.ceron@gmail.com> | |
| # | |
| import re, sys, os | |
| import urllib, urllib2, HTMLParser | |
| def translation(text, to_lang, from_lang): | |
| agent = {'User-Agent':"Mozilla/4.0 (compatible;MSIE 6.0;Windows NT 5.1;SV1;.NET CLR 1.1.4322;.NET CLR 2.0.50727;.NET CLR 3.0.04506.30)"} | |
| base_link = "http://translate.google.com/m?hl=%s&sl=%s&q=%s" | |
| to_trans = urllib.quote_plus(text) | |
| link = base_link % (to_lang,from_lang,to_trans) | |
| req = urllib2.Request(link, headers = agent) | |
| response = urllib2.urlopen(req).read() | |
| data = response.decode("utf-8") | |
| expr = r'class="t0">(.*?)>' | |
| re_result = re.findall(expr, data) | |
| if len(re_result) == 0: | |
| result = "" | |
| else: | |
| result = unescape(re_result[0]) | |
| return result.encode('utf-8') | |
| def unescape(text): | |
| if sys.version_info[0] < 3: | |
| parser = HTMLParser.HTMLParser() | |
| else: | |
| parser = html.parser.HTMLParser() | |
| return (parser.unescape(text)) | |
| def main(argv): | |
| if len(argv) != 3: | |
| print("[!] Error. There is not enough information, please enter the information as follows:\n") | |
| print("[*] python fansub.py [file] [from language] [to languaje]") | |
| else: | |
| original_subs = argv[0] # Here goes the path to the subtitles script | |
| original_lang = argv[1] | |
| translate_lang = argv[2] | |
| new_script = [] | |
| with open(original_subtitles) as fp: | |
| for line in fp: | |
| line = line.strip() | |
| if line.startswith('Dialogue:') or line.startswith('Comment:'): | |
| event_type, rest = line.split(": ", 1) | |
| buf = rest.split(',') | |
| dialogue = buf[9] | |
| text = buf[9].replace('\N','\n') | |
| text = re.sub(r'{.*}','',text) | |
| trans = translation(text,translate_lang,original_lang) | |
| buf[9] = trans | |
| rest = ','.join(buf) | |
| new_line = "%s: %s" %(event_type,rest) | |
| new_script.append(new_line) | |
| else | |
| new_script.append(line) | |
| name, ext = os.path.splitext(original_subs) | |
| translated_subs | |
| nfp = open(translated_subs, 'w') | |
| for line in new_script: | |
| nfp.write("%s\n" %line) | |
| fp.close() | |
| nfp.close() | |
| if __name__ == "__main__": | |
| main(sys.argv[1:]) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment