def getallsubs(url, allowed_languages, filename="", episode=""):
subtitle_pattern = ("<td class=\"a1\">\s+<a href=\"(?P<link>/subtitles/[^\"]+)\">\s+"
"<span class=\"[^\"]+ (?P<quality>\w+-icon)\">\s+(?P<language>[^\r\n\t]+)\s+</span>\s+"
"<span>\s+(?P<filename>[^\r\n\t]+)\s+</span>\s+"
"</a>\s+</td>\s+"
"<td class=\"[^\"]+\">\s+(?P<numfiles>[^\r\n\t]*)\s+</td>\s+"
"<td class=\"(?P<hiclass>[^\"]+)\">"
"(?:.*?)<td class=\"a6\">\s+<div>\s+(?P<comment>[^\"]+) \s*</div>")
codes = get_language_codes(allowed_languages)
if len(codes) < 1:
xbmc.executebuiltin((u'Notification(%s,%s)' % (__scriptname__, __language__(32004))).encode('utf-8'))
return
log(__name__, 'LanguageFilter='+','.join(codes))
content, response_url = geturl(url, 'LanguageFilter='+','.join(codes))
if content is None:
return
subtitles = []
h = HTMLParser.HTMLParser()
episode_regex = None
if episode != "":
episode_regex = re.compile(get_episode_pattern(episode), re.IGNORECASE)
log(__name__, "regex: %s" % get_episode_pattern(episode))
for matches in re.finditer(subtitle_pattern, content, re.IGNORECASE | re.DOTALL):
numfiles = 1
if matches.group('numfiles') != "":
numfiles = int(matches.group('numfiles'))
languagefound = matches.group('language')
language_info = subscene_languages[languagefound]
if language_info and language_info['3let'] in allowed_languages:
link = main_url + matches.group('link')
subtitle_name = string.strip(matches.group('filename'))
hearing_imp = (matches.group('hiclass') == "a41")
rating = '0'
if matches.group('quality') == "bad-icon":
continue
if matches.group('quality') == "positive-icon":
rating = '5'
comment = re.sub("[\r\n\t]+", " ", h.unescape(string.strip(matches.group('comment'))))
sync = False
if filename != "" and string.lower(filename) == string.lower(subtitle_name):
sync = True
if episode != "":
# log(__name__, "match: "+subtitle_name)
if episode_regex.search(subtitle_name):
subtitles.append({'rating': rating, 'filename': subtitle_name, 'sync': sync, 'link': link,
'lang': language_info, 'hearing_imp': hearing_imp, 'comment': comment})
elif numfiles > 2:
subtitle_name = subtitle_name + ' ' + (__language__(32001) % int(matches.group('numfiles')))
subtitles.append({'rating': rating, 'filename': subtitle_name, 'sync': sync, 'link': link,
'lang': language_info, 'hearing_imp': hearing_imp, 'comment': comment,
'episode': episode})
else:
subtitles.append({'rating': rating, 'filename': subtitle_name, 'sync': sync, 'link': link,
'lang': language_info, 'hearing_imp': hearing_imp, 'comment': comment})
subtitles.sort(key=lambda x: [not x['sync'], not x['lang']['name'] == PreferredSub])
for s in subtitles:
append_subtitle(s)
def getallsubs(url, allowed_languages, filename="", episode=""):
subtitle_pattern = ("<td class=\"a1\">\s+<a href=\"(?P<link>/subtitles/[^\"]+)\">\s+"
"<span class=\"[^\"]+ (?P<quality>\w+-icon)\">\s+(?P<language>[^\r\n\t]+)\s+</span>\s+"
"<span>\s+(?P<filename>[^\r\n\t]+)\s+</span>\s+"
"</a>\s+</td>\s+"
"<td class=\"[^\"]+\">\s+(?P<numfiles>[^\r\n\t]*)\s+</td>\s+"
"<td class=\"(?P<hiclass>[^\"]+)\">"
"(?:.*?)<td class=\"a6\">\s+<div>\s+(?P<comment>[^\"]+) \s*</div>")
codes = get_language_codes(allowed_languages)
if len(codes) < 1:
xbmc.executebuiltin((u'Notification(%s,%s)' % (__scriptname__, __language__(32004))).encode('utf-8'))
return
log(__name__, 'LanguageFilter='+','.join(codes))
content, response_url = geturl(url, 'LanguageFilter='+','.join(codes))
if content is None:
return
subtitles = []
h = HTMLParser.HTMLParser()
episode_regex = None
if episode != "":
episode_regex = re.compile(get_episode_pattern(episode), re.IGNORECASE)
log(__name__, "regex: %s" % get_episode_pattern(episode))
for matches in re.finditer(subtitle_pattern, content, re.IGNORECASE | re.DOTALL):
numfiles = 1
if matches.group('numfiles') != "":
numfiles = int(matches.group('numfiles'))
languagefound = matches.group('language')
language_info = subscene_languages[languagefound]
if language_info and language_info['3let'] in allowed_languages:
link = main_url + matches.group('link')
subtitle_name = string.strip(matches.group('filename'))
hearing_imp = (matches.group('hiclass') == "a41")
rating = '0'
if matches.group('quality') == "bad-icon":
continue
if matches.group('quality') == "positive-icon":
rating = '5'
comment = re.sub("[\r\n\t]+", " ", h.unescape(string.strip(matches.group('comment'))))
sync = False
if filename != "" and string.lower(filename) == string.lower(subtitle_name):
sync = True
if episode != "":
log(__name__, "match: "+subtitle_name)
if episode_regex.search(subtitle_name):
subtitles.append({'rating': rating, 'filename': subtitle_name, 'sync': sync, 'link': link,
'lang': language_info, 'hearing_imp': hearing_imp, 'comment': comment})
elif numfiles > 2:
subtitle_name = subtitle_name + ' ' + (__language__(32001) % int(matches.group('numfiles')))
subtitles.append({'rating': rating, 'filename': subtitle_name, 'sync': sync, 'link': link,
'lang': language_info, 'hearing_imp': hearing_imp, 'comment': comment,
'episode': episode})
else:
subtitles.append({'rating': rating, 'filename': subtitle_name, 'sync': sync, 'link': link,
'lang': language_info, 'hearing_imp': hearing_imp, 'comment': comment})
subtitles.sort(key=lambda x: [not x['sync'], not x['lang']['name'] == PreferredSub])
for s in subtitles:
append_subtitle(s)
def getallsubs(url, allowed_languages, filename="", episode=""):
subtitle_pattern = ("<td class=\"a1\">\s+<a href=\"(?P<link>/subtitles/[^\"]+)\">\s+"
"<span class=\"[^\"]+ (?P<quality>\w+-icon)\">\s+(?P<language>[^\r\n\t]+)\s+</span>\s+"
"<span>\s+(?P<filename>[^\r\n\t]+)\s+</span>\s+"
"</a>\s+</td>\s+"
"<td class=\"[^\"]+\">\s+(?P<numfiles>[^\r\n\t]*)\s+</td>\s+"
"<td class=\"(?P<hiclass>[^\"]+)\">"
"(?:.*?)<td class=\"a6\">\s+<div>\s+(?P<comment>[^\"]+) \s*</div>")
codes = get_language_codes(allowed_languages)
if len(codes) < 1:
_xbmc_notification(32004)
return
log(__name__, 'LanguageFilter='+','.join(codes))
#content, response_url = geturl(url, 'LanguageFilter='+','.join(codes))
content, response_url = geturl(url)
if content is None:
log(__name__, 'response empty')
return
subtitles = []
h = HTMLParser.HTMLParser()
episode_regex = None
any_episode_regex = None
if episode != "":
episode_regex = re.compile(get_episode_pattern(episode), re.IGNORECASE)
any_episode_regex = re.compile("(?:s[0-9]{2}e[0-9]{2}|\D[0-9]{1,2}x[0-9]{2})", re.IGNORECASE)
log(__name__, "regex: %s" % get_episode_pattern(episode))
for matches in re.finditer(subtitle_pattern, content, re.IGNORECASE | re.DOTALL):
log(__name__, "Found subtitle: %s" % matches.groupdict())
numfiles = -1
if matches.group('numfiles') != "":
numfiles = int(matches.group('numfiles'))
languagefound = matches.group('language')
language_info = None
if languagefound in subscene_languages:
language_info = subscene_languages[languagefound]
else:
log(__name__, "not in subscene_languages: %s" % languagefound)
continue
log(__name__, "language_info: %s, language_info['3let']: %s, allowed_languages: %s" % (language_info, language_info['3let'], allowed_languages))
if language_info is not None and language_info['3let'] in allowed_languages:
link = main_url + matches.group('link')
subtitle_name = string.strip(matches.group('filename'))
hearing_imp = (matches.group('hiclass') == "a41")
rating = '0'
if matches.group('quality') == "bad-icon":
continue
if matches.group('quality') == "positive-icon":
rating = '5'
comment = re.sub("[\r\n\t]+", " ", h.unescape(string.strip(matches.group('comment'))))
sync = False
if filename != "" and string.lower(filename) == string.lower(subtitle_name):
sync = True
if episode != "":
# log(__name__, "match: "+subtitle_name)
# matching episode
if episode_regex.search(subtitle_name):
subtitles.append({'rating': rating, 'filename': subtitle_name, 'sync': sync, 'link': link,
'lang': language_info, 'hearing_imp': hearing_imp, 'comment': comment})
# multiple files
elif numfiles > 2:
subtitle_name = subtitle_name + ' ' + (_xmbc_localized_string_utf8(32001) % int(matches.group('numfiles')))
subtitles.append({'rating': rating, 'filename': subtitle_name, 'sync': sync, 'link': link,
'lang': language_info, 'hearing_imp': hearing_imp, 'comment': comment,
'episode': episode})
# not matching any episode (?)
elif not any_episode_regex.search(subtitle_name):
subtitles.append({'rating': rating, 'filename': subtitle_name, 'sync': sync, 'link': link,
'lang': language_info, 'hearing_imp': hearing_imp, 'comment': comment,
'episode': episode})
else:
subtitles.append({'rating': rating, 'filename': subtitle_name, 'sync': sync, 'link': link,
'lang': language_info, 'hearing_imp': hearing_imp, 'comment': comment})
subtitles.sort(key=lambda x: [not x['sync'], not x['lang']['name'] == PreferredSub])
log(__name__, "subtitles count: %s" % len(subtitles))
for s in subtitles:
append_subtitle(s)