From 32f9036447d1211f9ce0750203d71671f0ee99dc Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Fri, 1 Jan 2016 13:28:45 +0100 Subject: [PATCH] [ccc] Add language information to formats --- youtube_dl/YoutubeDL.py | 4 ++++ youtube_dl/extractor/ccc.py | 8 ++++++-- youtube_dl/extractor/common.py | 5 +++-- 3 files changed, 13 insertions(+), 4 deletions(-) diff --git a/youtube_dl/YoutubeDL.py b/youtube_dl/YoutubeDL.py index 50425b8d7..3b2be3159 100755 --- a/youtube_dl/YoutubeDL.py +++ b/youtube_dl/YoutubeDL.py @@ -1791,6 +1791,10 @@ class YoutubeDL(object): res = '' if fdict.get('ext') in ['f4f', 'f4m']: res += '(unsupported) ' + if fdict.get('language'): + if res: + res += ' ' + res += '[%s]' % fdict['language'] if fdict.get('format_note') is not None: res += fdict['format_note'] + ' ' if fdict.get('tbr') is not None: diff --git a/youtube_dl/extractor/ccc.py b/youtube_dl/extractor/ccc.py index 710e5919c..e94b1e35b 100644 --- a/youtube_dl/extractor/ccc.py +++ b/youtube_dl/extractor/ccc.py @@ -58,11 +58,12 @@ class CCCIE(InfoExtractor): webpage, 'duration', fatal=False, group='duration')) matches = re.finditer(r'''(?xs) - <(?:span|div)\s+class='label\s+filetype'>(?P.*?)\s* + <(?:span|div)\s+class='label\s+filetype'>(?P[^<]*)\s* + <(?:span|div)\s+class='label\s+filetype'>(?P[^<]*)\s* [^']+)'>\s* (?: .*? - [^']+\.torrent)' + [^']+\.torrent)' )?''', webpage) formats = [] for m in matches: @@ -70,12 +71,15 @@ class CCCIE(InfoExtractor): format_id = self._search_regex( r'.*/([a-z0-9_-]+)/[^/]*$', m.group('http_url'), 'format id', default=None) + if format_id: + format_id = m.group('lang') + '-' + format_id vcodec = 'h264' if 'h264' in format_id else ( 'none' if format_id in ('mp3', 'opus') else None ) formats.append({ 'format_id': format_id, 'format': format, + 'language': m.group('lang'), 'url': m.group('http_url'), 'vcodec': vcodec, 'preference': preference(format_id), diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index 655207447..2823b1d18 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -108,8 +108,9 @@ class InfoExtractor(object): -2 or smaller for less than default. < -1000 to hide the format (if there is another one which is strictly better) - * language_preference Is this in the correct requested - language? + * language Language code, e.g. "de" or "en-US". + * language_preference Is this in the language mentioned in + the URL? 10 if it's what the URL is about, -1 for default (don't know), -10 otherwise, other values reserved for now.