X-Git-Url: http://git.cielonegro.org/gitweb.cgi?a=blobdiff_plain;ds=sidebyside;f=youtube_dl%2Fextractor%2Fccc.py;h=dda2c0959882c3cd3c5de56b817ccd7815ef0068;hb=49dea4913bea3b8e5c7d65dd932aa68ada526088;hp=5b549b343f94da1bf76bd31572df62cf361fa449;hpb=c9154514c495bd2259df2250d4cf72a2564a9136;p=youtube-dl.git diff --git a/youtube_dl/extractor/ccc.py b/youtube_dl/extractor/ccc.py index 5b549b343..dda2c0959 100644 --- a/youtube_dl/extractor/ccc.py +++ b/youtube_dl/extractor/ccc.py @@ -5,6 +5,7 @@ import re from .common import InfoExtractor from ..utils import ( int_or_none, + parse_duration, qualities, unified_strdate, ) @@ -21,10 +22,11 @@ class CCCIE(InfoExtractor): 'id': '30C3_-_5443_-_en_-_saal_g_-_201312281830_-_introduction_to_processor_design_-_byterazor', 'ext': 'mp4', 'title': 'Introduction to Processor Design', - 'description': 'md5:5ddbf8c734800267f2cee4eab187bc1b', + 'description': 'md5:80be298773966f66d56cb11260b879af', 'thumbnail': 're:^https?://.*\.jpg$', 'view_count': int, - 'upload_date': '20131229', + 'upload_date': '20131228', + 'duration': 3660, } }, { 'url': 'https://media.ccc.de/v/32c3-7368-shopshifting#download', @@ -43,7 +45,7 @@ class CCCIE(InfoExtractor): title = self._html_search_regex( r'(?s)

(.*?)

', webpage, 'title') description = self._html_search_regex( - r"(?s)

(.*?)

", + r'(?s)

About

(.+?)

', webpage, 'description', fatal=False) upload_date = unified_strdate(self._html_search_regex( r"(?s)]+class='[^']*fa-calendar-o'[^>]*>(.+?)", @@ -51,13 +53,17 @@ class CCCIE(InfoExtractor): view_count = int_or_none(self._html_search_regex( r"(?s)(.*?)", webpage, 'view count', fatal=False)) + duration = parse_duration(self._html_search_regex( + r'(?s)]+class=(["\']).*?fa-clock-o.*?\1[^>]*>(?P.+?)(?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: @@ -65,12 +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), @@ -98,5 +107,6 @@ class CCCIE(InfoExtractor): 'thumbnail': thumbnail, 'view_count': view_count, 'upload_date': upload_date, + 'duration': duration, 'formats': formats, }