X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Flecture2go.py;h=81b5d41be4a676e55c795fe233591913e7a691c8;hb=HEAD;hp=a2f9d5c543bbc816d578db262aa59ef849c26fa8;hpb=e9c6deffee26db40992293b3055df31804ca7e12;p=youtube-dl diff --git a/youtube_dl/extractor/lecture2go.py b/youtube_dl/extractor/lecture2go.py index a2f9d5c54..81b5d41be 100644 --- a/youtube_dl/extractor/lecture2go.py +++ b/youtube_dl/extractor/lecture2go.py @@ -6,6 +6,7 @@ import re from .common import InfoExtractor from ..utils import ( determine_ext, + determine_protocol, parse_duration, int_or_none, ) @@ -18,10 +19,14 @@ class Lecture2GoIE(InfoExtractor): 'md5': 'ac02b570883020d208d405d5a3fd2f7f', 'info_dict': { 'id': '17473', - 'ext': 'flv', + 'ext': 'mp4', 'title': '2 - Endliche Automaten und reguläre Sprachen', 'creator': 'Frank Heitmann', 'duration': 5220, + }, + 'params': { + # m3u8 download + 'skip_download': True, } } @@ -32,20 +37,25 @@ class Lecture2GoIE(InfoExtractor): title = self._html_search_regex(r']+class="title">(.+)', webpage, 'title') formats = [] - for url in set(re.findall(r'"src","([^"]+)"', webpage)): + for url in set(re.findall(r'var\s+playerUri\d+\s*=\s*"([^"]+)"', webpage)): ext = determine_ext(url) + protocol = determine_protocol({'url': url}) if ext == 'f4m': - formats.extend(self._extract_f4m_formats(url, video_id)) + formats.extend(self._extract_f4m_formats(url, video_id, f4m_id='hds')) elif ext == 'm3u8': - formats.extend(self._extract_m3u8_formats(url, video_id)) + formats.extend(self._extract_m3u8_formats(url, video_id, ext='mp4', m3u8_id='hls')) else: + if protocol == 'rtmp': + continue # XXX: currently broken formats.append({ + 'format_id': protocol, 'url': url, }) self._sort_formats(formats) - creator = self._html_search_regex(r']+id="description">([^<]+)', webpage, 'creator') + creator = self._html_search_regex( + r']+id="description">([^<]+)', webpage, 'creator', fatal=False) duration = parse_duration(self._html_search_regex( r'Duration:\s*\s*]*>([^<]+)', webpage, 'duration', fatal=False)) view_count = int_or_none(self._html_search_regex(