2 from __future__ import unicode_literals
6 from .common import InfoExtractor
15 class Lecture2GoIE(InfoExtractor):
16 _VALID_URL = r'https?://lecture2go\.uni-hamburg\.de/veranstaltungen/-/v/(?P<id>\d+)'
18 'url': 'https://lecture2go.uni-hamburg.de/veranstaltungen/-/v/17473',
19 'md5': 'ac02b570883020d208d405d5a3fd2f7f',
23 'title': '2 - Endliche Automaten und reguläre Sprachen',
24 'creator': 'Frank Heitmann',
29 'skip_download': True,
33 def _real_extract(self, url):
34 video_id = self._match_id(url)
35 webpage = self._download_webpage(url, video_id)
37 title = self._html_search_regex(r'<em[^>]+class="title">(.+)</em>', webpage, 'title')
40 for url in set(re.findall(r'var\s+playerUri\d+\s*=\s*"([^"]+)"', webpage)):
41 ext = determine_ext(url)
42 protocol = determine_protocol({'url': url})
44 formats.extend(self._extract_f4m_formats(url, video_id, f4m_id='hds'))
46 formats.extend(self._extract_m3u8_formats(url, video_id, ext='mp4', m3u8_id='hls'))
48 if protocol == 'rtmp':
49 continue # XXX: currently broken
51 'format_id': protocol,
55 self._sort_formats(formats)
57 creator = self._html_search_regex(
58 r'<div[^>]+id="description">([^<]+)</div>', webpage, 'creator', fatal=False)
59 duration = parse_duration(self._html_search_regex(
60 r'Duration:\s*</em>\s*<em[^>]*>([^<]+)</em>', webpage, 'duration', fatal=False))
61 view_count = int_or_none(self._html_search_regex(
62 r'Views:\s*</em>\s*<em[^>]+>(\d+)</em>', webpage, 'view count', fatal=False))
70 'view_count': view_count,