]>
Commit | Line | Data |
---|---|---|
1 | import re | |
2 | ||
3 | from .common import InfoExtractor | |
4 | from ..utils import ( | |
5 | determine_ext, | |
6 | determine_protocol, | |
7 | int_or_none, | |
8 | parse_duration, | |
9 | ) | |
10 | ||
11 | ||
12 | class Lecture2GoIE(InfoExtractor): | |
13 | _WORKING = False | |
14 | _VALID_URL = r'https?://lecture2go\.uni-hamburg\.de/veranstaltungen/-/v/(?P<id>\d+)' | |
15 | _TEST = { | |
16 | 'url': 'https://lecture2go.uni-hamburg.de/veranstaltungen/-/v/17473', | |
17 | 'md5': 'ac02b570883020d208d405d5a3fd2f7f', | |
18 | 'info_dict': { | |
19 | 'id': '17473', | |
20 | 'ext': 'mp4', | |
21 | 'title': '2 - Endliche Automaten und reguläre Sprachen', | |
22 | 'creator': 'Frank Heitmann', | |
23 | 'duration': 5220, | |
24 | }, | |
25 | 'params': { | |
26 | # m3u8 download | |
27 | 'skip_download': True, | |
28 | }, | |
29 | } | |
30 | ||
31 | def _real_extract(self, url): | |
32 | video_id = self._match_id(url) | |
33 | webpage = self._download_webpage(url, video_id) | |
34 | ||
35 | title = self._html_search_regex(r'<em[^>]+class="title">(.+)</em>', webpage, 'title') | |
36 | ||
37 | formats = [] | |
38 | for url in set(re.findall(r'var\s+playerUri\d+\s*=\s*"([^"]+)"', webpage)): | |
39 | ext = determine_ext(url) | |
40 | protocol = determine_protocol({'url': url}) | |
41 | if ext == 'f4m': | |
42 | formats.extend(self._extract_f4m_formats(url, video_id, f4m_id='hds')) | |
43 | elif ext == 'm3u8': | |
44 | formats.extend(self._extract_m3u8_formats(url, video_id, ext='mp4', m3u8_id='hls')) | |
45 | else: | |
46 | if protocol == 'rtmp': | |
47 | continue # XXX: currently broken | |
48 | formats.append({ | |
49 | 'format_id': protocol, | |
50 | 'url': url, | |
51 | }) | |
52 | ||
53 | creator = self._html_search_regex( | |
54 | r'<div[^>]+id="description">([^<]+)</div>', webpage, 'creator', fatal=False) | |
55 | duration = parse_duration(self._html_search_regex( | |
56 | r'Duration:\s*</em>\s*<em[^>]*>([^<]+)</em>', webpage, 'duration', fatal=False)) | |
57 | view_count = int_or_none(self._html_search_regex( | |
58 | r'Views:\s*</em>\s*<em[^>]+>(\d+)</em>', webpage, 'view count', fatal=False)) | |
59 | ||
60 | return { | |
61 | 'id': video_id, | |
62 | 'title': title, | |
63 | 'formats': formats, | |
64 | 'creator': creator, | |
65 | 'duration': duration, | |
66 | 'view_count': view_count, | |
67 | } |