]> jfr.im git - yt-dlp.git/blame - yt_dlp/extractor/nobelprize.py
[extractor] Deprecate `_sort_formats`
[yt-dlp.git] / yt_dlp / extractor / nobelprize.py
CommitLineData
43c53a17
RA
1from .common import InfoExtractor
2from ..utils import (
3 js_to_json,
4 mimetype2ext,
5 determine_ext,
6 update_url_query,
7 get_element_by_attribute,
8 int_or_none,
9)
10
11
12class NobelPrizeIE(InfoExtractor):
13 _VALID_URL = r'https?://(?:www\.)?nobelprize\.org/mediaplayer.*?\bid=(?P<id>\d+)'
14 _TEST = {
15 'url': 'http://www.nobelprize.org/mediaplayer/?id=2636',
16 'md5': '04c81e5714bb36cc4e2232fee1d8157f',
17 'info_dict': {
18 'id': '2636',
19 'ext': 'mp4',
20 'title': 'Announcement of the 2016 Nobel Prize in Physics',
21 'description': 'md5:05beba57f4f5a4bbd4cf2ef28fcff739',
22 }
23 }
24
25 def _real_extract(self, url):
26 video_id = self._match_id(url)
27 webpage = self._download_webpage(url, video_id)
28 media = self._parse_json(self._search_regex(
29 r'(?s)var\s*config\s*=\s*({.+?});', webpage,
30 'config'), video_id, js_to_json)['media']
31 title = media['title']
32
33 formats = []
34 for source in media.get('source', []):
35 source_src = source.get('src')
36 if not source_src:
37 continue
38 ext = mimetype2ext(source.get('type')) or determine_ext(source_src)
39 if ext == 'm3u8':
40 formats.extend(self._extract_m3u8_formats(
41 source_src, video_id, 'mp4', 'm3u8_native',
42 m3u8_id='hls', fatal=False))
43 elif ext == 'f4m':
44 formats.extend(self._extract_f4m_formats(
45 update_url_query(source_src, {'hdcore': '3.7.0'}),
46 video_id, f4m_id='hds', fatal=False))
47 else:
48 formats.append({
49 'url': source_src,
50 })
43c53a17
RA
51
52 return {
53 'id': video_id,
54 'title': title,
55 'description': get_element_by_attribute('itemprop', 'description', webpage),
56 'duration': int_or_none(media.get('duration')),
57 'formats': formats,
58 }