]> jfr.im git - yt-dlp.git/blame - yt_dlp/extractor/webcaster.py
[utils] Add `join_nonempty`
[yt-dlp.git] / yt_dlp / extractor / webcaster.py
CommitLineData
f25e1c8d
S
1# coding: utf-8
2from __future__ import unicode_literals
3
4import re
5
6from .common import InfoExtractor
7from ..utils import (
8 determine_ext,
34921b43 9 join_nonempty,
f25e1c8d
S
10 xpath_text,
11)
12
13
14class WebcasterIE(InfoExtractor):
15 _VALID_URL = r'https?://bl\.webcaster\.pro/(?:quote|media)/start/free_(?P<id>[^/]+)'
16 _TESTS = [{
17 # http://video.khl.ru/quotes/393859
18 'url': 'http://bl.webcaster.pro/quote/start/free_c8cefd240aa593681c8d068cff59f407_hd/q393859/eb173f99dd5f558674dae55f4ba6806d/1480289104?sr%3D105%26fa%3D1%26type_id%3D18',
19 'md5': '0c162f67443f30916ff1c89425dcd4cd',
20 'info_dict': {
21 'id': 'c8cefd240aa593681c8d068cff59f407_hd',
22 'ext': 'mp4',
23 'title': 'Сибирь - Нефтехимик. Лучшие моменты первого периода',
ec85ded8 24 'thumbnail': r're:^https?://.*\.jpg$',
f25e1c8d
S
25 },
26 }, {
27 'url': 'http://bl.webcaster.pro/media/start/free_6246c7a4453ac4c42b4398f840d13100_hd/2_2991109016/e8d0d82587ef435480118f9f9c41db41/4635726126',
28 'only_matching': True,
29 }]
30
31 def _real_extract(self, url):
32 video_id = self._match_id(url)
33
34 video = self._download_xml(url, video_id)
35
36 title = xpath_text(video, './/event_name', 'event name', fatal=True)
37
f25e1c8d
S
38 formats = []
39 for format_id in (None, 'noise'):
34921b43 40 track_tag = join_nonempty('track', format_id, delim='_')
f25e1c8d
S
41 for track in video.findall('.//iphone/%s' % track_tag):
42 track_url = track.text
43 if not track_url:
44 continue
45 if determine_ext(track_url) == 'm3u8':
46 m3u8_formats = self._extract_m3u8_formats(
47 track_url, video_id, 'mp4',
48 entry_protocol='m3u8_native',
34921b43 49 m3u8_id=join_nonempty('hls', format_id, delim='-'), fatal=False)
f25e1c8d
S
50 for f in m3u8_formats:
51 f.update({
52 'source_preference': 0 if format_id == 'noise' else 1,
53 'format_note': track.get('title'),
54 })
55 formats.extend(m3u8_formats)
56 self._sort_formats(formats)
57
58 thumbnail = xpath_text(video, './/image', 'thumbnail')
59
60 return {
61 'id': video_id,
62 'title': title,
63 'thumbnail': thumbnail,
64 'formats': formats,
65 }
66
67
68class WebcasterFeedIE(InfoExtractor):
69 _VALID_URL = r'https?://bl\.webcaster\.pro/feed/start/free_(?P<id>[^/]+)'
70 _TEST = {
71 'url': 'http://bl.webcaster.pro/feed/start/free_c8cefd240aa593681c8d068cff59f407_hd/q393859/eb173f99dd5f558674dae55f4ba6806d/1480289104',
72 'only_matching': True,
73 }
74
83f1481b
S
75 @staticmethod
76 def _extract_url(ie, webpage):
77 mobj = re.search(
78 r'<(?:object|a[^>]+class=["\']webcaster-player["\'])[^>]+data(?:-config)?=(["\']).*?config=(?P<url>https?://bl\.webcaster\.pro/feed/start/free_.*?)(?:[?&]|\1)',
79 webpage)
80 if mobj:
81 return mobj.group('url')
82 for secure in (True, False):
83 video_url = ie._og_search_video_url(
84 webpage, secure=secure, default=None)
85 if video_url:
86 mobj = re.search(
87 r'config=(?P<url>https?://bl\.webcaster\.pro/feed/start/free_[^?&=]+)',
88 video_url)
89 if mobj:
90 return mobj.group('url')
91
f25e1c8d
S
92 def _real_extract(self, url):
93 video_id = self._match_id(url)
94
95 feed = self._download_xml(url, video_id)
96
97 video_url = xpath_text(
98 feed, ('video_hd', 'video'), 'video url', fatal=True)
99
100 return self.url_result(video_url, WebcasterIE.ie_key())