]> Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/webcaster.py
Fix extraction from youtube.
[youtubedl] / youtube_dl / extractor / webcaster.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 import re
5
6 from .common import InfoExtractor
7 from ..utils import (
8 determine_ext,
9 xpath_text,
10 )
11
12
13 class WebcasterIE(InfoExtractor):
14 _VALID_URL = r'https?://bl\.webcaster\.pro/(?:quote|media)/start/free_(?P<id>[^/]+)'
15 _TESTS = [{
16 # http://video.khl.ru/quotes/393859
17 'url': 'http://bl.webcaster.pro/quote/start/free_c8cefd240aa593681c8d068cff59f407_hd/q393859/eb173f99dd5f558674dae55f4ba6806d/1480289104?sr%3D105%26fa%3D1%26type_id%3D18',
18 'md5': '0c162f67443f30916ff1c89425dcd4cd',
19 'info_dict': {
20 'id': 'c8cefd240aa593681c8d068cff59f407_hd',
21 'ext': 'mp4',
22 'title': 'Сибирь - Нефтехимик. Лучшие моменты первого периода',
23 'thumbnail': r're:^https?://.*\.jpg$',
24 },
25 }, {
26 'url': 'http://bl.webcaster.pro/media/start/free_6246c7a4453ac4c42b4398f840d13100_hd/2_2991109016/e8d0d82587ef435480118f9f9c41db41/4635726126',
27 'only_matching': True,
28 }]
29
30 def _real_extract(self, url):
31 video_id = self._match_id(url)
32
33 video = self._download_xml(url, video_id)
34
35 title = xpath_text(video, './/event_name', 'event name', fatal=True)
36
37 def make_id(parts, separator):
38 return separator.join(filter(None, parts))
39
40 formats = []
41 for format_id in (None, 'noise'):
42 track_tag = make_id(('track', format_id), '_')
43 for track in video.findall('.//iphone/%s' % track_tag):
44 track_url = track.text
45 if not track_url:
46 continue
47 if determine_ext(track_url) == 'm3u8':
48 m3u8_formats = self._extract_m3u8_formats(
49 track_url, video_id, 'mp4',
50 entry_protocol='m3u8_native',
51 m3u8_id=make_id(('hls', format_id), '-'), fatal=False)
52 for f in m3u8_formats:
53 f.update({
54 'source_preference': 0 if format_id == 'noise' else 1,
55 'format_note': track.get('title'),
56 })
57 formats.extend(m3u8_formats)
58 self._sort_formats(formats)
59
60 thumbnail = xpath_text(video, './/image', 'thumbnail')
61
62 return {
63 'id': video_id,
64 'title': title,
65 'thumbnail': thumbnail,
66 'formats': formats,
67 }
68
69
70 class WebcasterFeedIE(InfoExtractor):
71 _VALID_URL = r'https?://bl\.webcaster\.pro/feed/start/free_(?P<id>[^/]+)'
72 _TEST = {
73 'url': 'http://bl.webcaster.pro/feed/start/free_c8cefd240aa593681c8d068cff59f407_hd/q393859/eb173f99dd5f558674dae55f4ba6806d/1480289104',
74 'only_matching': True,
75 }
76
77 @staticmethod
78 def _extract_url(ie, webpage):
79 mobj = re.search(
80 r'<(?:object|a[^>]+class=["\']webcaster-player["\'])[^>]+data(?:-config)?=(["\']).*?config=(?P<url>https?://bl\.webcaster\.pro/feed/start/free_.*?)(?:[?&]|\1)',
81 webpage)
82 if mobj:
83 return mobj.group('url')
84 for secure in (True, False):
85 video_url = ie._og_search_video_url(
86 webpage, secure=secure, default=None)
87 if video_url:
88 mobj = re.search(
89 r'config=(?P<url>https?://bl\.webcaster\.pro/feed/start/free_[^?&=]+)',
90 video_url)
91 if mobj:
92 return mobj.group('url')
93
94 def _real_extract(self, url):
95 video_id = self._match_id(url)
96
97 feed = self._download_xml(url, video_id)
98
99 video_url = xpath_text(
100 feed, ('video_hd', 'video'), 'video url', fatal=True)
101
102 return self.url_result(video_url, WebcasterIE.ie_key())