]> Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/tvigle.py
Merge tag 'upstream/2015.06.04.1'
[youtubedl] / youtube_dl / extractor / tvigle.py
1 # encoding: utf-8
2 from __future__ import unicode_literals
3
4 import re
5
6 from .common import InfoExtractor
7 from ..utils import (
8 ExtractorError,
9 float_or_none,
10 int_or_none,
11 parse_age_limit,
12 )
13
14
15 class TvigleIE(InfoExtractor):
16 IE_NAME = 'tvigle'
17 IE_DESC = 'Интернет-телевидение Tvigle.ru'
18 _VALID_URL = r'https?://(?:www\.)?(?:tvigle\.ru/(?:[^/]+/)+(?P<display_id>[^/]+)/$|cloud\.tvigle\.ru/video/(?P<id>\d+))'
19
20 _TESTS = [
21 {
22 'url': 'http://www.tvigle.ru/video/sokrat/',
23 'md5': '36514aed3657d4f70b4b2cef8eb520cd',
24 'info_dict': {
25 'id': '1848932',
26 'display_id': 'sokrat',
27 'ext': 'flv',
28 'title': 'Сократ',
29 'description': 'md5:d6b92ffb7217b4b8ebad2e7665253c17',
30 'duration': 6586,
31 'age_limit': 12,
32 },
33 'skip': 'georestricted',
34 },
35 {
36 'url': 'http://www.tvigle.ru/video/vladimir-vysotskii/vedushchii-teleprogrammy-60-minut-ssha-o-vladimire-vysotskom/',
37 'md5': 'e7efe5350dd5011d0de6550b53c3ba7b',
38 'info_dict': {
39 'id': '5142516',
40 'ext': 'flv',
41 'title': 'Ведущий телепрограммы «60 минут» (США) о Владимире Высоцком',
42 'description': 'md5:027f7dc872948f14c96d19b4178428a4',
43 'duration': 186.080,
44 'age_limit': 0,
45 },
46 'skip': 'georestricted',
47 }, {
48 'url': 'https://cloud.tvigle.ru/video/5267604/',
49 'only_matching': True,
50 }
51 ]
52
53 def _real_extract(self, url):
54 mobj = re.match(self._VALID_URL, url)
55 video_id = mobj.group('id')
56 display_id = mobj.group('display_id')
57
58 if not video_id:
59 webpage = self._download_webpage(url, display_id)
60 video_id = self._html_search_regex(
61 r'class="video-preview current_playing" id="(\d+)">',
62 webpage, 'video id')
63
64 video_data = self._download_json(
65 'http://cloud.tvigle.ru/api/play/video/%s/' % video_id, display_id)
66
67 item = video_data['playlist']['items'][0]
68
69 videos = item.get('videos')
70
71 error_message = item.get('errorMessage')
72 if not videos and error_message:
73 raise ExtractorError(
74 '%s returned error: %s' % (self.IE_NAME, error_message), expected=True)
75
76 title = item['title']
77 description = item.get('description')
78 thumbnail = item.get('thumbnail')
79 duration = float_or_none(item.get('durationMilliseconds'), 1000)
80 age_limit = parse_age_limit(item.get('ageRestrictions'))
81
82 formats = []
83 for vcodec, fmts in item['videos'].items():
84 for format_id, video_url in fmts.items():
85 if format_id == 'm3u8':
86 formats.extend(self._extract_m3u8_formats(
87 video_url, video_id, 'mp4', m3u8_id=vcodec))
88 continue
89 height = self._search_regex(
90 r'^(\d+)[pP]$', format_id, 'height', default=None)
91 formats.append({
92 'url': video_url,
93 'format_id': '%s-%s' % (vcodec, format_id),
94 'vcodec': vcodec,
95 'height': int_or_none(height),
96 'filesize': int_or_none(item.get('video_files_size', {}).get(vcodec, {}).get(format_id)),
97 })
98 self._sort_formats(formats)
99
100 return {
101 'id': video_id,
102 'display_id': display_id,
103 'title': title,
104 'description': description,
105 'thumbnail': thumbnail,
106 'duration': duration,
107 'age_limit': age_limit,
108 'formats': formats,
109 }