]> git.bitcoin.ninja Git - youtube-dl/blob - youtube_dl/extractor/hotstar.py
[pornhub] Extract categories and tags (closes #10499)
[youtube-dl] / youtube_dl / extractor / hotstar.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 from .common import InfoExtractor
5 from ..utils import (
6     ExtractorError,
7     determine_ext,
8     int_or_none,
9 )
10
11
12 class HotStarIE(InfoExtractor):
13     _VALID_URL = r'https?://(?:www\.)?hotstar\.com/(?:.+?[/-])?(?P<id>\d{10})'
14     _TESTS = [{
15         'url': 'http://www.hotstar.com/on-air-with-aib--english-1000076273',
16         'info_dict': {
17             'id': '1000076273',
18             'ext': 'mp4',
19             'title': 'On Air With AIB - English',
20             'description': 'md5:c957d8868e9bc793ccb813691cc4c434',
21             'timestamp': 1447227000,
22             'upload_date': '20151111',
23             'duration': 381,
24         },
25         'params': {
26             # m3u8 download
27             'skip_download': True,
28         }
29     }, {
30         'url': 'http://www.hotstar.com/sports/cricket/rajitha-sizzles-on-debut-with-329/2001477583',
31         'only_matching': True,
32     }, {
33         'url': 'http://www.hotstar.com/1000000515',
34         'only_matching': True,
35     }]
36
37     _GET_CONTENT_TEMPLATE = 'http://account.hotstar.com/AVS/besc?action=GetAggregatedContentDetails&channel=PCTV&contentId=%s'
38     _GET_CDN_TEMPLATE = 'http://getcdn.hotstar.com/AVS/besc?action=GetCDN&asJson=Y&channel=%s&id=%s&type=%s'
39
40     def _download_json(self, url_or_request, video_id, note='Downloading JSON metadata', fatal=True):
41         json_data = super(HotStarIE, self)._download_json(url_or_request, video_id, note, fatal=fatal)
42         if json_data['resultCode'] != 'OK':
43             if fatal:
44                 raise ExtractorError(json_data['errorDescription'])
45             return None
46         return json_data['resultObj']
47
48     def _real_extract(self, url):
49         video_id = self._match_id(url)
50         video_data = self._download_json(
51             self._GET_CONTENT_TEMPLATE % video_id,
52             video_id)['contentInfo'][0]
53
54         formats = []
55         # PCTV for extracting f4m manifest
56         for f in ('TABLET',):
57             format_data = self._download_json(
58                 self._GET_CDN_TEMPLATE % (f, video_id, 'VOD'),
59                 video_id, 'Downloading %s JSON metadata' % f, fatal=False)
60             if format_data:
61                 format_url = format_data['src']
62                 ext = determine_ext(format_url)
63                 if ext == 'm3u8':
64                     formats.extend(self._extract_m3u8_formats(format_url, video_id, 'mp4', m3u8_id='hls', fatal=False))
65                 elif ext == 'f4m':
66                     # produce broken files
67                     continue
68                 else:
69                     formats.append({
70                         'url': format_url,
71                         'width': int_or_none(format_data.get('width')),
72                         'height': int_or_none(format_data.get('height')),
73                     })
74         self._sort_formats(formats)
75
76         return {
77             'id': video_id,
78             'title': video_data['episodeTitle'],
79             'description': video_data.get('description'),
80             'duration': int_or_none(video_data.get('duration')),
81             'timestamp': int_or_none(video_data.get('broadcastDate')),
82             'formats': formats,
83         }