Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/hotstar.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..compat import compat_str
   8 from ..utils import (
   9     determine_ext,
  10     ExtractorError,
  11     int_or_none,
  12 )
  13
  14
  15 class HotStarBaseIE(InfoExtractor):
  16     _GEO_COUNTRIES = ['IN']
  17
  18     def _download_json(self, *args, **kwargs):
  19         response = super(HotStarBaseIE, self)._download_json(*args, **kwargs)
  20         if response['resultCode'] != 'OK':
  21             if kwargs.get('fatal'):
  22                 raise ExtractorError(
  23                     response['errorDescription'], expected=True)
  24             return None
  25         return response['resultObj']
  26
  27     def _download_content_info(self, content_id):
  28         return self._download_json(
  29             'https://account.hotstar.com/AVS/besc', content_id, query={
  30                 'action': 'GetAggregatedContentDetails',
  31                 'appVersion': '5.0.40',
  32                 'channel': 'PCTV',
  33                 'contentId': content_id,
  34             })['contentInfo'][0]
  35
  36
  37 class HotStarIE(HotStarBaseIE):
  38     _VALID_URL = r'https?://(?:www\.)?hotstar\.com/(?:.+?[/-])?(?P<id>\d{10})'
  39     _TESTS = [{
  40         'url': 'http://www.hotstar.com/on-air-with-aib--english-1000076273',
  41         'info_dict': {
  42             'id': '1000076273',
  43             'ext': 'mp4',
  44             'title': 'On Air With AIB',
  45             'description': 'md5:c957d8868e9bc793ccb813691cc4c434',
  46             'timestamp': 1447227000,
  47             'upload_date': '20151111',
  48             'duration': 381,
  49         },
  50         'params': {
  51             # m3u8 download
  52             'skip_download': True,
  53         }
  54     }, {
  55         'url': 'http://www.hotstar.com/sports/cricket/rajitha-sizzles-on-debut-with-329/2001477583',
  56         'only_matching': True,
  57     }, {
  58         'url': 'http://www.hotstar.com/1000000515',
  59         'only_matching': True,
  60     }]
  61
  62     def _real_extract(self, url):
  63         video_id = self._match_id(url)
  64
  65         video_data = self._download_content_info(video_id)
  66
  67         title = video_data['episodeTitle']
  68
  69         if video_data.get('encrypted') == 'Y':
  70             raise ExtractorError('This video is DRM protected.', expected=True)
  71
  72         formats = []
  73         for f in ('JIO',):
  74             format_data = self._download_json(
  75                 'http://getcdn.hotstar.com/AVS/besc',
  76                 video_id, 'Downloading %s JSON metadata' % f,
  77                 fatal=False, query={
  78                     'action': 'GetCDN',
  79                     'asJson': 'Y',
  80                     'channel': f,
  81                     'id': video_id,
  82                     'type': 'VOD',
  83                 })
  84             if format_data:
  85                 format_url = format_data.get('src')
  86                 if not format_url:
  87                     continue
  88                 ext = determine_ext(format_url)
  89                 if ext == 'm3u8':
  90                     formats.extend(self._extract_m3u8_formats(
  91                         format_url, video_id, 'mp4',
  92                         m3u8_id='hls', fatal=False))
  93                 elif ext == 'f4m':
  94                     # produce broken files
  95                     continue
  96                 else:
  97                     formats.append({
  98                         'url': format_url,
  99                         'width': int_or_none(format_data.get('width')),
 100                         'height': int_or_none(format_data.get('height')),
 101                     })
 102         self._sort_formats(formats)
 103
 104         return {
 105             'id': video_id,
 106             'title': title,
 107             'description': video_data.get('description'),
 108             'duration': int_or_none(video_data.get('duration')),
 109             'timestamp': int_or_none(video_data.get('broadcastDate')),
 110             'formats': formats,
 111             'episode': title,
 112             'episode_number': int_or_none(video_data.get('episodeNumber')),
 113             'series': video_data.get('contentTitle'),
 114         }
 115
 116
 117 class HotStarPlaylistIE(HotStarBaseIE):
 118     IE_NAME = 'hotstar:playlist'
 119     _VALID_URL = r'(?P<url>https?://(?:www\.)?hotstar\.com/tv/[^/]+/(?P<content_id>\d+))/(?P<type>[^/]+)/(?P<id>\d+)'
 120     _TESTS = [{
 121         'url': 'http://www.hotstar.com/tv/pratidaan/14982/episodes/14812/9993',
 122         'info_dict': {
 123             'id': '14812',
 124         },
 125         'playlist_mincount': 75,
 126     }, {
 127         'url': 'http://www.hotstar.com/tv/pratidaan/14982/popular-clips/9998/9998',
 128         'only_matching': True,
 129     }]
 130     _ITEM_TYPES = {
 131         'episodes': 'EPISODE',
 132         'popular-clips': 'CLIPS',
 133     }
 134
 135     def _real_extract(self, url):
 136         mobj = re.match(self._VALID_URL, url)
 137         base_url = mobj.group('url')
 138         content_id = mobj.group('content_id')
 139         playlist_type = mobj.group('type')
 140
 141         content_info = self._download_content_info(content_id)
 142         playlist_id = compat_str(content_info['categoryId'])
 143
 144         collection = self._download_json(
 145             'https://search.hotstar.com/AVS/besc', playlist_id, query={
 146                 'action': 'SearchContents',
 147                 'appVersion': '5.0.40',
 148                 'channel': 'PCTV',
 149                 'moreFilters': 'series:%s;' % playlist_id,
 150                 'query': '*',
 151                 'searchOrder': 'last_broadcast_date desc,year desc,title asc',
 152                 'type': self._ITEM_TYPES.get(playlist_type, 'EPISODE'),
 153             })
 154
 155         entries = [
 156             self.url_result(
 157                 '%s/_/%s' % (base_url, video['contentId']),
 158                 ie=HotStarIE.ie_key(), video_id=video['contentId'])
 159             for video in collection['response']['docs']
 160             if video.get('contentId')]
 161
 162         return self.playlist_result(entries, playlist_id)