yt_dlp/extractor/mxplayer.py

   1 from __future__ import unicode_literals
   2
   3
   4 from .common import InfoExtractor
   5 from ..compat import compat_str
   6 from ..utils import (
   7     ExtractorError,
   8     js_to_json,
   9     qualities,
  10     try_get,
  11     url_or_none,
  12     urljoin,
  13 )
  14
  15
  16 class MxplayerIE(InfoExtractor):
  17     _VALID_URL = r'https?://(?:www\.)?mxplayer\.in/(?:movie|show/[-\w]+/[-\w]+)/(?P<display_id>[-\w]+)-(?P<id>\w+)'
  18     _TESTS = [{
  19         'url': 'https://www.mxplayer.in/movie/watch-knock-knock-hindi-dubbed-movie-online-b9fa28df3bfb8758874735bbd7d2655a?watch=true',
  20         'info_dict': {
  21             'id': 'b9fa28df3bfb8758874735bbd7d2655a',
  22             'ext': 'mp4',
  23             'title': 'Knock Knock (Hindi Dubbed)',
  24             'description': 'md5:b195ba93ff1987309cfa58e2839d2a5b'
  25         },
  26         'params': {
  27             'skip_download': True,
  28             'format': 'bestvideo'
  29         }
  30     }, {
  31         'url': 'https://www.mxplayer.in/show/watch-shaitaan/season-1/the-infamous-taxi-gang-of-meerut-online-45055d5bcff169ad48f2ad7552a83d6c',
  32         'info_dict': {
  33             'id': '45055d5bcff169ad48f2ad7552a83d6c',
  34             'ext': 'm3u8',
  35             'title': 'The infamous taxi gang of Meerut',
  36             'description': 'md5:033a0a7e3fd147be4fb7e07a01a3dc28',
  37             'season': 'Season 1',
  38             'series': 'Shaitaan'
  39         },
  40         'params': {
  41             'skip_download': True,
  42         }
  43     }, {
  44         'url': 'https://www.mxplayer.in/show/watch-aashram/chapter-1/duh-swapna-online-d445579792b0135598ba1bc9088a84cb',
  45         'info_dict': {
  46             'id': 'd445579792b0135598ba1bc9088a84cb',
  47             'ext': 'mp4',
  48             'title': 'Duh Swapna',
  49             'description': 'md5:35ff39c4bdac403c53be1e16a04192d8',
  50             'season': 'Chapter 1',
  51             'series': 'Aashram'
  52         },
  53         'expected_warnings': ['Unknown MIME type application/mp4 in DASH manifest'],
  54         'params': {
  55             'skip_download': True,
  56             'format': 'bestvideo'
  57         }
  58     }]
  59
  60     def _get_stream_urls(self, video_dict):
  61         stream_provider_dict = try_get(
  62             video_dict,
  63             lambda x: x['stream'][x['stream']['provider']])
  64         if not stream_provider_dict:
  65             raise ExtractorError('No stream provider found', expected=True)
  66
  67         for stream_name, stream in stream_provider_dict.items():
  68             if stream_name in ('hls', 'dash', 'hlsUrl', 'dashUrl'):
  69                 stream_type = stream_name.replace('Url', '')
  70                 if isinstance(stream, dict):
  71                     for quality, stream_url in stream.items():
  72                         if stream_url:
  73                             yield stream_type, quality, stream_url
  74                 else:
  75                     yield stream_type, 'base', stream
  76
  77     def _real_extract(self, url):
  78         display_id, video_id = self._match_valid_url(url).groups()
  79         webpage = self._download_webpage(url, video_id)
  80
  81         source = self._parse_json(
  82             js_to_json(self._html_search_regex(
  83                 r'(?s)<script>window\.state\s*[:=]\s(\{.+\})\n(\w+).*(</script>).*',
  84                 webpage, 'WindowState')),
  85             video_id)
  86         if not source:
  87             raise ExtractorError('Cannot find source', expected=True)
  88
  89         config_dict = source['config']
  90         video_dict = source['entities'][video_id]
  91
  92         thumbnails = []
  93         for i in video_dict.get('imageInfo') or []:
  94             thumbnails.append({
  95                 'url': urljoin(config_dict['imageBaseUrl'], i['url']),
  96                 'width': i['width'],
  97                 'height': i['height'],
  98             })
  99
 100         formats = []
 101         get_quality = qualities(['main', 'base', 'high'])
 102         for stream_type, quality, stream_url in self._get_stream_urls(video_dict):
 103             format_url = url_or_none(urljoin(config_dict['videoCdnBaseUrl'], stream_url))
 104             if not format_url:
 105                 continue
 106             if stream_type == 'dash':
 107                 dash_formats = self._extract_mpd_formats(
 108                     format_url, video_id, mpd_id='dash-%s' % quality, headers={'Referer': url})
 109                 for frmt in dash_formats:
 110                     frmt['quality'] = get_quality(quality)
 111                 formats.extend(dash_formats)
 112                 dash_formats_h265 = self._extract_mpd_formats(
 113                     format_url.replace('h264_high', 'h265_main'), video_id, mpd_id='dash-%s' % quality, headers={'Referer': url}, fatal=False)
 114                 for frmt in dash_formats_h265:
 115                     frmt['quality'] = get_quality(quality)
 116                 formats.extend(dash_formats_h265)
 117             elif stream_type == 'hls':
 118                 formats.extend(self._extract_m3u8_formats(
 119                     format_url, video_id, fatal=False,
 120                     m3u8_id='hls-%s' % quality, quality=get_quality(quality), ext='mp4'))
 121
 122         self._sort_formats(formats)
 123         return {
 124             'id': video_id,
 125             'display_id': display_id,
 126             'title': video_dict['title'] or self._og_search_title(webpage),
 127             'formats': formats,
 128             'description': video_dict.get('description'),
 129             'season': try_get(video_dict, lambda x: x['container']['title']),
 130             'series': try_get(video_dict, lambda x: x['container']['container']['title']),
 131             'thumbnails': thumbnails,
 132         }
 133
 134
 135 class MxplayerShowIE(InfoExtractor):
 136     _VALID_URL = r'(?:https?://)(?:www\.)?mxplayer\.in/show/(?P<display_id>[-\w]+)-(?P<id>\w+)/?(?:$|[#?])'
 137     _TESTS = [{
 138         'url': 'https://www.mxplayer.in/show/watch-chakravartin-ashoka-samrat-series-online-a8f44e3cc0814b5601d17772cedf5417',
 139         'playlist_mincount': 440,
 140         'info_dict': {
 141             'id': 'a8f44e3cc0814b5601d17772cedf5417',
 142             'title': 'Watch Chakravartin Ashoka Samrat Series Online',
 143         }
 144     }]
 145
 146     _API_SHOW_URL = "https://api.mxplay.com/v1/web/detail/tab/tvshowseasons?type=tv_show&id={}&device-density=2&platform=com.mxplay.desktop&content-languages=hi,en"
 147     _API_EPISODES_URL = "https://api.mxplay.com/v1/web/detail/tab/tvshowepisodes?type=season&id={}&device-density=1&platform=com.mxplay.desktop&content-languages=hi,en&{}"
 148
 149     def _entries(self, show_id):
 150         show_json = self._download_json(
 151             self._API_SHOW_URL.format(show_id),
 152             video_id=show_id, headers={'Referer': 'https://mxplayer.in'})
 153         page_num = 0
 154         for season in show_json.get('items') or []:
 155             season_id = try_get(season, lambda x: x['id'], compat_str)
 156             next_url = ''
 157             while next_url is not None:
 158                 page_num += 1
 159                 season_json = self._download_json(
 160                     self._API_EPISODES_URL.format(season_id, next_url),
 161                     video_id=season_id,
 162                     headers={'Referer': 'https://mxplayer.in'},
 163                     note='Downloading JSON metadata page %d' % page_num)
 164                 for episode in season_json.get('items') or []:
 165                     video_url = episode['webUrl']
 166                     yield self.url_result(
 167                         'https://mxplayer.in%s' % video_url,
 168                         ie=MxplayerIE.ie_key(), video_id=video_url.split('-')[-1])
 169                 next_url = season_json.get('next')
 170
 171     def _real_extract(self, url):
 172         display_id, show_id = self._match_valid_url(url).groups()
 173         return self.playlist_result(
 174             self._entries(show_id), playlist_id=show_id,
 175             playlist_title=display_id.replace('-', ' ').title())