yt_dlp/extractor/puhutv.py

   1 from .common import InfoExtractor
   2 from ..compat import (
   3     compat_HTTPError,
   4     compat_str,
   5 )
   6 from ..utils import (
   7     ExtractorError,
   8     int_or_none,
   9     float_or_none,
  10     parse_resolution,
  11     str_or_none,
  12     try_get,
  13     unified_timestamp,
  14     url_or_none,
  15     urljoin,
  16 )
  17
  18
  19 class PuhuTVIE(InfoExtractor):
  20     _VALID_URL = r'https?://(?:www\.)?puhutv\.com/(?P<id>[^/?#&]+)-izle'
  21     IE_NAME = 'puhutv'
  22     _TESTS = [{
  23         # film
  24         'url': 'https://puhutv.com/sut-kardesler-izle',
  25         'md5': 'a347470371d56e1585d1b2c8dab01c96',
  26         'info_dict': {
  27             'id': '5085',
  28             'display_id': 'sut-kardesler',
  29             'ext': 'mp4',
  30             'title': 'Süt Kardeşler',
  31             'description': 'md5:ca09da25b7e57cbb5a9280d6e48d17aa',
  32             'thumbnail': r're:^https?://.*\.jpg$',
  33             'duration': 4832.44,
  34             'creator': 'Arzu Film',
  35             'timestamp': 1561062602,
  36             'upload_date': '20190620',
  37             'release_year': 1976,
  38             'view_count': int,
  39             'tags': list,
  40         },
  41     }, {
  42         # episode, geo restricted, bypassable with --geo-verification-proxy
  43         'url': 'https://puhutv.com/jet-sosyete-1-bolum-izle',
  44         'only_matching': True,
  45     }, {
  46         # 4k, with subtitles
  47         'url': 'https://puhutv.com/dip-1-bolum-izle',
  48         'only_matching': True,
  49     }]
  50     _SUBTITLE_LANGS = {
  51         'English': 'en',
  52         'Deutsch': 'de',
  53         'عربى': 'ar'
  54     }
  55
  56     def _real_extract(self, url):
  57         display_id = self._match_id(url)
  58
  59         info = self._download_json(
  60             urljoin(url, '/api/slug/%s-izle' % display_id),
  61             display_id)['data']
  62
  63         video_id = compat_str(info['id'])
  64         show = info.get('title') or {}
  65         title = info.get('name') or show['name']
  66         if info.get('display_name'):
  67             title = '%s %s' % (title, info['display_name'])
  68
  69         try:
  70             videos = self._download_json(
  71                 'https://puhutv.com/api/assets/%s/videos' % video_id,
  72                 display_id, 'Downloading video JSON',
  73                 headers=self.geo_verification_headers())
  74         except ExtractorError as e:
  75             if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
  76                 self.raise_geo_restricted()
  77             raise
  78
  79         urls = []
  80         formats = []
  81
  82         for video in videos['data']['videos']:
  83             media_url = url_or_none(video.get('url'))
  84             if not media_url or media_url in urls:
  85                 continue
  86             urls.append(media_url)
  87
  88             playlist = video.get('is_playlist')
  89             if (video.get('stream_type') == 'hls' and playlist is True) or 'playlist.m3u8' in media_url:
  90                 formats.extend(self._extract_m3u8_formats(
  91                     media_url, video_id, 'mp4', entry_protocol='m3u8_native',
  92                     m3u8_id='hls', fatal=False))
  93                 continue
  94
  95             quality = int_or_none(video.get('quality'))
  96             f = {
  97                 'url': media_url,
  98                 'ext': 'mp4',
  99                 'height': quality
 100             }
 101             video_format = video.get('video_format')
 102             is_hls = (video_format == 'hls' or '/hls/' in media_url or '/chunklist.m3u8' in media_url) and playlist is False
 103             if is_hls:
 104                 format_id = 'hls'
 105                 f['protocol'] = 'm3u8_native'
 106             elif video_format == 'mp4':
 107                 format_id = 'http'
 108             else:
 109                 continue
 110             if quality:
 111                 format_id += '-%sp' % quality
 112             f['format_id'] = format_id
 113             formats.append(f)
 114         self._sort_formats(formats)
 115
 116         creator = try_get(
 117             show, lambda x: x['producer']['name'], compat_str)
 118
 119         content = info.get('content') or {}
 120
 121         images = try_get(
 122             content, lambda x: x['images']['wide'], dict) or {}
 123         thumbnails = []
 124         for image_id, image_url in images.items():
 125             if not isinstance(image_url, compat_str):
 126                 continue
 127             if not image_url.startswith(('http', '//')):
 128                 image_url = 'https://%s' % image_url
 129             t = parse_resolution(image_id)
 130             t.update({
 131                 'id': image_id,
 132                 'url': image_url
 133             })
 134             thumbnails.append(t)
 135
 136         tags = []
 137         for genre in show.get('genres') or []:
 138             if not isinstance(genre, dict):
 139                 continue
 140             genre_name = genre.get('name')
 141             if genre_name and isinstance(genre_name, compat_str):
 142                 tags.append(genre_name)
 143
 144         subtitles = {}
 145         for subtitle in content.get('subtitles') or []:
 146             if not isinstance(subtitle, dict):
 147                 continue
 148             lang = subtitle.get('language')
 149             sub_url = url_or_none(subtitle.get('url') or subtitle.get('file'))
 150             if not lang or not isinstance(lang, compat_str) or not sub_url:
 151                 continue
 152             subtitles[self._SUBTITLE_LANGS.get(lang, lang)] = [{
 153                 'url': sub_url
 154             }]
 155
 156         return {
 157             'id': video_id,
 158             'display_id': display_id,
 159             'title': title,
 160             'description': info.get('description') or show.get('description'),
 161             'season_id': str_or_none(info.get('season_id')),
 162             'season_number': int_or_none(info.get('season_number')),
 163             'episode_number': int_or_none(info.get('episode_number')),
 164             'release_year': int_or_none(show.get('released_at')),
 165             'timestamp': unified_timestamp(info.get('created_at')),
 166             'creator': creator,
 167             'view_count': int_or_none(content.get('watch_count')),
 168             'duration': float_or_none(content.get('duration_in_ms'), 1000),
 169             'tags': tags,
 170             'subtitles': subtitles,
 171             'thumbnails': thumbnails,
 172             'formats': formats
 173         }
 174
 175
 176 class PuhuTVSerieIE(InfoExtractor):
 177     _VALID_URL = r'https?://(?:www\.)?puhutv\.com/(?P<id>[^/?#&]+)-detay'
 178     IE_NAME = 'puhutv:serie'
 179     _TESTS = [{
 180         'url': 'https://puhutv.com/deniz-yildizi-detay',
 181         'info_dict': {
 182             'title': 'Deniz Yıldızı',
 183             'id': 'deniz-yildizi',
 184         },
 185         'playlist_mincount': 205,
 186     }, {
 187         # a film detail page which is using same url with serie page
 188         'url': 'https://puhutv.com/kaybedenler-kulubu-detay',
 189         'only_matching': True,
 190     }]
 191
 192     def _extract_entries(self, seasons):
 193         for season in seasons:
 194             season_id = season.get('id')
 195             if not season_id:
 196                 continue
 197             page = 1
 198             has_more = True
 199             while has_more is True:
 200                 season = self._download_json(
 201                     'https://galadriel.puhutv.com/seasons/%s' % season_id,
 202                     season_id, 'Downloading page %s' % page, query={
 203                         'page': page,
 204                         'per': 40,
 205                     })
 206                 episodes = season.get('episodes')
 207                 if isinstance(episodes, list):
 208                     for ep in episodes:
 209                         slug_path = str_or_none(ep.get('slugPath'))
 210                         if not slug_path:
 211                             continue
 212                         video_id = str_or_none(int_or_none(ep.get('id')))
 213                         yield self.url_result(
 214                             'https://puhutv.com/%s' % slug_path,
 215                             ie=PuhuTVIE.ie_key(), video_id=video_id,
 216                             video_title=ep.get('name') or ep.get('eventLabel'))
 217                 page += 1
 218                 has_more = season.get('hasMore')
 219
 220     def _real_extract(self, url):
 221         playlist_id = self._match_id(url)
 222
 223         info = self._download_json(
 224             urljoin(url, '/api/slug/%s-detay' % playlist_id),
 225             playlist_id)['data']
 226
 227         seasons = info.get('seasons')
 228         if seasons:
 229             return self.playlist_result(
 230                 self._extract_entries(seasons), playlist_id, info.get('name'))
 231
 232         # For films, these are using same url with series
 233         video_id = info.get('slug') or info['assets'][0]['slug']
 234         return self.url_result(
 235             'https://puhutv.com/%s-izle' % video_id,
 236             PuhuTVIE.ie_key(), video_id)