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
 115         creator = try_get(
 116             show, lambda x: x['producer']['name'], compat_str)
 117
 118         content = info.get('content') or {}
 119
 120         images = try_get(
 121             content, lambda x: x['images']['wide'], dict) or {}
 122         thumbnails = []
 123         for image_id, image_url in images.items():
 124             if not isinstance(image_url, compat_str):
 125                 continue
 126             if not image_url.startswith(('http', '//')):
 127                 image_url = 'https://%s' % image_url
 128             t = parse_resolution(image_id)
 129             t.update({
 130                 'id': image_id,
 131                 'url': image_url
 132             })
 133             thumbnails.append(t)
 134
 135         tags = []
 136         for genre in show.get('genres') or []:
 137             if not isinstance(genre, dict):
 138                 continue
 139             genre_name = genre.get('name')
 140             if genre_name and isinstance(genre_name, compat_str):
 141                 tags.append(genre_name)
 142
 143         subtitles = {}
 144         for subtitle in content.get('subtitles') or []:
 145             if not isinstance(subtitle, dict):
 146                 continue
 147             lang = subtitle.get('language')
 148             sub_url = url_or_none(subtitle.get('url') or subtitle.get('file'))
 149             if not lang or not isinstance(lang, compat_str) or not sub_url:
 150                 continue
 151             subtitles[self._SUBTITLE_LANGS.get(lang, lang)] = [{
 152                 'url': sub_url
 153             }]
 154
 155         return {
 156             'id': video_id,
 157             'display_id': display_id,
 158             'title': title,
 159             'description': info.get('description') or show.get('description'),
 160             'season_id': str_or_none(info.get('season_id')),
 161             'season_number': int_or_none(info.get('season_number')),
 162             'episode_number': int_or_none(info.get('episode_number')),
 163             'release_year': int_or_none(show.get('released_at')),
 164             'timestamp': unified_timestamp(info.get('created_at')),
 165             'creator': creator,
 166             'view_count': int_or_none(content.get('watch_count')),
 167             'duration': float_or_none(content.get('duration_in_ms'), 1000),
 168             'tags': tags,
 169             'subtitles': subtitles,
 170             'thumbnails': thumbnails,
 171             'formats': formats
 172         }
 173
 174
 175 class PuhuTVSerieIE(InfoExtractor):
 176     _VALID_URL = r'https?://(?:www\.)?puhutv\.com/(?P<id>[^/?#&]+)-detay'
 177     IE_NAME = 'puhutv:serie'
 178     _TESTS = [{
 179         'url': 'https://puhutv.com/deniz-yildizi-detay',
 180         'info_dict': {
 181             'title': 'Deniz Yıldızı',
 182             'id': 'deniz-yildizi',
 183         },
 184         'playlist_mincount': 205,
 185     }, {
 186         # a film detail page which is using same url with serie page
 187         'url': 'https://puhutv.com/kaybedenler-kulubu-detay',
 188         'only_matching': True,
 189     }]
 190
 191     def _extract_entries(self, seasons):
 192         for season in seasons:
 193             season_id = season.get('id')
 194             if not season_id:
 195                 continue
 196             page = 1
 197             has_more = True
 198             while has_more is True:
 199                 season = self._download_json(
 200                     'https://galadriel.puhutv.com/seasons/%s' % season_id,
 201                     season_id, 'Downloading page %s' % page, query={
 202                         'page': page,
 203                         'per': 40,
 204                     })
 205                 episodes = season.get('episodes')
 206                 if isinstance(episodes, list):
 207                     for ep in episodes:
 208                         slug_path = str_or_none(ep.get('slugPath'))
 209                         if not slug_path:
 210                             continue
 211                         video_id = str_or_none(int_or_none(ep.get('id')))
 212                         yield self.url_result(
 213                             'https://puhutv.com/%s' % slug_path,
 214                             ie=PuhuTVIE.ie_key(), video_id=video_id,
 215                             video_title=ep.get('name') or ep.get('eventLabel'))
 216                 page += 1
 217                 has_more = season.get('hasMore')
 218
 219     def _real_extract(self, url):
 220         playlist_id = self._match_id(url)
 221
 222         info = self._download_json(
 223             urljoin(url, '/api/slug/%s-detay' % playlist_id),
 224             playlist_id)['data']
 225
 226         seasons = info.get('seasons')
 227         if seasons:
 228             return self.playlist_result(
 229                 self._extract_entries(seasons), playlist_id, info.get('name'))
 230
 231         # For films, these are using same url with series
 232         video_id = info.get('slug') or info['assets'][0]['slug']
 233         return self.url_result(
 234             'https://puhutv.com/%s-izle' % video_id,
 235             PuhuTVIE.ie_key(), video_id)