yt_dlp/extractor/puhutv.py

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