yt_dlp/extractor/puhutv.py

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