youtube_dl/extractor/puhutv.py

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