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': 'fbd8f2d8e7681f8bcd51b592475a6ae7',
  29         'info_dict': {
  30             'id': '5085',
  31             'display_id': 'sut-kardesler',
  32             'ext': 'mp4',
  33             'title': 'Süt Kardeşler',
  34             'description': 'md5:405fd024df916ca16731114eb18e511a',
  35             'thumbnail': r're:^https?://.*\.jpg$',
  36             'duration': 4832.44,
  37             'creator': 'Arzu Film',
  38             'timestamp': 1469778212,
  39             'upload_date': '20160729',
  40             'release_year': 1976,
  41             'view_count': int,
  42             'tags': ['Aile', 'Komedi', 'Klasikler'],
  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         title = info.get('name') or info['title']['name']
  68         if info.get('display_name'):
  69             title = '%s %s' % (title, info.get('display_name'))
  70
  71         try:
  72             videos = self._download_json(
  73                 'https://puhutv.com/api/assets/%s/videos' % video_id,
  74                 display_id, 'Downloading video JSON',
  75                 headers=self.geo_verification_headers())
  76         except ExtractorError as e:
  77             if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
  78                 self.raise_geo_restricted()
  79             raise
  80
  81         formats = []
  82         for video in videos['data']['videos']:
  83             media_url = url_or_none(video.get('url'))
  84             if not media_url:
  85                 continue
  86             playlist = video.get('is_playlist')
  87             if video.get('stream_type') == 'hls' and playlist is True:
  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             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             if video_format == 'hls' and playlist is False:
 100                 format_id = 'hls'
 101                 f['protocol'] = 'm3u8_native'
 102             elif video_format == 'mp4':
 103                 format_id = 'http'
 104
 105             else:
 106                 continue
 107             if quality:
 108                 format_id += '-%sp' % quality
 109             f['format_id'] = format_id
 110             formats.append(f)
 111         self._sort_formats(formats)
 112
 113         description = try_get(
 114             info, lambda x: x['title']['description'],
 115             compat_str) or info.get('description')
 116         timestamp = unified_timestamp(info.get('created_at'))
 117         creator = try_get(
 118             info, lambda x: x['title']['producer']['name'], compat_str)
 119
 120         duration = float_or_none(
 121             try_get(info, lambda x: x['content']['duration_in_ms'], int),
 122             scale=1000)
 123         view_count = try_get(info, lambda x: x['content']['watch_count'], int)
 124
 125         images = try_get(
 126             info, lambda x: x['content']['images']['wide'], dict) or {}
 127         thumbnails = []
 128         for image_id, image_url in images.items():
 129             if not isinstance(image_url, compat_str):
 130                 continue
 131             if not image_url.startswith(('http', '//')):
 132                 image_url = 'https://%s' % image_url
 133             t = parse_resolution(image_id)
 134             t.update({
 135                 'id': image_id,
 136                 'url': image_url
 137             })
 138             thumbnails.append(t)
 139
 140         release_year = try_get(info, lambda x: x['title']['released_at'], int)
 141
 142         season_number = int_or_none(info.get('season_number'))
 143         season_id = str_or_none(info.get('season_id'))
 144         episode_number = int_or_none(info.get('episode_number'))
 145
 146         tags = []
 147         for genre in try_get(info, lambda x: x['title']['genres'], list) or []:
 148             if not isinstance(genre, dict):
 149                 continue
 150             genre_name = genre.get('name')
 151             if genre_name and isinstance(genre_name, compat_str):
 152                 tags.append(genre_name)
 153
 154         subtitles = {}
 155         for subtitle in try_get(
 156                 info, lambda x: x['content']['subtitles'], list) or []:
 157             if not isinstance(subtitle, dict):
 158                 continue
 159             lang = subtitle.get('language')
 160             sub_url = url_or_none(subtitle.get('url'))
 161             if not lang or not isinstance(lang, compat_str) or not sub_url:
 162                 continue
 163             subtitles[self._SUBTITLE_LANGS.get(lang, lang)] = [{
 164                 'url': sub_url
 165             }]
 166
 167         return {
 168             'id': video_id,
 169             'display_id': display_id,
 170             'title': title,
 171             'description': description,
 172             'season_id': season_id,
 173             'season_number': season_number,
 174             'episode_number': episode_number,
 175             'release_year': release_year,
 176             'timestamp': timestamp,
 177             'creator': creator,
 178             'view_count': view_count,
 179             'duration': duration,
 180             'tags': tags,
 181             'subtitles': subtitles,
 182             'thumbnails': thumbnails,
 183             'formats': formats
 184         }
 185
 186
 187 class PuhuTVSerieIE(InfoExtractor):
 188     _VALID_URL = r'https?://(?:www\.)?puhutv\.com/(?P<id>[^/?#&]+)-detay'
 189     IE_NAME = 'puhutv:serie'
 190     _TESTS = [{
 191         'url': 'https://puhutv.com/deniz-yildizi-detay',
 192         'info_dict': {
 193             'title': 'Deniz Yıldızı',
 194             'id': 'deniz-yildizi',
 195         },
 196         'playlist_mincount': 205,
 197     }, {
 198         # a film detail page which is using same url with serie page
 199         'url': 'https://puhutv.com/kaybedenler-kulubu-detay',
 200         'only_matching': True,
 201     }]
 202
 203     def _extract_entries(self, seasons):
 204         for season in seasons:
 205             season_id = season.get('id')
 206             if not season_id:
 207                 continue
 208             page = 1
 209             has_more = True
 210             while has_more is True:
 211                 season = self._download_json(
 212                     'https://galadriel.puhutv.com/seasons/%s' % season_id,
 213                     season_id, 'Downloading page %s' % page, query={
 214                         'page': page,
 215                         'per': 40,
 216                     })
 217                 episodes = season.get('episodes')
 218                 if isinstance(episodes, list):
 219                     for ep in episodes:
 220                         slug_path = str_or_none(ep.get('slugPath'))
 221                         if not slug_path:
 222                             continue
 223                         video_id = str_or_none(int_or_none(ep.get('id')))
 224                         yield self.url_result(
 225                             'https://puhutv.com/%s' % slug_path,
 226                             ie=PuhuTVIE.ie_key(), video_id=video_id,
 227                             video_title=ep.get('name') or ep.get('eventLabel'))
 228                 page += 1
 229                 has_more = season.get('hasMore')
 230
 231     def _real_extract(self, url):
 232         playlist_id = self._match_id(url)
 233
 234         info = self._download_json(
 235             urljoin(url, '/api/slug/%s-detay' % playlist_id),
 236             playlist_id)['data']
 237
 238         seasons = info.get('seasons')
 239         if seasons:
 240             return self.playlist_result(
 241                 self._extract_entries(seasons), playlist_id, info.get('name'))
 242
 243         # For films, these are using same url with series
 244         video_id = info.get('slug') or info['assets'][0]['slug']
 245         return self.url_result(
 246             'https://puhutv.com/%s-izle' % video_id,
 247             PuhuTVIE.ie_key(), video_id)