yt_dlp/extractor/ertgr.py

   1 import json
   2 import re
   3
   4 from .common import InfoExtractor
   5 from ..compat import compat_str
   6 from ..utils import (
   7     clean_html,
   8     determine_ext,
   9     ExtractorError,
  10     dict_get,
  11     int_or_none,
  12     merge_dicts,
  13     parse_qs,
  14     parse_age_limit,
  15     parse_iso8601,
  16     str_or_none,
  17     try_get,
  18     url_or_none,
  19     variadic,
  20 )
  21
  22
  23 class ERTFlixBaseIE(InfoExtractor):
  24     def _call_api(
  25             self, video_id, method='Player/AcquireContent', api_version=1,
  26             param_headers=None, data=None, headers=None, **params):
  27         platform_codename = {'platformCodename': 'www'}
  28         headers_as_param = {'X-Api-Date-Format': 'iso', 'X-Api-Camel-Case': False}
  29         headers_as_param.update(param_headers or {})
  30         headers = headers or {}
  31         if data:
  32             headers['Content-Type'] = headers_as_param['Content-Type'] = 'application/json;charset=utf-8'
  33             data = json.dumps(merge_dicts(platform_codename, data)).encode('utf-8')
  34         query = merge_dicts(
  35             {} if data else platform_codename,
  36             {'$headers': json.dumps(headers_as_param)},
  37             params)
  38         response = self._download_json(
  39             'https://api.app.ertflix.gr/v%s/%s' % (str(api_version), method),
  40             video_id, fatal=False, query=query, data=data, headers=headers)
  41         if try_get(response, lambda x: x['Result']['Success']) is True:
  42             return response
  43
  44     def _call_api_get_tiles(self, video_id, *tile_ids):
  45         requested_tile_ids = [video_id] + list(tile_ids)
  46         requested_tiles = [{'Id': tile_id} for tile_id in requested_tile_ids]
  47         tiles_response = self._call_api(
  48             video_id, method='Tile/GetTiles', api_version=2,
  49             data={'RequestedTiles': requested_tiles})
  50         tiles = try_get(tiles_response, lambda x: x['Tiles'], list) or []
  51         if tile_ids:
  52             if sorted([tile['Id'] for tile in tiles]) != sorted(requested_tile_ids):
  53                 raise ExtractorError('Requested tiles not found', video_id=video_id)
  54             return tiles
  55         try:
  56             return next(tile for tile in tiles if tile['Id'] == video_id)
  57         except StopIteration:
  58             raise ExtractorError('No matching tile found', video_id=video_id)
  59
  60
  61 class ERTFlixCodenameIE(ERTFlixBaseIE):
  62     IE_NAME = 'ertflix:codename'
  63     IE_DESC = 'ERTFLIX videos by codename'
  64     _VALID_URL = r'ertflix:(?P<id>[\w-]+)'
  65     _TESTS = [{
  66         'url': 'ertflix:monogramma-praxitelis-tzanoylinos',
  67         'md5': '5b9c2cd171f09126167e4082fc1dd0ef',
  68         'info_dict': {
  69             'id': 'monogramma-praxitelis-tzanoylinos',
  70             'ext': 'mp4',
  71             'title': 'md5:ef0b439902963d56c43ac83c3f41dd0e',
  72         },
  73     },
  74     ]
  75
  76     def _extract_formats_and_subs(self, video_id):
  77         media_info = self._call_api(video_id, codename=video_id)
  78         formats, subs = [], {}
  79         for media_file in try_get(media_info, lambda x: x['MediaFiles'], list) or []:
  80             for media in try_get(media_file, lambda x: x['Formats'], list) or []:
  81                 fmt_url = url_or_none(try_get(media, lambda x: x['Url']))
  82                 if not fmt_url:
  83                     continue
  84                 ext = determine_ext(fmt_url)
  85                 if ext == 'm3u8':
  86                     formats_, subs_ = self._extract_m3u8_formats_and_subtitles(
  87                         fmt_url, video_id, m3u8_id='hls', ext='mp4', fatal=False)
  88                 elif ext == 'mpd':
  89                     formats_, subs_ = self._extract_mpd_formats_and_subtitles(
  90                         fmt_url, video_id, mpd_id='dash', fatal=False)
  91                 else:
  92                     formats.append({
  93                         'url': fmt_url,
  94                         'format_id': str_or_none(media.get('Id')),
  95                     })
  96                     continue
  97                 formats.extend(formats_)
  98                 self._merge_subtitles(subs_, target=subs)
  99
 100         return formats, subs
 101
 102     def _real_extract(self, url):
 103         video_id = self._match_id(url)
 104
 105         formats, subs = self._extract_formats_and_subs(video_id)
 106
 107         if formats:
 108             return {
 109                 'id': video_id,
 110                 'formats': formats,
 111                 'subtitles': subs,
 112                 'title': self._generic_title(url),
 113             }
 114
 115
 116 class ERTFlixIE(ERTFlixBaseIE):
 117     IE_NAME = 'ertflix'
 118     IE_DESC = 'ERTFLIX videos'
 119     _VALID_URL = r'https?://www\.ertflix\.gr/(?:[^/]+/)?(?:series|vod)/(?P<id>[a-z]{3}\.\d+)'
 120     _TESTS = [{
 121         'url': 'https://www.ertflix.gr/vod/vod.173258-aoratoi-ergates',
 122         'md5': '6479d5e60fd7e520b07ba5411dcdd6e7',
 123         'info_dict': {
 124             'id': 'aoratoi-ergates',
 125             'ext': 'mp4',
 126             'title': 'md5:c1433d598fbba0211b0069021517f8b4',
 127             'description': 'md5:01a64d113c31957eb7eb07719ab18ff4',
 128             'thumbnail': r're:https?://.+\.jpg',
 129             'episode_id': 'vod.173258',
 130             'timestamp': 1639648800,
 131             'upload_date': '20211216',
 132             'duration': 3166,
 133             'age_limit': 8,
 134         },
 135     }, {
 136         'url': 'https://www.ertflix.gr/series/ser.3448-monogramma',
 137         'info_dict': {
 138             'id': 'ser.3448',
 139             'age_limit': 8,
 140             'description': 'Η εκπομπή σαράντα ετών που σημάδεψε τον πολιτισμό μας.',
 141             'title': 'Μονόγραμμα',
 142         },
 143         'playlist_mincount': 64,
 144     }, {
 145         'url': 'https://www.ertflix.gr/series/ser.3448-monogramma?season=1',
 146         'info_dict': {
 147             'id': 'ser.3448',
 148             'age_limit': 8,
 149             'description': 'Η εκπομπή σαράντα ετών που σημάδεψε τον πολιτισμό μας.',
 150             'title': 'Μονόγραμμα',
 151         },
 152         'playlist_count': 22,
 153     }, {
 154         'url': 'https://www.ertflix.gr/series/ser.3448-monogramma?season=1&season=2021%20-%202022',
 155         'info_dict': {
 156             'id': 'ser.3448',
 157             'age_limit': 8,
 158             'description': 'Η εκπομπή σαράντα ετών που σημάδεψε τον πολιτισμό μας.',
 159             'title': 'Μονόγραμμα',
 160         },
 161         'playlist_mincount': 36,
 162     }, {
 163         'url': 'https://www.ertflix.gr/series/ser.164991-to-diktuo-1?season=1-9',
 164         'info_dict': {
 165             'id': 'ser.164991',
 166             'age_limit': 8,
 167             'description': 'Η πρώτη ελληνική εκπομπή με θεματολογία αποκλειστικά γύρω από το ίντερνετ.',
 168             'title': 'Το δίκτυο',
 169         },
 170         'playlist_mincount': 9,
 171     }, {
 172         'url': 'https://www.ertflix.gr/en/vod/vod.127652-ta-kalytera-mas-chronia-ep1-mia-volta-sto-feggari',
 173         'only_matching': True,
 174     }]
 175
 176     def _extract_episode(self, episode):
 177         codename = try_get(episode, lambda x: x['Codename'], compat_str)
 178         title = episode.get('Title')
 179         description = clean_html(dict_get(episode, ('ShortDescription', 'TinyDescription', )))
 180         if not codename or not title or not episode.get('HasPlayableStream', True):
 181             return
 182         thumbnail = next((
 183             url_or_none(thumb.get('Url'))
 184             for thumb in variadic(dict_get(episode, ('Images', 'Image')) or {})
 185             if thumb.get('IsMain')),
 186             None)
 187         return {
 188             '_type': 'url_transparent',
 189             'thumbnail': thumbnail,
 190             'id': codename,
 191             'episode_id': episode.get('Id'),
 192             'title': title,
 193             'alt_title': episode.get('Subtitle'),
 194             'description': description,
 195             'timestamp': parse_iso8601(episode.get('PublishDate')),
 196             'duration': episode.get('DurationSeconds'),
 197             'age_limit': self._parse_age_rating(episode),
 198             'url': 'ertflix:%s' % (codename, ),
 199         }
 200
 201     @staticmethod
 202     def _parse_age_rating(info_dict):
 203         return parse_age_limit(
 204             info_dict.get('AgeRating')
 205             or (info_dict.get('IsAdultContent') and 18)
 206             or (info_dict.get('IsKidsContent') and 0))
 207
 208     def _extract_series(self, video_id, season_titles=None, season_numbers=None):
 209         media_info = self._call_api(video_id, method='Tile/GetSeriesDetails', id=video_id)
 210
 211         series = try_get(media_info, lambda x: x['Series'], dict) or {}
 212         series_info = {
 213             'age_limit': self._parse_age_rating(series),
 214             'title': series.get('Title'),
 215             'description': dict_get(series, ('ShortDescription', 'TinyDescription', )),
 216         }
 217         if season_numbers:
 218             season_titles = season_titles or []
 219             for season in try_get(series, lambda x: x['Seasons'], list) or []:
 220                 if season.get('SeasonNumber') in season_numbers and season.get('Title'):
 221                     season_titles.append(season['Title'])
 222
 223         def gen_episode(m_info, season_titles):
 224             for episode_group in try_get(m_info, lambda x: x['EpisodeGroups'], list) or []:
 225                 if season_titles and episode_group.get('Title') not in season_titles:
 226                     continue
 227                 episodes = try_get(episode_group, lambda x: x['Episodes'], list)
 228                 if not episodes:
 229                     continue
 230                 season_info = {
 231                     'season': episode_group.get('Title'),
 232                     'season_number': int_or_none(episode_group.get('SeasonNumber')),
 233                 }
 234                 try:
 235                     episodes = [(int(ep['EpisodeNumber']), ep) for ep in episodes]
 236                     episodes.sort()
 237                 except (KeyError, ValueError):
 238                     episodes = enumerate(episodes, 1)
 239                 for n, episode in episodes:
 240                     info = self._extract_episode(episode)
 241                     if info is None:
 242                         continue
 243                     info['episode_number'] = n
 244                     info.update(season_info)
 245                     yield info
 246
 247         return self.playlist_result(
 248             gen_episode(media_info, season_titles), playlist_id=video_id, **series_info)
 249
 250     def _real_extract(self, url):
 251         video_id = self._match_id(url)
 252         if video_id.startswith('ser.'):
 253             param_season = parse_qs(url).get('season', [None])
 254             param_season = [
 255                 (have_number, int_or_none(v) if have_number else str_or_none(v))
 256                 for have_number, v in
 257                 [(int_or_none(ps) is not None, ps) for ps in param_season]
 258                 if v is not None
 259             ]
 260             season_kwargs = {
 261                 k: [v for is_num, v in param_season if is_num is c] or None
 262                 for k, c in
 263                 [('season_titles', False), ('season_numbers', True)]
 264             }
 265             return self._extract_series(video_id, **season_kwargs)
 266
 267         return self._extract_episode(self._call_api_get_tiles(video_id))
 268
 269
 270 class ERTWebtvEmbedIE(InfoExtractor):
 271     IE_NAME = 'ertwebtv:embed'
 272     IE_DESC = 'ert.gr webtv embedded videos'
 273     _BASE_PLAYER_URL_RE = re.escape('//www.ert.gr/webtv/live-uni/vod/dt-uni-vod.php')
 274     _VALID_URL = rf'https?:{_BASE_PLAYER_URL_RE}\?([^#]+&)?f=(?P<id>[^#&]+)'
 275     _EMBED_REGEX = [rf'<iframe[^>]+?src=(?P<_q1>["\'])(?P<url>(?:https?:)?{_BASE_PLAYER_URL_RE}\?(?:(?!(?P=_q1)).)+)(?P=_q1)']
 276
 277     _TESTS = [{
 278         'url': 'https://www.ert.gr/webtv/live-uni/vod/dt-uni-vod.php?f=trailers/E2251_TO_DIKTYO_E09_16-01_1900.mp4&bgimg=/photos/2022/1/to_diktio_ep09_i_istoria_tou_diadiktiou_stin_Ellada_1021x576.jpg',
 279         'md5': 'f9e9900c25c26f4ecfbddbb4b6305854',
 280         'info_dict': {
 281             'id': 'trailers/E2251_TO_DIKTYO_E09_16-01_1900.mp4',
 282             'title': 'md5:914f06a73cd8b62fbcd6fb90c636e497',
 283             'ext': 'mp4',
 284             'thumbnail': 'https://program.ert.gr/photos/2022/1/to_diktio_ep09_i_istoria_tou_diadiktiou_stin_Ellada_1021x576.jpg'
 285         },
 286     }]
 287
 288     def _real_extract(self, url):
 289         video_id = self._match_id(url)
 290         formats, subs = self._extract_m3u8_formats_and_subtitles(
 291             f'https://mediastream.ert.gr/vodedge/_definst_/mp4:dvrorigin/{video_id}/playlist.m3u8',
 292             video_id, 'mp4')
 293         thumbnail_id = parse_qs(url).get('bgimg', [None])[0]
 294         if thumbnail_id and not thumbnail_id.startswith('http'):
 295             thumbnail_id = f'https://program.ert.gr{thumbnail_id}'
 296         return {
 297             'id': video_id,
 298             'title': f'VOD - {video_id}',
 299             'thumbnail': thumbnail_id,
 300             'formats': formats,
 301             'subtitles': subs,
 302         }