yt_dlp/extractor/lnkgo.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     clean_html,
   4     format_field,
   5     int_or_none,
   6     parse_iso8601,
   7     unified_strdate,
   8 )
   9
  10
  11 class LnkGoIE(InfoExtractor):
  12     _VALID_URL = r'https?://(?:www\.)?lnk(?:go)?\.(?:alfa\.)?lt/(?:visi-video/[^/]+|video)/(?P<id>[A-Za-z0-9-]+)(?:/(?P<episode_id>\d+))?'
  13     _TESTS = [{
  14         'url': 'http://www.lnkgo.lt/visi-video/aktualai-pratesimas/ziurek-putka-trys-klausimai',
  15         'info_dict': {
  16             'id': '10809',
  17             'ext': 'mp4',
  18             'title': "Put'ka: Trys Klausimai",
  19             'upload_date': '20161216',
  20             'description': 'Seniai matytas Put’ka užduoda tris klausimėlius. Pabandykime surasti atsakymus.',
  21             'age_limit': 18,
  22             'duration': 117,
  23             'thumbnail': r're:^https?://.*\.jpg$',
  24             'timestamp': 1481904000,
  25         },
  26         'params': {
  27             'skip_download': True,  # HLS download
  28         },
  29     }, {
  30         'url': 'http://lnkgo.alfa.lt/visi-video/aktualai-pratesimas/ziurek-nerdas-taiso-kompiuteri-2',
  31         'info_dict': {
  32             'id': '10467',
  33             'ext': 'mp4',
  34             'title': 'Nėrdas: Kompiuterio Valymas',
  35             'upload_date': '20150113',
  36             'description': 'md5:7352d113a242a808676ff17e69db6a69',
  37             'age_limit': 18,
  38             'duration': 346,
  39             'thumbnail': r're:^https?://.*\.jpg$',
  40             'timestamp': 1421164800,
  41         },
  42         'params': {
  43             'skip_download': True,  # HLS download
  44         },
  45     }, {
  46         'url': 'https://lnk.lt/video/neigalieji-tv-bokste/37413',
  47         'only_matching': True,
  48     }]
  49     _AGE_LIMITS = {
  50         'N-7': 7,
  51         'N-14': 14,
  52         'S': 18,
  53     }
  54     _M3U8_TEMPL = 'https://vod.lnk.lt/lnk_vod/lnk/lnk/%s:%s/playlist.m3u8%s'
  55
  56     def _real_extract(self, url):
  57         display_id, video_id = self._match_valid_url(url).groups()
  58
  59         video_info = self._download_json(
  60             'https://lnk.lt/api/main/video-page/{}/{}/false'.format(display_id, video_id or '0'),
  61             display_id)['videoConfig']['videoInfo']
  62
  63         video_id = str(video_info['id'])
  64         title = video_info['title']
  65         prefix = 'smil' if video_info.get('isQualityChangeAvailable') else 'mp4'
  66         formats = self._extract_m3u8_formats(
  67             self._M3U8_TEMPL % (prefix, video_info['videoUrl'], video_info.get('secureTokenParams') or ''),
  68             video_id, 'mp4', 'm3u8_native')
  69
  70         return {
  71             'id': video_id,
  72             'display_id': display_id,
  73             'title': title,
  74             'formats': formats,
  75             'thumbnail': format_field(video_info, 'posterImage', 'https://lnk.lt/all-images/%s'),
  76             'duration': int_or_none(video_info.get('duration')),
  77             'description': clean_html(video_info.get('htmlDescription')),
  78             'age_limit': self._AGE_LIMITS.get(video_info.get('pgRating'), 0),
  79             'timestamp': parse_iso8601(video_info.get('airDate')),
  80             'view_count': int_or_none(video_info.get('viewsCount')),
  81         }
  82
  83
  84 class LnkIE(InfoExtractor):
  85     _VALID_URL = r'https?://(?:www\.)?lnk\.lt/[^/]+/(?P<id>\d+)'
  86
  87     _TESTS = [{
  88         'url': 'https://lnk.lt/zinios/79791',
  89         'info_dict': {
  90             'id': '79791',
  91             'ext': 'mp4',
  92             'title': 'LNK.lt: Viešintų gyventojai sukilo prieš radijo bangų siųstuvą',
  93             'description': 'Svarbiausios naujienos trumpai, LNK žinios ir Info dienos pokalbiai.',
  94             'view_count': int,
  95             'duration': 233,
  96             'upload_date': '20191123',
  97             'thumbnail': r're:^https?://.*\.jpg$',
  98             'episode_number': 13431,
  99             'series': 'Naujausi žinių reportažai',
 100             'episode': 'Episode 13431',
 101         },
 102         'params': {'skip_download': True},
 103     }, {
 104         'url': 'https://lnk.lt/istorijos-trumpai/152546',
 105         'info_dict': {
 106             'id': '152546',
 107             'ext': 'mp4',
 108             'title': 'Radžio koncertas gaisre ',
 109             'description': 'md5:0666b5b85cb9fc7c1238dec96f71faba',
 110             'view_count': int,
 111             'duration': 54,
 112             'upload_date': '20220105',
 113             'thumbnail': r're:^https?://.*\.jpg$',
 114             'episode_number': 1036,
 115             'series': 'Istorijos trumpai',
 116             'episode': 'Episode 1036',
 117         },
 118         'params': {'skip_download': True},
 119     }, {
 120         'url': 'https://lnk.lt/gyvunu-pasaulis/151549',
 121         'info_dict': {
 122             'id': '151549',
 123             'ext': 'mp4',
 124             'title': 'Gyvūnų pasaulis',
 125             'description': '',
 126             'view_count': int,
 127             'duration': 1264,
 128             'upload_date': '20220108',
 129             'thumbnail': r're:^https?://.*\.jpg$',
 130             'episode_number': 16,
 131             'series': 'Gyvūnų pasaulis',
 132             'episode': 'Episode 16',
 133         },
 134         'params': {'skip_download': True},
 135     }]
 136
 137     def _real_extract(self, url):
 138         video_id = self._match_id(url)
 139         video_json = self._download_json(f'https://lnk.lt/api/video/video-config/{video_id}', video_id)['videoInfo']
 140         formats, subtitles = [], {}
 141         if video_json.get('videoUrl'):
 142             fmts, subs = self._extract_m3u8_formats_and_subtitles(video_json['videoUrl'], video_id)
 143             formats.extend(fmts)
 144             subtitles = self._merge_subtitles(subtitles, subs)
 145         if video_json.get('videoFairplayUrl') and not video_json.get('drm'):
 146             fmts, subs = self._extract_m3u8_formats_and_subtitles(video_json['videoFairplayUrl'], video_id)
 147             formats.extend(fmts)
 148             subtitles = self._merge_subtitles(subtitles, subs)
 149
 150         return {
 151             'id': video_id,
 152             'title': video_json.get('title'),
 153             'description': video_json.get('description'),
 154             'view_count': video_json.get('viewsCount'),
 155             'duration': video_json.get('duration'),
 156             'upload_date': unified_strdate(video_json.get('airDate')),
 157             'thumbnail': format_field(video_json, 'posterImage', 'https://lnk.lt/all-images/%s'),
 158             'episode_number': int_or_none(video_json.get('episodeNumber')),
 159             'series': video_json.get('programTitle'),
 160             'formats': formats,
 161             'subtitles': subtitles,
 162         }