yt_dlp/extractor/rtnews.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import js_to_json
   5
   6
   7 class RTNewsIE(InfoExtractor):
   8     _VALID_URL = r'https?://(?:www\.)?rt\.com/[^/]+/(?:[^/]+/)?(?P<id>\d+)'
   9
  10     _TESTS = [{
  11         'url': 'https://www.rt.com/sport/546301-djokovic-arrives-belgrade-crowds/',
  12         'playlist_mincount': 2,
  13         'info_dict': {
  14             'id': '546301',
  15             'title': 'Crowds gather to greet deported Djokovic as he returns to Serbia (VIDEO)',
  16             'description': 'md5:1d5bfe1a988d81fd74227cfdf93d314d',
  17             'thumbnail': 'https://cdni.rt.com/files/2022.01/article/61e587a085f540102c3386c1.png',
  18         },
  19     }, {
  20         'url': 'https://www.rt.com/shows/in-question/535980-plot-to-assassinate-julian-assange/',
  21         'playlist_mincount': 1,
  22         'info_dict': {
  23             'id': '535980',
  24             'title': 'The plot to assassinate Julian Assange',
  25             'description': 'md5:55279ce5e4441dc1d16e2e4a730152cd',
  26             'thumbnail': 'https://cdni.rt.com/files/2021.09/article/615226f42030274e8879b53d.png',
  27         },
  28         'playlist': [{
  29             'info_dict': {
  30                 'id': '6152271d85f5400464496162',
  31                 'ext': 'mp4',
  32                 'title': '6152271d85f5400464496162',
  33             },
  34         }],
  35     }]
  36
  37     def _entries(self, webpage):
  38         video_urls = set(re.findall(r'https://cdnv\.rt\.com/.*[a-f0-9]+\.mp4', webpage))
  39         for v_url in video_urls:
  40             v_id = re.search(r'([a-f0-9]+)\.mp4', v_url).group(1)
  41             if v_id:
  42                 yield {
  43                     'id': v_id,
  44                     'title': v_id,
  45                     'url': v_url,
  46                 }
  47
  48     def _real_extract(self, url):
  49         playlist_id = self._match_id(url)
  50         webpage = self._download_webpage(url, playlist_id)
  51
  52         return {
  53             '_type': 'playlist',
  54             'id': playlist_id,
  55             'entries': self._entries(webpage),
  56             'title': self._og_search_title(webpage),
  57             'description': self._og_search_description(webpage),
  58             'thumbnail': self._og_search_thumbnail(webpage),
  59         }
  60
  61
  62 class RTDocumentryIE(InfoExtractor):
  63     _VALID_URL = r'https?://rtd\.rt\.com/(?:(?:series|shows)/[^/]+|films)/(?P<id>[^/?$&#]+)'
  64
  65     _TESTS = [{
  66         'url': 'https://rtd.rt.com/films/escobars-hitman/',
  67         'info_dict': {
  68             'id': 'escobars-hitman',
  69             'ext': 'mp4',
  70             'title': "Escobar's Hitman. Former drug-gang killer, now loved and loathed in Colombia",
  71             'description': 'md5:647c76984b7cb9a8b52a567e87448d88',
  72             'thumbnail': 'https://cdni.rt.com/rtd-files/films/escobars-hitman/escobars-hitman_11.jpg',
  73             'average_rating': 8.53,
  74             'duration': 3134.0,
  75         },
  76         'params': {'skip_download': True},
  77     }, {
  78         'url': 'https://rtd.rt.com/shows/the-kalashnikova-show-military-secrets-anna-knishenko/iskander-tactical-system-natos-headache/',
  79         'info_dict': {
  80             'id': 'iskander-tactical-system-natos-headache',
  81             'ext': 'mp4',
  82             'title': "Iskander tactical system. NATO's headache | The Kalashnikova Show. Episode 10",
  83             'description': 'md5:da7c24a0aa67bc2bb88c86658508ca87',
  84             'thumbnail': 'md5:89de8ce38c710b7c501ff02d47e2aa89',
  85             'average_rating': 9.27,
  86             'duration': 274.0,
  87             'timestamp': 1605726000,
  88             'view_count': int,
  89             'upload_date': '20201118',
  90         },
  91         'params': {'skip_download': True},
  92     }, {
  93         'url': 'https://rtd.rt.com/series/i-am-hacked-trailer/introduction-to-safe-digital-life-ep2/',
  94         'info_dict': {
  95             'id': 'introduction-to-safe-digital-life-ep2',
  96             'ext': 'mp4',
  97             'title': 'How to Keep your Money away from Hackers | I am Hacked. Episode 2',
  98             'description': 'md5:c46fa9a5af86c0008c45a3940a8cce87',
  99             'thumbnail': 'md5:a5e81b9bf5aed8f5e23d9c053601b825',
 100             'average_rating': 10.0,
 101             'duration': 1524.0,
 102             'timestamp': 1636977600,
 103             'view_count': int,
 104             'upload_date': '20211115',
 105         },
 106         'params': {'skip_download': True},
 107     }]
 108
 109     def _real_extract(self, url):
 110         video_id = self._match_id(url)
 111         webpage = self._download_webpage(url, video_id)
 112         ld_json = self._search_json_ld(webpage, None, fatal=False)
 113         if not ld_json:
 114             self.raise_no_formats('No video/audio found at the provided url.', expected=True)
 115         media_json = self._parse_json(
 116             self._search_regex(r'(?s)\'Med\'\s*:\s*\[\s*({.+})\s*\]\s*};', webpage, 'media info'),
 117             video_id, transform_source=js_to_json)
 118         if 'title' not in ld_json and 'title' in media_json:
 119             ld_json['title'] = media_json['title']
 120         formats = [{'url': src['file']} for src in media_json.get('sources') or [] if src.get('file')]
 121
 122         return {
 123             'id': video_id,
 124             'thumbnail': media_json.get('image'),
 125             'formats': formats,
 126             **ld_json,
 127         }
 128
 129
 130 class RTDocumentryPlaylistIE(InfoExtractor):
 131     _VALID_URL = r'https?://rtd\.rt\.com/(?:series|shows)/(?P<id>[^/]+)/$'
 132
 133     _TESTS = [{
 134         'url': 'https://rtd.rt.com/series/i-am-hacked-trailer/',
 135         'playlist_mincount': 6,
 136         'info_dict': {
 137             'id': 'i-am-hacked-trailer',
 138         },
 139     }, {
 140         'url': 'https://rtd.rt.com/shows/the-kalashnikova-show-military-secrets-anna-knishenko/',
 141         'playlist_mincount': 34,
 142         'info_dict': {
 143             'id': 'the-kalashnikova-show-military-secrets-anna-knishenko',
 144         },
 145     }]
 146
 147     def _entries(self, webpage, playlist_id):
 148         video_urls = set(re.findall(r'list-2__link\s*"\s*href="([^"]+)"', webpage))
 149         for v_url in video_urls:
 150             if playlist_id not in v_url:
 151                 continue
 152             yield self.url_result(
 153                 f'https://rtd.rt.com{v_url}',
 154                 ie=RTDocumentryIE.ie_key())
 155
 156     def _real_extract(self, url):
 157         playlist_id = self._match_id(url)
 158         webpage = self._download_webpage(url, playlist_id)
 159
 160         return {
 161             '_type': 'playlist',
 162             'id': playlist_id,
 163             'entries': self._entries(webpage, playlist_id),
 164         }
 165
 166
 167 class RuptlyIE(InfoExtractor):
 168     _VALID_URL = r'https?://(?:www\.)?ruptly\.tv/[a-z]{2}/videos/(?P<id>\d+-\d+)'
 169
 170     _TESTS = [{
 171         'url': 'https://www.ruptly.tv/en/videos/20220112-020-Japan-Double-trouble-Tokyo-zoo-presents-adorable-panda-twins',
 172         'info_dict': {
 173             'id': '20220112-020',
 174             'ext': 'mp4',
 175             'title': 'Japan: Double trouble! Tokyo zoo presents adorable panda twins | Video Ruptly',
 176             'description': 'md5:85a8da5fdb31486f0562daf4360ce75a',
 177             'thumbnail': 'https://storage.ruptly.tv/thumbnails/20220112-020/i6JQKnTNpYuqaXsR/i6JQKnTNpYuqaXsR.jpg',
 178         },
 179         'params': {'skip_download': True},
 180     }]
 181
 182     def _real_extract(self, url):
 183         video_id = self._match_id(url)
 184         webpage = self._download_webpage(url, video_id)
 185         m3u8_url = self._search_regex(r'preview_url"\s?:\s?"(https?://storage\.ruptly\.tv/video_projects/.+\.m3u8)"', webpage, 'm3u8 url', fatal=False)
 186         if not m3u8_url:
 187             self.raise_no_formats('No video/audio found at the provided url.', expected=True)
 188         formats, subs = self._extract_m3u8_formats_and_subtitles(m3u8_url, video_id, ext='mp4')
 189         return {
 190             'id': video_id,
 191             'formats': formats,
 192             'subtitles': subs,
 193             'title': self._og_search_title(webpage),
 194             'description': self._og_search_description(webpage),
 195             'thumbnail': self._og_search_thumbnail(webpage),
 196         }