yt_dlp/extractor/lrt.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     clean_html,
   4     merge_dicts,
   5 )
   6
   7
   8 class LRTIE(InfoExtractor):
   9     IE_NAME = 'lrt.lt'
  10     _VALID_URL = r'https?://(?:www\.)?lrt\.lt(?P<path>/mediateka/irasas/(?P<id>[0-9]+))'
  11     _TESTS = [{
  12         # m3u8 download
  13         'url': 'https://www.lrt.lt/mediateka/irasas/2000127261/greita-ir-gardu-sicilijos-ikvepta-klasikiniu-makaronu-su-baklazanais-vakariene',
  14         'md5': '85cb2bb530f31d91a9c65b479516ade4',
  15         'info_dict': {
  16             'id': '2000127261',
  17             'ext': 'mp4',
  18             'title': 'Greita ir gardu: Sicilijos įkvėpta klasikinių makaronų su baklažanais vakarienė',
  19             'description': 'md5:ad7d985f51b0dc1489ba2d76d7ed47fa',
  20             'duration': 3035,
  21             'timestamp': 1604079000,
  22             'upload_date': '20201030',
  23         },
  24     }, {
  25         # direct mp3 download
  26         'url': 'http://www.lrt.lt/mediateka/irasas/1013074524/',
  27         'md5': '389da8ca3cad0f51d12bed0c844f6a0a',
  28         'info_dict': {
  29             'id': '1013074524',
  30             'ext': 'mp3',
  31             'title': 'Kita tema 2016-09-05 15:05',
  32             'description': 'md5:1b295a8fc7219ed0d543fc228c931fb5',
  33             'duration': 3008,
  34             'view_count': int,
  35             'like_count': int,
  36         },
  37     }]
  38
  39     def _extract_js_var(self, webpage, var_name, default):
  40         return self._search_regex(
  41             r'%s\s*=\s*(["\'])((?:(?!\1).)+)\1' % var_name,
  42             webpage, var_name.replace('_', ' '), default, group=2)
  43
  44     def _real_extract(self, url):
  45         path, video_id = self._match_valid_url(url).groups()
  46         webpage = self._download_webpage(url, video_id)
  47
  48         media_url = self._extract_js_var(webpage, 'main_url', path)
  49         media = self._download_json(self._extract_js_var(
  50             webpage, 'media_info_url',
  51             'https://www.lrt.lt/servisai/stream_url/vod/media_info/'),
  52             video_id, query={'url': media_url})
  53         jw_data = self._parse_jwplayer_data(
  54             media['playlist_item'], video_id, base_url=url)
  55
  56         json_ld_data = self._search_json_ld(webpage, video_id)
  57
  58         tags = []
  59         for tag in (media.get('tags') or []):
  60             tag_name = tag.get('name')
  61             if not tag_name:
  62                 continue
  63             tags.append(tag_name)
  64
  65         clean_info = {
  66             'description': clean_html(media.get('content')),
  67             'tags': tags,
  68         }
  69
  70         return merge_dicts(clean_info, jw_data, json_ld_data)