yt_dlp/extractor/lrt.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     clean_html,
   8     merge_dicts,
   9 )
  10
  11
  12 class LRTIE(InfoExtractor):
  13     IE_NAME = 'lrt.lt'
  14     _VALID_URL = r'https?://(?:www\.)?lrt\.lt(?P<path>/mediateka/irasas/(?P<id>[0-9]+))'
  15     _TESTS = [{
  16         # m3u8 download
  17         'url': 'https://www.lrt.lt/mediateka/irasas/2000127261/greita-ir-gardu-sicilijos-ikvepta-klasikiniu-makaronu-su-baklazanais-vakariene',
  18         'md5': '85cb2bb530f31d91a9c65b479516ade4',
  19         'info_dict': {
  20             'id': '2000127261',
  21             'ext': 'mp4',
  22             'title': 'Greita ir gardu: Sicilijos įkvėpta klasikinių makaronų su baklažanais vakarienė',
  23             'description': 'md5:ad7d985f51b0dc1489ba2d76d7ed47fa',
  24             'duration': 3035,
  25             'timestamp': 1604079000,
  26             'upload_date': '20201030',
  27         },
  28     }, {
  29         # direct mp3 download
  30         'url': 'http://www.lrt.lt/mediateka/irasas/1013074524/',
  31         'md5': '389da8ca3cad0f51d12bed0c844f6a0a',
  32         'info_dict': {
  33             'id': '1013074524',
  34             'ext': 'mp3',
  35             'title': 'Kita tema 2016-09-05 15:05',
  36             'description': 'md5:1b295a8fc7219ed0d543fc228c931fb5',
  37             'duration': 3008,
  38             'view_count': int,
  39             'like_count': int,
  40         },
  41     }]
  42
  43     def _extract_js_var(self, webpage, var_name, default):
  44         return self._search_regex(
  45             r'%s\s*=\s*(["\'])((?:(?!\1).)+)\1' % var_name,
  46             webpage, var_name.replace('_', ' '), default, group=2)
  47
  48     def _real_extract(self, url):
  49         path, video_id = self._match_valid_url(url).groups()
  50         webpage = self._download_webpage(url, video_id)
  51
  52         media_url = self._extract_js_var(webpage, 'main_url', path)
  53         media = self._download_json(self._extract_js_var(
  54             webpage, 'media_info_url',
  55             'https://www.lrt.lt/servisai/stream_url/vod/media_info/'),
  56             video_id, query={'url': media_url})
  57         jw_data = self._parse_jwplayer_data(
  58             media['playlist_item'], video_id, base_url=url)
  59
  60         json_ld_data = self._search_json_ld(webpage, video_id)
  61
  62         tags = []
  63         for tag in (media.get('tags') or []):
  64             tag_name = tag.get('name')
  65             if not tag_name:
  66                 continue
  67             tags.append(tag_name)
  68
  69         clean_info = {
  70             'description': clean_html(media.get('content')),
  71             'tags': tags,
  72         }
  73
  74         return merge_dicts(clean_info, jw_data, json_ld_data)