youtube_dl/extractor/lrt.py

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