yt_dlp/extractor/rtvs.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     parse_duration,
   6     traverse_obj,
   7     unified_timestamp,
   8 )
   9
  10
  11 class RTVSIE(InfoExtractor):
  12     _VALID_URL = r'https?://(?:www\.)?rtvs\.sk/(?:radio|televizia)/archiv(?:/\d+)?/(?P<id>\d+)/?(?:[#?]|$)'
  13     _TESTS = [{
  14         # radio archive
  15         'url': 'http://www.rtvs.sk/radio/archiv/11224/414872',
  16         'md5': '134d5d6debdeddf8a5d761cbc9edacb8',
  17         'info_dict': {
  18             'id': '414872',
  19             'ext': 'mp3',
  20             'title': 'Ostrov pokladov 1 časť.mp3',
  21             'duration': 2854,
  22             'thumbnail': 'https://www.rtvs.sk/media/a501/image/file/2/0000/b1R8.rtvs.jpg',
  23             'display_id': '135331',
  24         },
  25     }, {
  26         # tv archive
  27         'url': 'http://www.rtvs.sk/televizia/archiv/8249/63118',
  28         'info_dict': {
  29             'id': '63118',
  30             'ext': 'mp4',
  31             'title': 'Amaro Džives - Náš deň',
  32             'description': 'Galavečer pri príležitosti Medzinárodného dňa Rómov.',
  33             'thumbnail': 'https://www.rtvs.sk/media/a501/image/file/2/0031/L7Qm.amaro_dzives_png.jpg',
  34             'timestamp': 1428555900,
  35             'upload_date': '20150409',
  36             'duration': 4986,
  37         },
  38     }, {
  39         # tv archive
  40         'url': 'https://www.rtvs.sk/televizia/archiv/18083?utm_source=web&utm_medium=rozcestnik&utm_campaign=Robin',
  41         'info_dict': {
  42             'id': '18083',
  43             'ext': 'mp4',
  44             'title': 'Robin',
  45             'description': 'md5:2f70505a7b8364491003d65ff7a0940a',
  46             'timestamp': 1636652760,
  47             'display_id': '307655',
  48             'duration': 831,
  49             'upload_date': '20211111',
  50             'thumbnail': 'https://www.rtvs.sk/media/a501/image/file/2/0916/robin.jpg',
  51         },
  52     }]
  53
  54     def _real_extract(self, url):
  55         video_id = self._match_id(url)
  56
  57         webpage = self._download_webpage(url, video_id)
  58         iframe_id = self._search_regex(
  59             r'<iframe[^>]+id\s*=\s*"player_[^_]+_([0-9]+)"', webpage, 'Iframe ID')
  60         iframe_url = self._search_regex(
  61             fr'<iframe[^>]+id\s*=\s*"player_[^_]+_{re.escape(iframe_id)}"[^>]+src\s*=\s*"([^"]+)"', webpage, 'Iframe URL')
  62
  63         webpage = self._download_webpage(iframe_url, video_id, 'Downloading iframe')
  64         json_url = self._search_regex(r'var\s+url\s*=\s*"([^"]+)"\s*\+\s*ruurl', webpage, 'json URL')
  65         data = self._download_json(f'https:{json_url}b=mozilla&p=win&v=97&f=0&d=1', video_id)
  66
  67         if data.get('clip'):
  68             data['playlist'] = [data['clip']]
  69
  70         if traverse_obj(data, ('playlist', 0, 'sources', 0, 'type')) == 'audio/mp3':
  71             formats = [{'url': traverse_obj(data, ('playlist', 0, 'sources', 0, 'src'))}]
  72         else:
  73             formats = self._extract_m3u8_formats(traverse_obj(data, ('playlist', 0, 'sources', 0, 'src')), video_id)
  74
  75         return {
  76             'id': video_id,
  77             'display_id': iframe_id,
  78             'title': traverse_obj(data, ('playlist', 0, 'title')),
  79             'description': traverse_obj(data, ('playlist', 0, 'description')),
  80             'duration': parse_duration(traverse_obj(data, ('playlist', 0, 'length'))),
  81             'thumbnail': traverse_obj(data, ('playlist', 0, 'image')),
  82             'timestamp': unified_timestamp(traverse_obj(data, ('playlist', 0, 'datetime_create'))),
  83             'formats': formats,
  84         }