yt_dlp/extractor/rtvs.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7
   8 from ..utils import (
   9     parse_duration,
  10     traverse_obj,
  11     unified_timestamp,
  12 )
  13
  14
  15 class RTVSIE(InfoExtractor):
  16     _VALID_URL = r'https?://(?:www\.)?rtvs\.sk/(?:radio|televizia)/archiv(?:/\d+)?/(?P<id>\d+)/?(?:[#?]|$)'
  17     _TESTS = [{
  18         # radio archive
  19         'url': 'http://www.rtvs.sk/radio/archiv/11224/414872',
  20         'md5': '134d5d6debdeddf8a5d761cbc9edacb8',
  21         'info_dict': {
  22             'id': '414872',
  23             'ext': 'mp3',
  24             'title': 'Ostrov pokladov 1 časť.mp3',
  25             'duration': 2854,
  26             'thumbnail': 'https://www.rtvs.sk/media/a501/image/file/2/0000/b1R8.rtvs.jpg',
  27             'display_id': '135331',
  28         }
  29     }, {
  30         # tv archive
  31         'url': 'http://www.rtvs.sk/televizia/archiv/8249/63118',
  32         'info_dict': {
  33             'id': '63118',
  34             'ext': 'mp4',
  35             'title': 'Amaro Džives - Náš deň',
  36             'description': 'Galavečer pri príležitosti Medzinárodného dňa Rómov.',
  37             'thumbnail': 'https://www.rtvs.sk/media/a501/image/file/2/0031/L7Qm.amaro_dzives_png.jpg',
  38             'timestamp': 1428555900,
  39             'upload_date': '20150409',
  40             'duration': 4986,
  41         }
  42     }, {
  43         # tv archive
  44         'url': 'https://www.rtvs.sk/televizia/archiv/18083?utm_source=web&utm_medium=rozcestnik&utm_campaign=Robin',
  45         'info_dict': {
  46             'id': '18083',
  47             'ext': 'mp4',
  48             'title': 'Robin',
  49             'description': 'md5:2f70505a7b8364491003d65ff7a0940a',
  50             'timestamp': 1636652760,
  51             'display_id': '307655',
  52             'duration': 831,
  53             'upload_date': '20211111',
  54             'thumbnail': 'https://www.rtvs.sk/media/a501/image/file/2/0916/robin.jpg',
  55         }
  56     }]
  57
  58     def _real_extract(self, url):
  59         video_id = self._match_id(url)
  60
  61         webpage = self._download_webpage(url, video_id)
  62         iframe_id = self._search_regex(
  63             r'<iframe[^>]+id\s*=\s*"player_[^_]+_([0-9]+)"', webpage, 'Iframe ID')
  64         iframe_url = self._search_regex(
  65             fr'<iframe[^>]+id\s*=\s*"player_[^_]+_{re.escape(iframe_id)}"[^>]+src\s*=\s*"([^"]+)"', webpage, 'Iframe URL')
  66
  67         webpage = self._download_webpage(iframe_url, video_id, 'Downloading iframe')
  68         json_url = self._search_regex(r'var\s+url\s*=\s*"([^"]+)"\s*\+\s*ruurl', webpage, 'json URL')
  69         data = self._download_json(f'https:{json_url}b=mozilla&p=win&v=97&f=0&d=1', video_id)
  70
  71         if data.get('clip'):
  72             data['playlist'] = [data['clip']]
  73
  74         if traverse_obj(data, ('playlist', 0, 'sources', 0, 'type')) == 'audio/mp3':
  75             formats = [{'url': traverse_obj(data, ('playlist', 0, 'sources', 0, 'src'))}]
  76         else:
  77             formats = self._extract_m3u8_formats(traverse_obj(data, ('playlist', 0, 'sources', 0, 'src')), video_id)
  78         self._sort_formats(formats)
  79
  80         return {
  81             'id': video_id,
  82             'display_id': iframe_id,
  83             'title': traverse_obj(data, ('playlist', 0, 'title')),
  84             'description': traverse_obj(data, ('playlist', 0, 'description')),
  85             'duration': parse_duration(traverse_obj(data, ('playlist', 0, 'length'))),
  86             'thumbnail': traverse_obj(data, ('playlist', 0, 'image')),
  87             'timestamp': unified_timestamp(traverse_obj(data, ('playlist', 0, 'datetime_create'))),
  88             'formats': formats
  89         }