Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/sverigesradio.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     determine_ext,
   7     int_or_none,
   8     str_or_none,
   9 )
  10
  11
  12 class SverigesRadioBaseIE(InfoExtractor):
  13     _BASE_URL = 'https://sverigesradio.se/sida/playerajax/'
  14     _QUALITIES = ['low', 'medium', 'high']
  15     _EXT_TO_CODEC_MAP = {
  16         'mp3': 'mp3',
  17         'm4a': 'aac',
  18     }
  19     _CODING_FORMAT_TO_ABR_MAP = {
  20         5: 128,
  21         11: 192,
  22         12: 32,
  23         13: 96,
  24     }
  25
  26     def _real_extract(self, url):
  27         audio_id = self._match_id(url)
  28         query = {
  29             'id': audio_id,
  30             'type': self._AUDIO_TYPE,
  31         }
  32
  33         item = self._download_json(
  34             self._BASE_URL + 'audiometadata', audio_id,
  35             'Downloading audio JSON metadata', query=query)['items'][0]
  36         title = item['subtitle']
  37
  38         query['format'] = 'iis'
  39         urls = []
  40         formats = []
  41         for quality in self._QUALITIES:
  42             query['quality'] = quality
  43             audio_url_data = self._download_json(
  44                 self._BASE_URL + 'getaudiourl', audio_id,
  45                 'Downloading %s format JSON metadata' % quality,
  46                 fatal=False, query=query) or {}
  47             audio_url = audio_url_data.get('audioUrl')
  48             if not audio_url or audio_url in urls:
  49                 continue
  50             urls.append(audio_url)
  51             ext = determine_ext(audio_url)
  52             coding_format = audio_url_data.get('codingFormat')
  53             abr = int_or_none(self._search_regex(
  54                 r'_a(\d+)\.m4a', audio_url, 'audio bitrate',
  55                 default=None)) or self._CODING_FORMAT_TO_ABR_MAP.get(coding_format)
  56             formats.append({
  57                 'abr': abr,
  58                 'acodec': self._EXT_TO_CODEC_MAP.get(ext),
  59                 'ext': ext,
  60                 'format_id': str_or_none(coding_format),
  61                 'vcodec': 'none',
  62                 'url': audio_url,
  63             })
  64         self._sort_formats(formats)
  65
  66         return {
  67             'id': audio_id,
  68             'title': title,
  69             'formats': formats,
  70             'series': item.get('title'),
  71             'duration': int_or_none(item.get('duration')),
  72             'thumbnail': item.get('displayimageurl'),
  73             'description': item.get('description'),
  74         }
  75
  76
  77 class SverigesRadioPublicationIE(SverigesRadioBaseIE):
  78     IE_NAME = 'sverigesradio:publication'
  79     _VALID_URL = r'https?://(?:www\.)?sverigesradio\.se/sida/(?:artikel|gruppsida)\.aspx\?.*?\bartikel=(?P<id>[0-9]+)'
  80     _TESTS = [{
  81         'url': 'https://sverigesradio.se/sida/artikel.aspx?programid=83&artikel=7038546',
  82         'md5': '6a4917e1923fccb080e5a206a5afa542',
  83         'info_dict': {
  84             'id': '7038546',
  85             'ext': 'm4a',
  86             'duration': 132,
  87             'series': 'Nyheter (Ekot)',
  88             'title': 'Esa Teittinen: Sanningen har inte kommit fram',
  89             'description': 'md5:daf7ce66a8f0a53d5465a5984d3839df',
  90             'thumbnail': r're:^https?://.*\.jpg',
  91         },
  92     }, {
  93         'url': 'https://sverigesradio.se/sida/gruppsida.aspx?programid=3304&grupp=6247&artikel=7146887',
  94         'only_matching': True,
  95     }]
  96     _AUDIO_TYPE = 'publication'
  97
  98
  99 class SverigesRadioEpisodeIE(SverigesRadioBaseIE):
 100     IE_NAME = 'sverigesradio:episode'
 101     _VALID_URL = r'https?://(?:www\.)?sverigesradio\.se/(?:sida/)?avsnitt/(?P<id>[0-9]+)'
 102     _TEST = {
 103         'url': 'https://sverigesradio.se/avsnitt/1140922?programid=1300',
 104         'md5': '20dc4d8db24228f846be390b0c59a07c',
 105         'info_dict': {
 106             'id': '1140922',
 107             'ext': 'mp3',
 108             'duration': 3307,
 109             'series': 'Konflikt',
 110             'title': 'Metoo och valen',
 111             'description': 'md5:fcb5c1f667f00badcc702b196f10a27e',
 112             'thumbnail': r're:^https?://.*\.jpg',
 113         }
 114     }
 115     _AUDIO_TYPE = 'episode'