yt_dlp/extractor/tunein.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import ExtractorError
   5 from ..compat import compat_urlparse
   6
   7
   8 class TuneInBaseIE(InfoExtractor):
   9     _API_BASE_URL = 'http://tunein.com/tuner/tune/'
  10
  11     @staticmethod
  12     def _extract_urls(webpage):
  13         return re.findall(
  14             r'<iframe[^>]+src=["\'](?P<url>(?:https?://)?tunein\.com/embed/player/[pst]\d+)',
  15             webpage)
  16
  17     def _real_extract(self, url):
  18         content_id = self._match_id(url)
  19
  20         content_info = self._download_json(
  21             self._API_BASE_URL + self._API_URL_QUERY % content_id,
  22             content_id, note='Downloading JSON metadata')
  23
  24         title = content_info['Title']
  25         thumbnail = content_info.get('Logo')
  26         location = content_info.get('Location')
  27         streams_url = content_info.get('StreamUrl')
  28         if not streams_url:
  29             raise ExtractorError('No downloadable streams found', expected=True)
  30         if not streams_url.startswith('http://'):
  31             streams_url = compat_urlparse.urljoin(url, streams_url)
  32
  33         streams = self._download_json(
  34             streams_url, content_id, note='Downloading stream data',
  35             transform_source=lambda s: re.sub(r'^\s*\((.*)\);\s*$', r'\1', s))['Streams']
  36
  37         is_live = None
  38         formats = []
  39         for stream in streams:
  40             if stream.get('Type') == 'Live':
  41                 is_live = True
  42             reliability = stream.get('Reliability')
  43             format_note = (
  44                 'Reliability: %d%%' % reliability
  45                 if reliability is not None else None)
  46             formats.append({
  47                 'preference': (
  48                     0 if reliability is None or reliability > 90
  49                     else 1),
  50                 'abr': stream.get('Bandwidth'),
  51                 'ext': stream.get('MediaType').lower(),
  52                 'acodec': stream.get('MediaType'),
  53                 'vcodec': 'none',
  54                 'url': stream.get('Url'),
  55                 'source_preference': reliability,
  56                 'format_note': format_note,
  57             })
  58         self._sort_formats(formats)
  59
  60         return {
  61             'id': content_id,
  62             'title': title,
  63             'formats': formats,
  64             'thumbnail': thumbnail,
  65             'location': location,
  66             'is_live': is_live,
  67         }
  68
  69
  70 class TuneInClipIE(TuneInBaseIE):
  71     IE_NAME = 'tunein:clip'
  72     _VALID_URL = r'https?://(?:www\.)?tunein\.com/station/.*?audioClipId\=(?P<id>\d+)'
  73     _API_URL_QUERY = '?tuneType=AudioClip&audioclipId=%s'
  74
  75     _TESTS = [{
  76         'url': 'http://tunein.com/station/?stationId=246119&audioClipId=816',
  77         'md5': '99f00d772db70efc804385c6b47f4e77',
  78         'info_dict': {
  79             'id': '816',
  80             'title': '32m',
  81             'ext': 'mp3',
  82         },
  83     }]
  84
  85
  86 class TuneInStationIE(TuneInBaseIE):
  87     IE_NAME = 'tunein:station'
  88     _VALID_URL = r'https?://(?:www\.)?tunein\.com/(?:radio/.*?-s|station/.*?StationId=|embed/player/s)(?P<id>\d+)'
  89     _API_URL_QUERY = '?tuneType=Station&stationId=%s'
  90
  91     @classmethod
  92     def suitable(cls, url):
  93         return False if TuneInClipIE.suitable(url) else super(TuneInStationIE, cls).suitable(url)
  94
  95     _TESTS = [{
  96         'url': 'http://tunein.com/radio/Jazz24-885-s34682/',
  97         'info_dict': {
  98             'id': '34682',
  99             'title': 'Jazz 24 on 88.5 Jazz24 - KPLU-HD2',
 100             'ext': 'mp3',
 101             'location': 'Tacoma, WA',
 102         },
 103         'params': {
 104             'skip_download': True,  # live stream
 105         },
 106     }, {
 107         'url': 'http://tunein.com/embed/player/s6404/',
 108         'only_matching': True,
 109     }]
 110
 111
 112 class TuneInProgramIE(TuneInBaseIE):
 113     IE_NAME = 'tunein:program'
 114     _VALID_URL = r'https?://(?:www\.)?tunein\.com/(?:radio/.*?-p|program/.*?ProgramId=|embed/player/p)(?P<id>\d+)'
 115     _API_URL_QUERY = '?tuneType=Program&programId=%s'
 116
 117     _TESTS = [{
 118         'url': 'http://tunein.com/radio/Jazz-24-p2506/',
 119         'info_dict': {
 120             'id': '2506',
 121             'title': 'Jazz 24 on 91.3 WUKY-HD3',
 122             'ext': 'mp3',
 123             'location': 'Lexington, KY',
 124         },
 125         'params': {
 126             'skip_download': True,  # live stream
 127         },
 128     }, {
 129         'url': 'http://tunein.com/embed/player/p191660/',
 130         'only_matching': True,
 131     }]
 132
 133
 134 class TuneInTopicIE(TuneInBaseIE):
 135     IE_NAME = 'tunein:topic'
 136     _VALID_URL = r'https?://(?:www\.)?tunein\.com/(?:topic/.*?TopicId=|embed/player/t)(?P<id>\d+)'
 137     _API_URL_QUERY = '?tuneType=Topic&topicId=%s'
 138
 139     _TESTS = [{
 140         'url': 'http://tunein.com/topic/?TopicId=101830576',
 141         'md5': 'c31a39e6f988d188252eae7af0ef09c9',
 142         'info_dict': {
 143             'id': '101830576',
 144             'title': 'Votez pour moi du 29 octobre 2015 (29/10/15)',
 145             'ext': 'mp3',
 146             'location': 'Belgium',
 147         },
 148     }, {
 149         'url': 'http://tunein.com/embed/player/t101830576/',
 150         'only_matching': True,
 151     }]
 152
 153
 154 class TuneInShortenerIE(InfoExtractor):
 155     IE_NAME = 'tunein:shortener'
 156     IE_DESC = False  # Do not list
 157     _VALID_URL = r'https?://tun\.in/(?P<id>[A-Za-z0-9]+)'
 158
 159     _TEST = {
 160         # test redirection
 161         'url': 'http://tun.in/ser7s',
 162         'info_dict': {
 163             'id': '34682',
 164             'title': 'Jazz 24 on 88.5 Jazz24 - KPLU-HD2',
 165             'ext': 'mp3',
 166             'location': 'Tacoma, WA',
 167         },
 168         'params': {
 169             'skip_download': True,  # live stream
 170         },
 171     }
 172
 173     def _real_extract(self, url):
 174         redirect_id = self._match_id(url)
 175         # The server doesn't support HEAD requests
 176         urlh = self._request_webpage(
 177             url, redirect_id, note='Downloading redirect page')
 178         url = urlh.geturl()
 179         self.to_screen('Following redirect: %s' % url)
 180         return self.url_result(url)