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