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
  53         return {
  54             'id': content_id,
  55             'title': title,
  56             'formats': formats,
  57             'thumbnail': thumbnail,
  58             'location': location,
  59             'is_live': is_live,
  60         }
  61
  62
  63 class TuneInClipIE(TuneInBaseIE):
  64     IE_NAME = 'tunein:clip'
  65     _VALID_URL = r'https?://(?:www\.)?tunein\.com/station/.*?audioClipId\=(?P<id>\d+)'
  66     _API_URL_QUERY = '?tuneType=AudioClip&audioclipId=%s'
  67
  68     _TESTS = [{
  69         'url': 'http://tunein.com/station/?stationId=246119&audioClipId=816',
  70         'md5': '99f00d772db70efc804385c6b47f4e77',
  71         'info_dict': {
  72             'id': '816',
  73             'title': '32m',
  74             'ext': 'mp3',
  75         },
  76     }]
  77
  78
  79 class TuneInStationIE(TuneInBaseIE):
  80     IE_NAME = 'tunein:station'
  81     _VALID_URL = r'https?://(?:www\.)?tunein\.com/(?:radio/.*?-s|station/.*?StationId=|embed/player/s)(?P<id>\d+)'
  82     _EMBED_REGEX = [r'<iframe[^>]+src=["\'](?P<url>(?:https?://)?tunein\.com/embed/player/[pst]\d+)']
  83     _API_URL_QUERY = '?tuneType=Station&stationId=%s'
  84
  85     @classmethod
  86     def suitable(cls, url):
  87         return False if TuneInClipIE.suitable(url) else super(TuneInStationIE, cls).suitable(url)
  88
  89     _TESTS = [{
  90         'url': 'http://tunein.com/radio/Jazz24-885-s34682/',
  91         'info_dict': {
  92             'id': '34682',
  93             'title': 'Jazz 24 on 88.5 Jazz24 - KPLU-HD2',
  94             'ext': 'mp3',
  95             'location': 'Tacoma, WA',
  96         },
  97         'params': {
  98             'skip_download': True,  # live stream
  99         },
 100     }, {
 101         'url': 'http://tunein.com/embed/player/s6404/',
 102         'only_matching': True,
 103     }]
 104
 105
 106 class TuneInProgramIE(TuneInBaseIE):
 107     IE_NAME = 'tunein:program'
 108     _VALID_URL = r'https?://(?:www\.)?tunein\.com/(?:radio/.*?-p|program/.*?ProgramId=|embed/player/p)(?P<id>\d+)'
 109     _API_URL_QUERY = '?tuneType=Program&programId=%s'
 110
 111     _TESTS = [{
 112         'url': 'http://tunein.com/radio/Jazz-24-p2506/',
 113         'info_dict': {
 114             'id': '2506',
 115             'title': 'Jazz 24 on 91.3 WUKY-HD3',
 116             'ext': 'mp3',
 117             'location': 'Lexington, KY',
 118         },
 119         'params': {
 120             'skip_download': True,  # live stream
 121         },
 122     }, {
 123         'url': 'http://tunein.com/embed/player/p191660/',
 124         'only_matching': True,
 125     }]
 126
 127
 128 class TuneInTopicIE(TuneInBaseIE):
 129     IE_NAME = 'tunein:topic'
 130     _VALID_URL = r'https?://(?:www\.)?tunein\.com/(?:topic/.*?TopicId=|embed/player/t)(?P<id>\d+)'
 131     _API_URL_QUERY = '?tuneType=Topic&topicId=%s'
 132
 133     _TESTS = [{
 134         'url': 'http://tunein.com/topic/?TopicId=101830576',
 135         'md5': 'c31a39e6f988d188252eae7af0ef09c9',
 136         'info_dict': {
 137             'id': '101830576',
 138             'title': 'Votez pour moi du 29 octobre 2015 (29/10/15)',
 139             'ext': 'mp3',
 140             'location': 'Belgium',
 141         },
 142     }, {
 143         'url': 'http://tunein.com/embed/player/t101830576/',
 144         'only_matching': True,
 145     }]
 146
 147
 148 class TuneInShortenerIE(InfoExtractor):
 149     IE_NAME = 'tunein:shortener'
 150     IE_DESC = False  # Do not list
 151     _VALID_URL = r'https?://tun\.in/(?P<id>[A-Za-z0-9]+)'
 152
 153     _TEST = {
 154         # test redirection
 155         'url': 'http://tun.in/ser7s',
 156         'info_dict': {
 157             'id': '34682',
 158             'title': 'Jazz 24 on 88.5 Jazz24 - KPLU-HD2',
 159             'ext': 'mp3',
 160             'location': 'Tacoma, WA',
 161         },
 162         'params': {
 163             'skip_download': True,  # live stream
 164         },
 165     }
 166
 167     def _real_extract(self, url):
 168         redirect_id = self._match_id(url)
 169         # The server doesn't support HEAD requests
 170         urlh = self._request_webpage(
 171             url, redirect_id, note='Downloading redirect page')
 172         url = urlh.geturl()
 173         self.to_screen('Following redirect: %s' % url)
 174         return self.url_result(url)