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

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