_ Git - youtube-dl/blob - youtube_dl/extractor/mixcloud.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..compat import (
   7     compat_urllib_parse,
   8 )
   9 from ..utils import (
  10     ExtractorError,
  11     HEADRequest,
  12     str_to_int,
  13     parse_iso8601,
  14 )
  15
  16
  17 class MixcloudIE(InfoExtractor):
  18     _VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/([^/]+)/([^/]+)'
  19     IE_NAME = 'mixcloud'
  20
  21     _TESTS = [{
  22         'url': 'http://www.mixcloud.com/dholbach/cryptkeeper/',
  23         'info_dict': {
  24             'id': 'dholbach-cryptkeeper',
  25             'ext': 'mp3',
  26             'title': 'Cryptkeeper',
  27             'description': 'After quite a long silence from myself, finally another Drum\'n\'Bass mix with my favourite current dance floor bangers.',
  28             'uploader': 'Daniel Holbach',
  29             'uploader_id': 'dholbach',
  30             'upload_date': '20111115',
  31             'timestamp': 1321359578,
  32             'thumbnail': 're:https?://.*\.jpg',
  33             'view_count': int,
  34             'like_count': int,
  35         },
  36     }, {
  37         'url': 'http://www.mixcloud.com/gillespeterson/caribou-7-inch-vinyl-mix-chat/',
  38         'info_dict': {
  39             'id': 'gillespeterson-caribou-7-inch-vinyl-mix-chat',
  40             'ext': 'm4a',
  41             'title': 'Electric Relaxation vol. 3',
  42             'description': 'md5:2b8aec6adce69f9d41724647c65875e8',
  43             'uploader': 'Daniel Drumz',
  44             'uploader_id': 'gillespeterson',
  45             'thumbnail': 're:https?://.*\.jpg',
  46             'view_count': int,
  47             'like_count': int,
  48         },
  49     }]
  50
  51     def _get_url(self, track_id, template_url):
  52         server_count = 30
  53         for i in range(server_count):
  54             url = template_url % i
  55             try:
  56                 # We only want to know if the request succeed
  57                 # don't download the whole file
  58                 self._request_webpage(
  59                     HEADRequest(url), track_id,
  60                     'Checking URL %d/%d ...' % (i + 1, server_count + 1))
  61                 return url
  62             except ExtractorError:
  63                 pass
  64
  65         return None
  66
  67     def _real_extract(self, url):
  68         mobj = re.match(self._VALID_URL, url)
  69         uploader = mobj.group(1)
  70         cloudcast_name = mobj.group(2)
  71         track_id = compat_urllib_parse.unquote('-'.join((uploader, cloudcast_name)))
  72
  73         webpage = self._download_webpage(url, track_id)
  74
  75         preview_url = self._search_regex(
  76             r'\s(?:data-preview-url|m-preview)="([^"]+)"', webpage, 'preview url')
  77         song_url = preview_url.replace('/previews/', '/c/originals/')
  78         template_url = re.sub(r'(stream\d*)', 'stream%d', song_url)
  79         final_song_url = self._get_url(track_id, template_url)
  80         if final_song_url is None:
  81             self.to_screen('Trying with m4a extension')
  82             template_url = template_url.replace('.mp3', '.m4a').replace('originals/', 'm4a/64/')
  83             final_song_url = self._get_url(track_id, template_url)
  84         if final_song_url is None:
  85             raise ExtractorError('Unable to extract track url')
  86
  87         PREFIX = (
  88             r'<span class="play-button[^"]*?"'
  89             r'(?:\s+[a-zA-Z0-9-]+(?:="[^"]+")?)*?\s+')
  90         title = self._html_search_regex(
  91             PREFIX + r'm-title="([^"]+)"', webpage, 'title')
  92         thumbnail = self._proto_relative_url(self._html_search_regex(
  93             PREFIX + r'm-thumbnail-url="([^"]+)"', webpage, 'thumbnail',
  94             fatal=False))
  95         uploader = self._html_search_regex(
  96             PREFIX + r'm-owner-name="([^"]+)"',
  97             webpage, 'uploader', fatal=False)
  98         uploader_id = self._search_regex(
  99             r'\s+"profile": "([^"]+)",', webpage, 'uploader id', fatal=False)
 100         description = self._og_search_description(webpage)
 101         like_count = str_to_int(self._search_regex(
 102             [r'<meta itemprop="interactionCount" content="UserLikes:([0-9]+)"',
 103              r'/favorites/?">([0-9]+)<'],
 104             webpage, 'like count', fatal=False))
 105         view_count = str_to_int(self._search_regex(
 106             [r'<meta itemprop="interactionCount" content="UserPlays:([0-9]+)"',
 107              r'/listeners/?">([0-9,.]+)</a>'],
 108             webpage, 'play count', fatal=False))
 109         timestamp = parse_iso8601(self._search_regex(
 110             r'<time itemprop="dateCreated" datetime="([^"]+)">',
 111             webpage, 'upload date', default=None))
 112
 113         return {
 114             'id': track_id,
 115             'title': title,
 116             'url': final_song_url,
 117             'description': description,
 118             'thumbnail': thumbnail,
 119             'uploader': uploader,
 120             'uploader_id': uploader_id,
 121             'timestamp': timestamp,
 122             'view_count': view_count,
 123             'like_count': like_count,
 124         }