_ 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 compat_urllib_parse_unquote
   7 from ..utils import (
   8     ExtractorError,
   9     HEADRequest,
  10     NO_DEFAULT,
  11     parse_count,
  12     str_to_int,
  13 )
  14
  15
  16 class MixcloudIE(InfoExtractor):
  17     _VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/([^/]+)/([^/]+)'
  18     IE_NAME = 'mixcloud'
  19
  20     _TESTS = [{
  21         'url': 'http://www.mixcloud.com/dholbach/cryptkeeper/',
  22         'info_dict': {
  23             'id': 'dholbach-cryptkeeper',
  24             'ext': 'mp3',
  25             'title': 'Cryptkeeper',
  26             'description': 'After quite a long silence from myself, finally another Drum\'n\'Bass mix with my favourite current dance floor bangers.',
  27             'uploader': 'Daniel Holbach',
  28             'uploader_id': 'dholbach',
  29             'thumbnail': 're:https?://.*\.jpg',
  30             'view_count': int,
  31             'like_count': int,
  32         },
  33     }, {
  34         'url': 'http://www.mixcloud.com/gillespeterson/caribou-7-inch-vinyl-mix-chat/',
  35         'info_dict': {
  36             'id': 'gillespeterson-caribou-7-inch-vinyl-mix-chat',
  37             'ext': 'mp3',
  38             'title': 'Caribou 7 inch Vinyl Mix & Chat',
  39             'description': 'md5:2b8aec6adce69f9d41724647c65875e8',
  40             'uploader': 'Gilles Peterson Worldwide',
  41             'uploader_id': 'gillespeterson',
  42             'thumbnail': 're:https?://.*/images/',
  43             'view_count': int,
  44             'like_count': int,
  45         },
  46     }]
  47
  48     def _check_url(self, url, track_id, ext):
  49         try:
  50             # We only want to know if the request succeed
  51             # don't download the whole file
  52             self._request_webpage(
  53                 HEADRequest(url), track_id,
  54                 'Trying %s URL' % ext)
  55             return True
  56         except ExtractorError:
  57             return False
  58
  59     def _real_extract(self, url):
  60         mobj = re.match(self._VALID_URL, url)
  61         uploader = mobj.group(1)
  62         cloudcast_name = mobj.group(2)
  63         track_id = compat_urllib_parse_unquote('-'.join((uploader, cloudcast_name)))
  64
  65         webpage = self._download_webpage(url, track_id)
  66
  67         message = self._html_search_regex(
  68             r'(?s)<div[^>]+class="global-message cloudcast-disabled-notice-light"[^>]*>(.+?)<(?:a|/div)',
  69             webpage, 'error message', default=None)
  70
  71         preview_url = self._search_regex(
  72             r'\s(?:data-preview-url|m-preview)="([^"]+)"',
  73             webpage, 'preview url', default=None if message else NO_DEFAULT)
  74
  75         if message:
  76             raise ExtractorError('%s said: %s' % (self.IE_NAME, message), expected=True)
  77
  78         song_url = re.sub(r'audiocdn(\d+)', r'stream\1', preview_url)
  79         song_url = song_url.replace('/previews/', '/c/originals/')
  80         if not self._check_url(song_url, track_id, 'mp3'):
  81             song_url = song_url.replace('.mp3', '.m4a').replace('originals/', 'm4a/64/')
  82             if not self._check_url(song_url, track_id, 'm4a'):
  83                 raise ExtractorError('Unable to extract track url')
  84
  85         PREFIX = (
  86             r'm-play-on-spacebar[^>]+'
  87             r'(?:\s+[a-zA-Z0-9-]+(?:="[^"]+")?)*?\s+')
  88         title = self._html_search_regex(
  89             PREFIX + r'm-title="([^"]+)"', webpage, 'title')
  90         thumbnail = self._proto_relative_url(self._html_search_regex(
  91             PREFIX + r'm-thumbnail-url="([^"]+)"', webpage, 'thumbnail',
  92             fatal=False))
  93         uploader = self._html_search_regex(
  94             PREFIX + r'm-owner-name="([^"]+)"',
  95             webpage, 'uploader', fatal=False)
  96         uploader_id = self._search_regex(
  97             r'\s+"profile": "([^"]+)",', webpage, 'uploader id', fatal=False)
  98         description = self._og_search_description(webpage)
  99         like_count = parse_count(self._search_regex(
 100             r'\bbutton-favorite[^>]+>.*?<span[^>]+class=["\']toggle-number[^>]+>\s*([^<]+)',
 101             webpage, 'like count', fatal=False))
 102         view_count = str_to_int(self._search_regex(
 103             [r'<meta itemprop="interactionCount" content="UserPlays:([0-9]+)"',
 104              r'/listeners/?">([0-9,.]+)</a>'],
 105             webpage, 'play count', fatal=False))
 106
 107         return {
 108             'id': track_id,
 109             'title': title,
 110             'url': song_url,
 111             'description': description,
 112             'thumbnail': thumbnail,
 113             'uploader': uploader,
 114             'uploader_id': uploader_id,
 115             'view_count': view_count,
 116             'like_count': like_count,
 117         }