_ 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 )
  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 _get_url(self, track_id, template_url):
  49         server_count = 30
  50         for i in range(server_count):
  51             url = template_url % i
  52             try:
  53                 # We only want to know if the request succeed
  54                 # don't download the whole file
  55                 self._request_webpage(
  56                     HEADRequest(url), track_id,
  57                     'Checking URL %d/%d ...' % (i + 1, server_count + 1))
  58                 return url
  59             except ExtractorError:
  60                 pass
  61
  62         return None
  63
  64     def _real_extract(self, url):
  65         mobj = re.match(self._VALID_URL, url)
  66         uploader = mobj.group(1)
  67         cloudcast_name = mobj.group(2)
  68         track_id = compat_urllib_parse.unquote('-'.join((uploader, cloudcast_name)))
  69
  70         webpage = self._download_webpage(url, track_id)
  71
  72         preview_url = self._search_regex(
  73             r'\s(?:data-preview-url|m-preview)="([^"]+)"', webpage, 'preview url')
  74         song_url = preview_url.replace('/previews/', '/c/originals/')
  75         template_url = re.sub(r'(stream\d*)', 'stream%d', song_url)
  76         final_song_url = self._get_url(track_id, template_url)
  77         if final_song_url is None:
  78             self.to_screen('Trying with m4a extension')
  79             template_url = template_url.replace('.mp3', '.m4a').replace('originals/', 'm4a/64/')
  80             final_song_url = self._get_url(track_id, template_url)
  81         if final_song_url is None:
  82             raise ExtractorError('Unable to extract track url')
  83
  84         PREFIX = (
  85             r'm-play-on-spacebar[^>]+'
  86             r'(?:\s+[a-zA-Z0-9-]+(?:="[^"]+")?)*?\s+')
  87         title = self._html_search_regex(
  88             PREFIX + r'm-title="([^"]+)"', webpage, 'title')
  89         thumbnail = self._proto_relative_url(self._html_search_regex(
  90             PREFIX + r'm-thumbnail-url="([^"]+)"', webpage, 'thumbnail',
  91             fatal=False))
  92         uploader = self._html_search_regex(
  93             PREFIX + r'm-owner-name="([^"]+)"',
  94             webpage, 'uploader', fatal=False)
  95         uploader_id = self._search_regex(
  96             r'\s+"profile": "([^"]+)",', webpage, 'uploader id', fatal=False)
  97         description = self._og_search_description(webpage)
  98         like_count = str_to_int(self._search_regex(
  99             r'\bbutton-favorite\b.+m-ajax-toggle-count="([^"]+)"',
 100             webpage, 'like count', fatal=False))
 101         view_count = str_to_int(self._search_regex(
 102             [r'<meta itemprop="interactionCount" content="UserPlays:([0-9]+)"',
 103              r'/listeners/?">([0-9,.]+)</a>'],
 104             webpage, 'play count', fatal=False))
 105
 106         return {
 107             'id': track_id,
 108             'title': title,
 109             'url': final_song_url,
 110             'description': description,
 111             'thumbnail': thumbnail,
 112             'uploader': uploader,
 113             'uploader_id': uploader_id,
 114             'view_count': view_count,
 115             'like_count': like_count,
 116         }