Raphaël G. Git Repositories - youtubedl/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     str_to_int,
  11 )
  12
  13
  14 class MixcloudIE(InfoExtractor):
  15     _VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/([^/]+)/([^/]+)'
  16     IE_NAME = 'mixcloud'
  17
  18     _TESTS = [{
  19         'url': 'http://www.mixcloud.com/dholbach/cryptkeeper/',
  20         'info_dict': {
  21             'id': 'dholbach-cryptkeeper',
  22             'ext': 'mp3',
  23             'title': 'Cryptkeeper',
  24             'description': 'After quite a long silence from myself, finally another Drum\'n\'Bass mix with my favourite current dance floor bangers.',
  25             'uploader': 'Daniel Holbach',
  26             'uploader_id': 'dholbach',
  27             'thumbnail': 're:https?://.*\.jpg',
  28             'view_count': int,
  29             'like_count': int,
  30         },
  31     }, {
  32         'url': 'http://www.mixcloud.com/gillespeterson/caribou-7-inch-vinyl-mix-chat/',
  33         'info_dict': {
  34             'id': 'gillespeterson-caribou-7-inch-vinyl-mix-chat',
  35             'ext': 'mp3',
  36             'title': 'Caribou 7 inch Vinyl Mix & Chat',
  37             'description': 'md5:2b8aec6adce69f9d41724647c65875e8',
  38             'uploader': 'Gilles Peterson Worldwide',
  39             'uploader_id': 'gillespeterson',
  40             'thumbnail': 're:https?://.*/images/',
  41             'view_count': int,
  42             'like_count': int,
  43         },
  44     }]
  45
  46     def _check_url(self, url, track_id, ext):
  47         try:
  48             # We only want to know if the request succeed
  49             # don't download the whole file
  50             self._request_webpage(
  51                 HEADRequest(url), track_id,
  52                 'Trying %s URL' % ext)
  53             return True
  54         except ExtractorError:
  55             return False
  56
  57     def _real_extract(self, url):
  58         mobj = re.match(self._VALID_URL, url)
  59         uploader = mobj.group(1)
  60         cloudcast_name = mobj.group(2)
  61         track_id = compat_urllib_parse_unquote('-'.join((uploader, cloudcast_name)))
  62
  63         webpage = self._download_webpage(url, track_id)
  64
  65         preview_url = self._search_regex(
  66             r'\s(?:data-preview-url|m-preview)="([^"]+)"', webpage, 'preview url')
  67         song_url = re.sub(r'audiocdn(\d+)', r'stream\1', preview_url)
  68         song_url = song_url.replace('/previews/', '/c/originals/')
  69         if not self._check_url(song_url, track_id, 'mp3'):
  70             song_url = song_url.replace('.mp3', '.m4a').replace('originals/', 'm4a/64/')
  71             if not self._check_url(song_url, track_id, 'm4a'):
  72                 raise ExtractorError('Unable to extract track url')
  73
  74         PREFIX = (
  75             r'm-play-on-spacebar[^>]+'
  76             r'(?:\s+[a-zA-Z0-9-]+(?:="[^"]+")?)*?\s+')
  77         title = self._html_search_regex(
  78             PREFIX + r'm-title="([^"]+)"', webpage, 'title')
  79         thumbnail = self._proto_relative_url(self._html_search_regex(
  80             PREFIX + r'm-thumbnail-url="([^"]+)"', webpage, 'thumbnail',
  81             fatal=False))
  82         uploader = self._html_search_regex(
  83             PREFIX + r'm-owner-name="([^"]+)"',
  84             webpage, 'uploader', fatal=False)
  85         uploader_id = self._search_regex(
  86             r'\s+"profile": "([^"]+)",', webpage, 'uploader id', fatal=False)
  87         description = self._og_search_description(webpage)
  88         like_count = str_to_int(self._search_regex(
  89             r'\bbutton-favorite\b[^>]+m-ajax-toggle-count="([^"]+)"',
  90             webpage, 'like count', fatal=False))
  91         view_count = str_to_int(self._search_regex(
  92             [r'<meta itemprop="interactionCount" content="UserPlays:([0-9]+)"',
  93              r'/listeners/?">([0-9,.]+)</a>'],
  94             webpage, 'play count', fatal=False))
  95
  96         return {
  97             'id': track_id,
  98             'title': title,
  99             'url': song_url,
 100             'description': description,
 101             'thumbnail': thumbnail,
 102             'uploader': uploader,
 103             'uploader_id': uploader_id,
 104             'view_count': view_count,
 105             'like_count': like_count,
 106         }