Update changelog.

[youtubedl] / youtube_dl / extractor / mixcloud.py

diff --git a/youtube_dl/extractor/mixcloud.py b/youtube_dl/extractor/mixcloud.py
index f3356db50ebf8941ac58e9a229778ba864c57be0..d47aecedae388829babaed8642611c5a6b7d29fe 100644 (file)
--- a/youtube_dl/extractor/mixcloud.py
+++ b/youtube_dl/extractor/mixcloud.py
@@ -3,76 +3,103 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
 import re
 
 from .common import InfoExtractor

+from ..compat import compat_urllib_parse_unquote

 from ..utils import (
 from ..utils import (

-    unified_strdate,

     ExtractorError,
     ExtractorError,

+    HEADRequest,
+    str_to_int,

 )
 
 
 class MixcloudIE(InfoExtractor):
 )
 
 
 class MixcloudIE(InfoExtractor):

-    _VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/([\w\d-]+)/([\w\d-]+)'
+    _VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/([^/]+)/([^/]+)'

     IE_NAME = 'mixcloud'
 
     IE_NAME = 'mixcloud'
 

-    _TEST = {
+    _TESTS = [{

         'url': 'http://www.mixcloud.com/dholbach/cryptkeeper/',
         'url': 'http://www.mixcloud.com/dholbach/cryptkeeper/',

-        'file': 'dholbach-cryptkeeper.mp3',

         'info_dict': {
         'info_dict': {

+            'id': 'dholbach-cryptkeeper',
+            'ext': 'mp3',

             'title': 'Cryptkeeper',
             'description': 'After quite a long silence from myself, finally another Drum\'n\'Bass mix with my favourite current dance floor bangers.',
             'uploader': 'Daniel Holbach',
             'uploader_id': 'dholbach',
             'title': 'Cryptkeeper',
             'description': 'After quite a long silence from myself, finally another Drum\'n\'Bass mix with my favourite current dance floor bangers.',
             'uploader': 'Daniel Holbach',
             'uploader_id': 'dholbach',

-            'upload_date': '20111115',
+            'thumbnail': 're:https?://.*\.jpg',
+            'view_count': int,
+            'like_count': int,

         },
         },

-    }
-
-    def check_urls(self, url_list):
-        """Returns 1st active url from list"""
-        for url in url_list:
-            try:
-                # We only want to know if the request succeed
-                # don't download the whole file
-                self._request_webpage(url, None, False)
-                return url
-            except ExtractorError:
-                url = None
-
-        return None
+    }, {
+        'url': 'http://www.mixcloud.com/gillespeterson/caribou-7-inch-vinyl-mix-chat/',
+        'info_dict': {
+            'id': 'gillespeterson-caribou-7-inch-vinyl-mix-chat',
+            'ext': 'mp3',
+            'title': 'Caribou 7 inch Vinyl Mix & Chat',
+            'description': 'md5:2b8aec6adce69f9d41724647c65875e8',
+            'uploader': 'Gilles Peterson Worldwide',
+            'uploader_id': 'gillespeterson',
+            'thumbnail': 're:https?://.*/images/',
+            'view_count': int,
+            'like_count': int,
+        },
+    }]

 
 

-    def _get_url(self, template_url):
-        return self.check_urls(template_url % i for i in range(30))
+    def _check_url(self, url, track_id, ext):
+        try:
+            # We only want to know if the request succeed
+            # don't download the whole file
+            self._request_webpage(
+                HEADRequest(url), track_id,
+                'Trying %s URL' % ext)
+            return True
+        except ExtractorError:
+            return False

 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         uploader = mobj.group(1)
         cloudcast_name = mobj.group(2)
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         uploader = mobj.group(1)
         cloudcast_name = mobj.group(2)

-        track_id = '-'.join((uploader, cloudcast_name))
+        track_id = compat_urllib_parse_unquote('-'.join((uploader, cloudcast_name)))

 
         webpage = self._download_webpage(url, track_id)
 
 
         webpage = self._download_webpage(url, track_id)
 

-        api_url = 'http://api.mixcloud.com/%s/%s/' % (uploader, cloudcast_name)
-        info = self._download_json(
-            api_url, track_id, 'Downloading cloudcast info')
-

         preview_url = self._search_regex(
         preview_url = self._search_regex(

-            r'\s(?:data-preview-url|m-preview)="(.+?)"', webpage, 'preview url')
+            r'\s(?:data-preview-url|m-preview)="([^"]+)"', webpage, 'preview url')

         song_url = preview_url.replace('/previews/', '/c/originals/')
         song_url = preview_url.replace('/previews/', '/c/originals/')

-        template_url = re.sub(r'(stream\d*)', 'stream%d', song_url)
-        final_song_url = self._get_url(template_url)
-        if final_song_url is None:
-            self.to_screen('Trying with m4a extension')
-            template_url = template_url.replace('.mp3', '.m4a').replace('originals/', 'm4a/64/')
-            final_song_url = self._get_url(template_url)
-        if final_song_url is None:
-            raise ExtractorError(u'Unable to extract track url')
+        if not self._check_url(song_url, track_id, 'mp3'):
+            song_url = song_url.replace('.mp3', '.m4a').replace('originals/', 'm4a/64/')
+            if not self._check_url(song_url, track_id, 'm4a'):
+                raise ExtractorError('Unable to extract track url')
+
+        PREFIX = (
+            r'm-play-on-spacebar[^>]+'
+            r'(?:\s+[a-zA-Z0-9-]+(?:="[^"]+")?)*?\s+')
+        title = self._html_search_regex(
+            PREFIX + r'm-title="([^"]+)"', webpage, 'title')
+        thumbnail = self._proto_relative_url(self._html_search_regex(
+            PREFIX + r'm-thumbnail-url="([^"]+)"', webpage, 'thumbnail',
+            fatal=False))
+        uploader = self._html_search_regex(
+            PREFIX + r'm-owner-name="([^"]+)"',
+            webpage, 'uploader', fatal=False)
+        uploader_id = self._search_regex(
+            r'\s+"profile": "([^"]+)",', webpage, 'uploader id', fatal=False)
+        description = self._og_search_description(webpage)
+        like_count = str_to_int(self._search_regex(
+            r'\bbutton-favorite\b[^>]+m-ajax-toggle-count="([^"]+)"',
+            webpage, 'like count', fatal=False))
+        view_count = str_to_int(self._search_regex(
+            [r'<meta itemprop="interactionCount" content="UserPlays:([0-9]+)"',
+             r'/listeners/?">([0-9,.]+)</a>'],
+            webpage, 'play count', fatal=False))

 
         return {
             'id': track_id,
 
         return {
             'id': track_id,

-            'title': info['name'],
-            'url': final_song_url,
-            'description': info.get('description'),
-            'thumbnail': info['pictures'].get('extra_large'),
-            'uploader': info['user']['name'],
-            'uploader_id': info['user']['username'],
-            'upload_date': unified_strdate(info['created_time']),
-            'view_count': info['play_count'],
+            'title': title,
+            'url': song_url,
+            'description': description,
+            'thumbnail': thumbnail,
+            'uploader': uploader,
+            'uploader_id': uploader_id,
+            'view_count': view_count,
+            'like_count': like_count,

         }
         }