Initiate release.

[youtubedl] / youtube_dl / extractor / mixcloud.py

diff --git a/youtube_dl/extractor/mixcloud.py b/youtube_dl/extractor/mixcloud.py
index f3356db50ebf8941ac58e9a229778ba864c57be0..5f64e7bd0d98b74aea2a4350a51f057b4d0280ba 100644 (file)
--- a/youtube_dl/extractor/mixcloud.py
+++ b/youtube_dl/extractor/mixcloud.py
@@ -4,24 +4,31 @@ import re
 
 from .common import InfoExtractor
 from ..utils import (
 
 from .common import InfoExtractor
 from ..utils import (

-    unified_strdate,
+    compat_urllib_parse,

     ExtractorError,
     ExtractorError,

+    int_or_none,
+    parse_iso8601,

 )
 
 
 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'
 
     _TEST = {
         'url': 'http://www.mixcloud.com/dholbach/cryptkeeper/',
     IE_NAME = 'mixcloud'
 
     _TEST = {
         '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',
             'upload_date': '20111115',
             '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',

+            'timestamp': 1321359578,
+            'thumbnail': 're:https?://.*\.jpg',
+            'view_count': int,
+            'like_count': int,

         },
     }
 
         },
     }
 


@@ -45,14 +52,10 @@ class MixcloudIE(InfoExtractor):
         mobj = re.match(self._VALID_URL, url)
         uploader = mobj.group(1)
         cloudcast_name = mobj.group(2)
         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(
             r'\s(?:data-preview-url|m-preview)="(.+?)"', webpage, 'preview url')
         song_url = preview_url.replace('/previews/', '/c/originals/')
         preview_url = self._search_regex(
             r'\s(?:data-preview-url|m-preview)="(.+?)"', webpage, 'preview url')
         song_url = preview_url.replace('/previews/', '/c/originals/')


@@ -63,16 +66,41 @@ class MixcloudIE(InfoExtractor):
             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:
             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')
+            raise ExtractorError('Unable to extract track url')
+
+        PREFIX = (
+            r'<div class="cloudcast-play-button-container"'
+            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 = int_or_none(self._search_regex(
+            r'<meta itemprop="interactionCount" content="UserLikes:([0-9]+)"',
+            webpage, 'like count', fatal=False))
+        view_count = int_or_none(self._search_regex(
+            r'<meta itemprop="interactionCount" content="UserPlays:([0-9]+)"',
+            webpage, 'play count', fatal=False))
+        timestamp = parse_iso8601(self._search_regex(
+            r'<time itemprop="dateCreated" datetime="([^"]+)">',
+            webpage, 'upload date'))

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

-            'title': info['name'],
+            'title': title,

             'url': final_song_url,
             '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'],
+            'description': description,
+            'thumbnail': thumbnail,
+            'uploader': uploader,
+            'uploader_id': uploader_id,
+            'timestamp': timestamp,
+            'view_count': view_count,
+            'like_count': like_count,

         }
         }