Update changelog.

[youtubedl] / youtube_dl / extractor / mixcloud.py

diff --git a/youtube_dl/extractor/mixcloud.py b/youtube_dl/extractor/mixcloud.py
index 07d194562e77044a8d8d87138ed32205842a1a25..c2b7ed9abbd27a2b2c8e0d9d95c59e387630180a 100644 (file)
--- a/youtube_dl/extractor/mixcloud.py
+++ b/youtube_dl/extractor/mixcloud.py
@@ -3,14 +3,11 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
 import re
 
 from .common import InfoExtractor

-from ..compat import (
-    compat_urllib_parse,
-)
+from ..compat import compat_urllib_parse_unquote

 from ..utils import (
     ExtractorError,
     HEADRequest,
 from ..utils import (
     ExtractorError,
     HEADRequest,

-    int_or_none,
-    parse_iso8601,
+    str_to_int,

 )
 
 
 )
 
 


@@ -18,7 +15,7 @@ class MixcloudIE(InfoExtractor):
     _VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/([^/]+)/([^/]+)'
     IE_NAME = 'mixcloud'
 
     _VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/([^/]+)/([^/]+)'
     IE_NAME = 'mixcloud'
 

-    _TEST = {
+    _TESTS = [{

         'url': 'http://www.mixcloud.com/dholbach/cryptkeeper/',
         'info_dict': {
             'id': 'dholbach-cryptkeeper',
         'url': 'http://www.mixcloud.com/dholbach/cryptkeeper/',
         'info_dict': {
             'id': 'dholbach-cryptkeeper',


@@ -27,52 +24,55 @@ class MixcloudIE(InfoExtractor):
             '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',
             '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,
         },
             'thumbnail': 're:https?://.*\.jpg',
             'view_count': int,
             'like_count': int,
         },

-    }
-
-    def _get_url(self, track_id, template_url):
-        server_count = 30
-        for i in range(server_count):
-            url = template_url % i
-            try:
-                # We only want to know if the request succeed
-                # don't download the whole file
-                self._request_webpage(
-                    HEADRequest(url), track_id,
-                    'Checking URL %d/%d ...' % (i + 1, server_count + 1))
-                return url
-            except ExtractorError:
-                pass
+    }, {
+        '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,
+        },
+    }]

 
 

-        return None
+    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 = compat_urllib_parse.unquote('-'.join((uploader, cloudcast_name)))
+        track_id = compat_urllib_parse_unquote('-'.join((uploader, cloudcast_name)))

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

-            r'\s(?:data-preview-url|m-preview)="(.+?)"', webpage, 'preview url')
-        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(track_id, 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(track_id, template_url)
-        if final_song_url is None:
-            raise ExtractorError('Unable to extract track url')
+            r'\s(?:data-preview-url|m-preview)="([^"]+)"', webpage, 'preview url')
+        song_url = re.sub(r'audiocdn(\d+)', r'stream\1', preview_url)
+        song_url = song_url.replace('/previews/', '/c/originals/')
+        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 = (
 
         PREFIX = (

-            r'<span class="play-button[^"]*?"'
+            r'm-play-on-spacebar[^>]+'

             r'(?:\s+[a-zA-Z0-9-]+(?:="[^"]+")?)*?\s+')
         title = self._html_search_regex(
             PREFIX + r'm-title="([^"]+)"', webpage, 'title')
             r'(?:\s+[a-zA-Z0-9-]+(?:="[^"]+")?)*?\s+')
         title = self._html_search_regex(
             PREFIX + r'm-title="([^"]+)"', webpage, 'title')


@@ -85,25 +85,22 @@ class MixcloudIE(InfoExtractor):
         uploader_id = self._search_regex(
             r'\s+"profile": "([^"]+)",', webpage, 'uploader id', fatal=False)
         description = self._og_search_description(webpage)
         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]+)"',
+        like_count = str_to_int(self._search_regex(
+            r'\bbutton-favorite\b[^>]+m-ajax-toggle-count="([^"]+)"',

             webpage, 'like count', fatal=False))
             webpage, 'like count', fatal=False))

-        view_count = int_or_none(self._search_regex(
-            r'<meta itemprop="interactionCount" content="UserPlays:([0-9]+)"',
+        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))
             webpage, 'play count', fatal=False))

-        timestamp = parse_iso8601(self._search_regex(
-            r'<time itemprop="dateCreated" datetime="([^"]+)">',
-            webpage, 'upload date'))

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

-            'url': final_song_url,
+            'url': song_url,

             'description': description,
             'thumbnail': thumbnail,
             'uploader': uploader,
             'uploader_id': uploader_id,
             'description': description,
             'thumbnail': thumbnail,
             'uploader': uploader,
             'uploader_id': uploader_id,

-            'timestamp': timestamp,

             'view_count': view_count,
             'like_count': like_count,
         }
             'view_count': view_count,
             'like_count': like_count,
         }