]> Raphaƫl G. Git Repositories - youtubedl/blobdiff - youtube_dl/extractor/mixcloud.py
Initiate a new release.
[youtubedl] / youtube_dl / extractor / mixcloud.py
index 5f64e7bd0d98b74aea2a4350a51f057b4d0280ba..1831c6749401405c5a39ca60f4347df03bfe3631 100644 (file)
@@ -3,10 +3,13 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
     compat_urllib_parse,
+)
+from ..utils import (
     ExtractorError,
-    int_or_none,
+    HEADRequest,
+    str_to_int,
     parse_iso8601,
 )
 
@@ -15,7 +18,7 @@ class MixcloudIE(InfoExtractor):
     _VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/([^/]+)/([^/]+)'
     IE_NAME = 'mixcloud'
 
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.mixcloud.com/dholbach/cryptkeeper/',
         'info_dict': {
             'id': 'dholbach-cryptkeeper',
@@ -30,24 +33,37 @@ class MixcloudIE(InfoExtractor):
             'view_count': int,
             'like_count': int,
         },
-    }
+    }, {
+        'url': 'http://www.mixcloud.com/gillespeterson/caribou-7-inch-vinyl-mix-chat/',
+        'info_dict': {
+            'id': 'gillespeterson-caribou-7-inch-vinyl-mix-chat',
+            'ext': 'm4a',
+            'title': 'Electric Relaxation vol. 3',
+            'description': 'md5:2b8aec6adce69f9d41724647c65875e8',
+            'uploader': 'Daniel Drumz',
+            'uploader_id': 'gillespeterson',
+            '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:
+    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(url, None, False)
+                self._request_webpage(
+                    HEADRequest(url), track_id,
+                    'Checking URL %d/%d ...' % (i + 1, server_count + 1))
                 return url
             except ExtractorError:
-                url = None
+                pass
 
         return None
 
-    def _get_url(self, template_url):
-        return self.check_urls(template_url % i for i in range(30))
-
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         uploader = mobj.group(1)
@@ -57,19 +73,19 @@ class MixcloudIE(InfoExtractor):
         webpage = self._download_webpage(url, track_id)
 
         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/')
         template_url = re.sub(r'(stream\d*)', 'stream%d', song_url)
-        final_song_url = self._get_url(template_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(template_url)
+            final_song_url = self._get_url(track_id, template_url)
         if final_song_url is None:
             raise ExtractorError('Unable to extract track url')
 
         PREFIX = (
-            r'<div class="cloudcast-play-button-container"'
+            r'<span class="play-button[^"]*?"'
             r'(?:\s+[a-zA-Z0-9-]+(?:="[^"]+")?)*?\s+')
         title = self._html_search_regex(
             PREFIX + r'm-title="([^"]+)"', webpage, 'title')
@@ -82,15 +98,17 @@ class MixcloudIE(InfoExtractor):
         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'<meta itemprop="interactionCount" content="UserLikes:([0-9]+)"',
+             r'/favorites/?">([0-9]+)<'],
             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))
         timestamp = parse_iso8601(self._search_regex(
             r'<time itemprop="dateCreated" datetime="([^"]+)">',
-            webpage, 'upload date'))
+            webpage, 'upload date', default=None))
 
         return {
             'id': track_id,