[extractor/generic] Add test for large compressed media

[youtube-dl] / youtube_dl / extractor / mixcloud.py

diff --git a/youtube_dl/extractor/mixcloud.py b/youtube_dl/extractor/mixcloud.py
index 2fe55179aac2b737cbf1fc68797fe48976c23270..425a4ccf16fff96b1bface874748b93762d2194b 100644 (file)
--- a/youtube_dl/extractor/mixcloud.py
+++ b/youtube_dl/extractor/mixcloud.py
@@ -45,21 +45,16 @@ class MixcloudIE(InfoExtractor):
         },
     }]
 
-    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
-
-        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)
@@ -72,14 +67,10 @@ class MixcloudIE(InfoExtractor):
         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')
+        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[^>]+'
@@ -96,7 +87,7 @@ class MixcloudIE(InfoExtractor):
             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="([^"]+)"',
+            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]+)"',
@@ -106,7 +97,7 @@ class MixcloudIE(InfoExtractor):
         return {
             'id': track_id,
             'title': title,
-            'url': final_song_url,
+            'url': song_url,
             'description': description,
             'thumbnail': thumbnail,
             'uploader': uploader,