[youtube:playlist] Recognize ‘top tracks’ urls (closes #2332)

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

diff --git a/youtube_dl/extractor/vine.py b/youtube_dl/extractor/vine.py
index b44b1cb024f607e78ba1b977be42220ea7090e81..e14ff91d44b80b6d6278faece8453b856c39485e 100644 (file)
--- a/youtube_dl/extractor/vine.py
+++ b/youtube_dl/extractor/vine.py
@@ -1,10 +1,22 @@
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
 
 
 class VineIE(InfoExtractor):
-    _VALID_URL = r'(?:https?://)?(?:www\.)?vine\.co/v/(?P<id>\w+)'
+    _VALID_URL = r'https?://(?:www\.)?vine\.co/v/(?P<id>\w+)'
+    _TEST = {
+        'url': 'https://vine.co/v/b9KOOWX7HUx',
+        'md5': '2f36fed6235b16da96ce9b4dc890940d',
+        'info_dict': {
+            'id': 'b9KOOWX7HUx',
+            'ext': 'mp4',
+            'uploader': 'Jack Dorsey',
+            'title': 'Chicken.',
+        },
+    }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
@@ -15,23 +27,17 @@ class VineIE(InfoExtractor):
 
         self.report_extraction(video_id)
 
-        video_url = self._html_search_regex(r'<meta property="twitter:player:stream" content="(.+?)"',
-            webpage, u'video URL')
-
-        video_title = self._html_search_regex(r'<meta property="og:title" content="(.+?)"',
-            webpage, u'title')
-
-        thumbnail = self._html_search_regex(r'<meta property="og:image" content="(.+?)(\?.*?)?"',
-            webpage, u'thumbnail', fatal=False)
+        video_url = self._html_search_meta('twitter:player:stream', webpage,
+            'video URL')
 
-        uploader = self._html_search_regex(r'<div class="user">.*?<h2>(.+?)</h2>',
-            webpage, u'uploader', fatal=False, flags=re.DOTALL)
+        uploader = self._html_search_regex(r'<p class="username">(.*?)</p>',
+            webpage, 'uploader', fatal=False, flags=re.DOTALL)
 
-        return [{
-            'id':        video_id,
-            'url':       video_url,
-            'ext':       'mp4',
-            'title':     video_title,
-            'thumbnail': thumbnail,
-            'uploader':  uploader,
-        }]
+        return {
+            'id': video_id,
+            'url': video_url,
+            'ext': 'mp4',
+            'title': self._og_search_title(webpage),
+            'thumbnail': self._og_search_thumbnail(webpage),
+            'uploader': uploader,
+        }