summary refs log tree commit diff
diff options
context:
space:
mode:
authorSergey M. <dstftw@gmail.com>2014-02-23 19:01:15 +0700
committerSergey M. <dstftw@gmail.com>2014-02-23 19:02:31 +0700
commitf919201ecccc6ac208b86d281439eb669d373765 (patch)
tree718dac8a592d6d50e92136d8d14ceb9c9110cfaf
parent7ff5d5c2e23cb1329d0505eb7f2bcc850f8d3047 (diff)
downloadyoutube-dl-f919201ecccc6ac208b86d281439eb669d373765.tar.gz
youtube-dl-f919201ecccc6ac208b86d281439eb669d373765.tar.xz
youtube-dl-f919201ecccc6ac208b86d281439eb669d373765.zip
[vine] Extract more metadata and support low format
-rw-r--r--youtube_dl/extractor/vine.py46
1 files changed, 31 insertions, 15 deletions
diff --git a/youtube_dl/extractor/vine.py b/youtube_dl/extractor/vine.py
index a919129a6..5bbc8ba88 100644
--- a/youtube_dl/extractor/vine.py
+++ b/youtube_dl/extractor/vine.py
@@ -1,8 +1,10 @@
 from __future__ import unicode_literals
 
 import re
+import json
 
 from .common import InfoExtractor
+from ..utils import unified_strdate
 
 
 class VineIE(InfoExtractor):
@@ -13,32 +15,46 @@ class VineIE(InfoExtractor):
         'info_dict': {
             'id': 'b9KOOWX7HUx',
             'ext': 'mp4',
-            'uploader': 'Jack Dorsey',
             'title': 'Chicken.',
+            'description': 'Chicken.',
+            'upload_date': '20130519',
+            'uploader': 'Jack Dorsey',
+            'uploader_id': '76',
         },
     }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-
         video_id = mobj.group('id')
-        webpage_url = 'https://vine.co/v/' + video_id
-        webpage = self._download_webpage(webpage_url, video_id)
 
-        self.report_extraction(video_id)
+        webpage = self._download_webpage('https://vine.co/v/' + video_id, video_id)
 
-        video_url = self._html_search_meta('twitter:player:stream', webpage,
-            'video URL')
+        data = json.loads(self._html_search_regex(
+            r'window\.POST_DATA = { %s: ({.+?}) }' % video_id, webpage, 'vine data'))
 
-        twitter_title  = self._html_search_meta('twitter:title', webpage,
-            'twitter title')
-        uploader = re.sub('\'s post on Vine', '', twitter_title)
+        formats = [
+            {
+                'url': data['videoLowURL'],
+                'ext': 'mp4',
+                'format_id': 'low',
+            },
+            {
+                'url': data['videoUrl'],
+                'ext': 'mp4',
+                'format_id': 'standard',
+            }
+        ]
 
         return {
             'id': video_id,
-            'url': video_url,
-            'ext': 'mp4',
             'title': self._og_search_title(webpage),
-            'thumbnail': self._og_search_thumbnail(webpage),
-            'uploader': uploader,
-        }
+            'description': data['description'],
+            'thumbnail': data['thumbnailUrl'],
+            'upload_date': unified_strdate(data['created']),
+            'uploader': data['username'],
+            'uploader_id': data['userIdStr'],
+            'like_count': data['likes']['count'],
+            'comment_count': data['comments']['count'],
+            'repost_count': data['reposts']['count'],
+            'formats': formats,
+        }
\ No newline at end of file