projects
/
youtube-dl
/ commitdiff
commit
grep
author
committer
pickaxe
?
search:
re
summary
|
shortlog
|
log
|
commit
| commitdiff |
tree
raw
|
patch
|
inline
| side by side (parent:
7ff5d5c
)
[vine] Extract more metadata and support low format
author
Sergey M.
<dstftw@gmail.com>
Sun, 23 Feb 2014 12:01:15 +0000
(19:01 +0700)
committer
Sergey M.
<dstftw@gmail.com>
Sun, 23 Feb 2014 12:02:31 +0000
(19:02 +0700)
youtube_dl/extractor/vine.py
patch
|
blob
|
history
diff --git
a/youtube_dl/extractor/vine.py
b/youtube_dl/extractor/vine.py
index a919129a67ae7cd73821a56485c4c879827d223f..5bbc8ba88bbdb6a0d069324a3fd191844ccf7773 100644
(file)
--- a/
youtube_dl/extractor/vine.py
+++ b/
youtube_dl/extractor/vine.py
@@
-1,8
+1,10
@@
from __future__ import unicode_literals
import re
from __future__ import unicode_literals
import re
+import json
from .common import InfoExtractor
from .common import InfoExtractor
+from ..utils import unified_strdate
class VineIE(InfoExtractor):
class VineIE(InfoExtractor):
@@
-13,32
+15,46
@@
class VineIE(InfoExtractor):
'info_dict': {
'id': 'b9KOOWX7HUx',
'ext': 'mp4',
'info_dict': {
'id': 'b9KOOWX7HUx',
'ext': 'mp4',
- 'uploader': 'Jack Dorsey',
'title': 'Chicken.',
'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)
},
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
-
video_id = mobj.group('id')
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,
return {
'id': video_id,
- 'url': video_url,
- 'ext': 'mp4',
'title': self._og_search_title(webpage),
'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