projects
/
youtube-dl
/ commitdiff
commit
grep
author
committer
pickaxe
?
search:
re
summary
|
shortlog
|
log
|
commit
| commitdiff |
tree
raw
|
patch
|
inline
| side by side (parent:
b43a7a9
)
[nba] Support non-video/ pages
author
Yen Chi Hsuan
<yan12125@gmail.com>
Sun, 21 Feb 2016 10:20:55 +0000
(18:20 +0800)
committer
Yen Chi Hsuan
<yan12125@gmail.com>
Tue, 23 Feb 2016 05:11:20 +0000
(13:11 +0800)
Fixes #8589
youtube_dl/extractor/nba.py
patch
|
blob
|
history
diff --git
a/youtube_dl/extractor/nba.py
b/youtube_dl/extractor/nba.py
index a071378b6d1dc18cefe3d76f98c3b30d0fe8a880..87b38c4c75c5a0312a7c10ea15f2f626920cbd53 100644
(file)
--- a/
youtube_dl/extractor/nba.py
+++ b/
youtube_dl/extractor/nba.py
@@
-1,18
+1,20
@@
from __future__ import unicode_literals
from __future__ import unicode_literals
+import os.path
import re
from .common import InfoExtractor
from ..utils import (
import re
from .common import InfoExtractor
from ..utils import (
- parse_duration,
int_or_none,
int_or_none,
+ parse_duration,
+ remove_start,
xpath_text,
xpath_attr,
)
class NBAIE(InfoExtractor):
xpath_text,
xpath_attr,
)
class NBAIE(InfoExtractor):
- _VALID_URL = r'https?://(?:watch\.|www\.)?nba\.com/(?P<path>(?:[^/]+/)
?video/
(?P<id>[^?]*?))/?(?:/index\.html)?(?:\?.*)?$'
+ _VALID_URL = r'https?://(?:watch\.|www\.)?nba\.com/(?P<path>(?:[^/]+/)
+
(?P<id>[^?]*?))/?(?:/index\.html)?(?:\?.*)?$'
_TESTS = [{
'url': 'http://www.nba.com/video/games/nets/2012/12/04/0021200253-okc-bkn-recap.nba/index.html',
'md5': '9e7729d3010a9c71506fd1248f74e4f4',
_TESTS = [{
'url': 'http://www.nba.com/video/games/nets/2012/12/04/0021200253-okc-bkn-recap.nba/index.html',
'md5': '9e7729d3010a9c71506fd1248f74e4f4',
@@
-44,14
+46,36
@@
class NBAIE(InfoExtractor):
'timestamp': 1432134543,
'upload_date': '20150520',
}
'timestamp': 1432134543,
'upload_date': '20150520',
}
+ }, {
+ 'url': 'http://www.nba.com/clippers/news/doc-rivers-were-not-trading-blake',
+ 'info_dict': {
+ 'id': '1455672027478-Doc_Feb16_720',
+ 'ext': 'mp4',
+ 'title': 'Practice: Doc Rivers - 2/16/16',
+ 'description': 'Head Coach Doc Rivers addresses the media following practice.',
+ 'upload_date': '20160217',
+ 'timestamp': 1455672000,
+ },
+ 'params': {
+ # m3u8 download
+ 'skip_download': True,
+ },
}]
def _real_extract(self, url):
path, video_id = re.match(self._VALID_URL, url).groups()
if path.startswith('nba/'):
path = path[3:]
}]
def _real_extract(self, url):
path, video_id = re.match(self._VALID_URL, url).groups()
if path.startswith('nba/'):
path = path[3:]
+
+ if 'video/' not in path:
+ webpage = self._download_webpage(url, video_id)
+ path = remove_start(self._search_regex(r'data-videoid="([^"]+)"', webpage, 'video id'), '/')
+ # See prepareContentId() of pkgCvp.js
+ if path.startswith('video/teams'):
+ path = 'video/channels/proxy/' + path[6:]
+
video_info = self._download_xml('http://www.nba.com/%s.xml' % path, video_id)
video_info = self._download_xml('http://www.nba.com/%s.xml' % path, video_id)
- video_id =
xpath_text(video_info, 'slug')
+ video_id =
os.path.splitext(xpath_text(video_info, 'slug'))[0]
title = xpath_text(video_info, 'headline')
description = xpath_text(video_info, 'description')
duration = parse_duration(xpath_text(video_info, 'length'))
title = xpath_text(video_info, 'headline')
description = xpath_text(video_info, 'description')
duration = parse_duration(xpath_text(video_info, 'length'))