mirror of
https://gitlab.com/dstftw/youtube-dl.git
synced 2020-11-16 09:42:26 +00:00
[nba] Simplify and use unicode_literals
Remove the commented parts for extracting the upload date
This commit is contained in:
parent
8db69786c2
commit
26a78d4bbf
|
@ -1,48 +1,39 @@
|
||||||
|
from __future__ import unicode_literals
|
||||||
|
|
||||||
import re
|
import re
|
||||||
|
|
||||||
from .common import InfoExtractor
|
from .common import InfoExtractor
|
||||||
from ..utils import (
|
|
||||||
ExtractorError,
|
|
||||||
)
|
|
||||||
|
|
||||||
|
|
||||||
class NBAIE(InfoExtractor):
|
class NBAIE(InfoExtractor):
|
||||||
_VALID_URL = r'^(?:https?://)?(?:watch\.|www\.)?nba\.com/(?:nba/)?video(/[^?]*?)(?:/index\.html)?(?:\?.*)?$'
|
_VALID_URL = r'^(?:https?://)?(?:watch\.|www\.)?nba\.com/(?:nba/)?video(/[^?]*?)(?:/index\.html)?(?:\?.*)?$'
|
||||||
_TEST = {
|
_TEST = {
|
||||||
u'url': u'http://www.nba.com/video/games/nets/2012/12/04/0021200253-okc-bkn-recap.nba/index.html',
|
'url': 'http://www.nba.com/video/games/nets/2012/12/04/0021200253-okc-bkn-recap.nba/index.html',
|
||||||
u'file': u'0021200253-okc-bkn-recap.nba.mp4',
|
'file': u'0021200253-okc-bkn-recap.nba.mp4',
|
||||||
u'md5': u'c0edcfc37607344e2ff8f13c378c88a4',
|
'md5': u'c0edcfc37607344e2ff8f13c378c88a4',
|
||||||
u'info_dict': {
|
'info_dict': {
|
||||||
u"description": u"Kevin Durant scores 32 points and dishes out six assists as the Thunder beat the Nets in Brooklyn.",
|
'description': 'Kevin Durant scores 32 points and dishes out six assists as the Thunder beat the Nets in Brooklyn.',
|
||||||
u"title": u"Thunder vs. Nets"
|
'title': 'Thunder vs. Nets',
|
||||||
}
|
},
|
||||||
}
|
}
|
||||||
|
|
||||||
def _real_extract(self, url):
|
def _real_extract(self, url):
|
||||||
mobj = re.match(self._VALID_URL, url)
|
mobj = re.match(self._VALID_URL, url)
|
||||||
if mobj is None:
|
|
||||||
raise ExtractorError(u'Invalid URL: %s' % url)
|
|
||||||
|
|
||||||
video_id = mobj.group(1)
|
video_id = mobj.group(1)
|
||||||
|
|
||||||
webpage = self._download_webpage(url, video_id)
|
webpage = self._download_webpage(url, video_id)
|
||||||
|
|
||||||
video_url = u'http://ht-mobile.cdn.turner.com/nba/big' + video_id + '_nba_1280x720.mp4'
|
video_url = 'http://ht-mobile.cdn.turner.com/nba/big' + video_id + '_nba_1280x720.mp4'
|
||||||
|
|
||||||
shortened_video_id = video_id.rpartition('/')[2]
|
shortened_video_id = video_id.rpartition('/')[2]
|
||||||
title = self._og_search_title(webpage, default=shortened_video_id).replace('NBA.com: ', '')
|
title = self._og_search_title(webpage, default=shortened_video_id).replace('NBA.com: ', '')
|
||||||
|
|
||||||
# It isn't there in the HTML it returns to us
|
|
||||||
# uploader_date = self._html_search_regex(r'<b>Date:</b> (.*?)</div>', webpage, 'upload_date', fatal=False)
|
|
||||||
|
|
||||||
description = self._html_search_regex(r'<meta name="description" (?:content|value)="(.*?)" />', webpage, 'description', fatal=False)
|
description = self._html_search_regex(r'<meta name="description" (?:content|value)="(.*?)" />', webpage, 'description', fatal=False)
|
||||||
|
|
||||||
info = {
|
return {
|
||||||
'id': shortened_video_id,
|
'id': shortened_video_id,
|
||||||
'url': video_url,
|
'url': video_url,
|
||||||
'ext': 'mp4',
|
'ext': 'mp4',
|
||||||
'title': title,
|
'title': title,
|
||||||
# 'uploader_date': uploader_date,
|
|
||||||
'description': description,
|
'description': description,
|
||||||
}
|
}
|
||||||
return [info]
|
|
||||||
|
|
Loading…
Reference in a new issue