pepepper/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl synced 2024-11-16 18:42:38 +09:00
Code Issues Projects Releases Wiki Activity

[nba] Support non-video/ pages

Browse Source 
Fixes #8589
This commit is contained in:
Yen Chi Hsuan 2016-02-21 18:20:55 +08:00
parent b43a7a92cd
commit 86a7dbe66e
1 changed files with 27 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

30
youtube_dl/extractor/nba.py
View File

@ -1,18 +1,20 @@
from __future__ import unicode_literals from __future__ import unicode_literals
import os.path
import re import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
parse_duration,
int_or_none, int_or_none,
parse_duration,
remove_start,
xpath_text, xpath_text,
xpath_attr, xpath_attr,
) )
class NBAIE(InfoExtractor): 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 = [{ _TESTS = [{
'url': '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',
'md5': '9e7729d3010a9c71506fd1248f74e4f4', 'md5': '9e7729d3010a9c71506fd1248f74e4f4',
@ -44,14 +46,36 @@ class NBAIE(InfoExtractor):
'timestamp': 1432134543, 'timestamp': 1432134543,
'upload_date': '20150520', '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): def _real_extract(self, url):
path, video_id = re.match(self._VALID_URL, url).groups() path, video_id = re.match(self._VALID_URL, url).groups()
if path.startswith('nba/'): if path.startswith('nba/'):
path = path[3:] 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') title = xpath_text(video_info, 'headline')
description = xpath_text(video_info, 'description') description = xpath_text(video_info, 'description')
duration = parse_duration(xpath_text(video_info, 'length')) duration = parse_duration(xpath_text(video_info, 'length'))