diff options
author | Philipp Hagemeister <phihag@phihag.de> | 2013-06-23 21:18:00 +0200 |
---|---|---|
committer | Philipp Hagemeister <phihag@phihag.de> | 2013-06-23 21:18:00 +0200 |
commit | 5b286728de721e4636c6f4d1df06e35b4b9d365d (patch) | |
tree | 6c45593540b0f88ca41e586424238c9c611b3ace /youtube_dl/extractor/nba.py | |
parent | 291a168bcc404313b16d031f6014383301e1d42f (diff) |
Move NBA IE into its own file
Diffstat (limited to 'youtube_dl/extractor/nba.py')
-rw-r--r-- | youtube_dl/extractor/nba.py | 40 |
1 files changed, 40 insertions, 0 deletions
diff --git a/youtube_dl/extractor/nba.py b/youtube_dl/extractor/nba.py new file mode 100644 index 000000000..296d4cd36 --- /dev/null +++ b/youtube_dl/extractor/nba.py @@ -0,0 +1,40 @@ +import re + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, +) + + +class NBAIE(InfoExtractor): + _VALID_URL = r'^(?:https?://)?(?:watch\.|www\.)?nba\.com/(?:nba/)?video(/[^?]*?)(?:/index\.html)?(?:\?.*)?$' + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + if mobj is None: + raise ExtractorError(u'Invalid URL: %s' % url) + + video_id = mobj.group(1) + + webpage = self._download_webpage(url, video_id) + + video_url = u'http://ht-mobile.cdn.turner.com/nba/big' + video_id + '_nba_1280x720.mp4' + + shortened_video_id = video_id.rpartition('/')[2] + title = self._html_search_regex(r'<meta property="og:title" content="(.*?)"', + webpage, 'title', 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) + + info = { + 'id': shortened_video_id, + 'url': video_url, + 'ext': 'mp4', + 'title': title, + # 'uploader_date': uploader_date, + 'description': description, + } + return [info] |