[brightcove] Add the extraction of the url from generic

This commit is contained in:
Jaime Marquínez Ferrándiz 2013-11-06 16:40:24 +01:00
parent 9ee2b5f6f2
commit eeb165e674
2 changed files with 32 additions and 4 deletions

View file

@ -9,6 +9,7 @@ from ..utils import (
compat_urllib_parse, compat_urllib_parse,
find_xpath_attr, find_xpath_attr,
compat_urlparse, compat_urlparse,
compat_str,
ExtractorError, ExtractorError,
) )
@ -71,6 +72,19 @@ class BrightcoveIE(InfoExtractor):
data = compat_urllib_parse.urlencode(params) data = compat_urllib_parse.urlencode(params)
return cls._FEDERATED_URL_TEMPLATE % data return cls._FEDERATED_URL_TEMPLATE % data
@classmethod
def _extract_brightcove_url(cls, webpage):
"""Try to extract the brightcove url from the wepbage, returns None
if it can't be found
"""
m_brightcove = re.search(
r'<object[^>]+?class=([\'"])[^>]*?BrightcoveExperience.*?\1.+?</object>',
webpage, re.DOTALL)
if m_brightcove is not None:
return cls._build_brighcove_url(m_brightcove.group())
else:
return None
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
query_str = mobj.group('query') query_str = mobj.group('query')
@ -109,7 +123,7 @@ class BrightcoveIE(InfoExtractor):
def _extract_video_info(self, video_info): def _extract_video_info(self, video_info):
info = { info = {
'id': video_info['id'], 'id': compat_str(video_info['id']),
'title': video_info['displayName'], 'title': video_info['displayName'],
'description': video_info.get('shortDescription'), 'description': video_info.get('shortDescription'),
'thumbnail': video_info.get('videoStillURL') or video_info.get('thumbnailURL'), 'thumbnail': video_info.get('videoStillURL') or video_info.get('thumbnailURL'),

View file

@ -54,6 +54,21 @@ class GenericIE(InfoExtractor):
}, },
u'skip': u'There is a limit of 200 free downloads / month for the test song', u'skip': u'There is a limit of 200 free downloads / month for the test song',
}, },
# embedded brightcove video
{
u'add_ie': ['Brightcove'],
u'url': u'http://www.scientificamerican.com/article.cfm?id=soap-bubble-physics',
u'info_dict': {
u'id': u'2365799484001',
u'ext': u'mp4',
u'title': u'Bubble Simulation',
u'description': u'A visualization from a new computer model of foam behavior.',
u'uploader': u'Scientific American',
},
u'params': {
u'skip_download': True,
},
},
] ]
def report_download_webpage(self, video_id): def report_download_webpage(self, video_id):
@ -146,10 +161,9 @@ class GenericIE(InfoExtractor):
self.report_extraction(video_id) self.report_extraction(video_id)
# Look for BrightCove: # Look for BrightCove:
m_brightcove = re.search(r'<object[^>]+?class=([\'"])[^>]*?BrightcoveExperience.*?\1.+?</object>', webpage, re.DOTALL) bc_url = BrightcoveIE._extract_brightcove_url(webpage)
if m_brightcove is not None: if bc_url is not None:
self.to_screen(u'Brightcove video detected.') self.to_screen(u'Brightcove video detected.')
bc_url = BrightcoveIE._build_brighcove_url(m_brightcove.group())
return self.url_result(bc_url, 'Brightcove') return self.url_result(bc_url, 'Brightcove')
# Look for embedded Vimeo player # Look for embedded Vimeo player