w/youtube-dl
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

[yahoo] Add support for custom brigthcove embeds (closes #14210)

Browse source
This commit is contained in:
Sergey M․ 2017-09-30 22:47:03 +07:00
parent 3600fd591d
commit eb9a15be60
No known key found for this signature in database
GPG key ID: 2C393E0F18A9236D
1 changed files with 26 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

29
youtube_dl/extractor/yahoo.py
View file

@ -28,7 +28,7 @@ from .nbc import NBCSportsVPlayerIE
class YahooIE(InfoExtractor): class YahooIE(InfoExtractor):
IE_DESC = 'Yahoo screen and movies' IE_DESC = 'Yahoo screen and movies'
_VALID_URL = r'(?P<url>(?P<host>https?://(?:[a-zA-Z]{2}\.)?[\da-zA-Z_-]+\.yahoo\.com)/(?:[^/]+/)*(?P<display_id>.+)?-(?P<id>[0-9]+)(?:-[a-z]+)?(?:\.html)?)' _VALID_URL = r'(?P<host>https?://(?:[a-zA-Z]{2}\.)?[\da-zA-Z_-]+\.yahoo\.com)/(?:[^/]+/)*(?:(?P<display_id>.+)?-)?(?P<id>[0-9]+)(?:-[a-z]+)?(?:\.html)?'
_TESTS = [ _TESTS = [
{ {
'url': 'http://screen.yahoo.com/julian-smith-travis-legg-watch-214727115.html', 'url': 'http://screen.yahoo.com/julian-smith-travis-legg-watch-214727115.html',
@ -227,13 +227,28 @@ class YahooIE(InfoExtractor):
'skip_download': True, 'skip_download': True,
}, },
}, },
{
# custom brightcove
'url': 'https://au.tv.yahoo.com/plus7/sunrise/-/watch/37083565/clown-entertainers-say-it-is-hurting-their-business/',
'info_dict': {
'id': '5575377707001',
'ext': 'mp4',
'title': "Clown entertainers say 'It' is hurting their business",
'description': 'Stephen King s horror film has much to answer for. Jelby and Mr Loopy the Clowns join us.',
'timestamp': 1505341164,
'upload_date': '20170913',
'uploader_id': '2376984109001',
},
'params': {
'skip_download': True,
},
}
] ]
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
display_id = mobj.group('display_id') or self._match_id(url)
page_id = mobj.group('id') page_id = mobj.group('id')
url = mobj.group('url') display_id = mobj.group('display_id') or page_id
host = mobj.group('host') host = mobj.group('host')
webpage, urlh = self._download_webpage_handle(url, display_id) webpage, urlh = self._download_webpage_handle(url, display_id)
if 'err=404' in urlh.geturl(): if 'err=404' in urlh.geturl():
@ -262,6 +277,14 @@ class YahooIE(InfoExtractor):
if bc_url: if bc_url:
return self.url_result(bc_url, BrightcoveNewIE.ie_key()) return self.url_result(bc_url, BrightcoveNewIE.ie_key())
brightcove_id = self._search_regex(
r'<iframe[^>]+data-video-id=["\'](\d+)', webpage, 'brightcove id',
default=None)
if brightcove_id:
return self.url_result(
'http://players.brightcove.net/2376984109001/default_default/index.html?videoId=%s' % brightcove_id,
BrightcoveNewIE.ie_key())
# Query result is often embedded in webpage as JSON. Sometimes explicit requests # Query result is often embedded in webpage as JSON. Sometimes explicit requests
# to video API results in a failure with geo restriction reason therefore using # to video API results in a failure with geo restriction reason therefore using
# embedded query result when present sounds reasonable. # embedded query result when present sounds reasonable.