mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2024-08-22 07:10:37 +02:00
[ellentv] Improve extraction (Closes #10067)
This commit is contained in:
parent
0385aa6199
commit
a0560d8ab8
@ -6,12 +6,13 @@
|
|||||||
from .common import InfoExtractor
|
from .common import InfoExtractor
|
||||||
from ..utils import (
|
from ..utils import (
|
||||||
ExtractorError,
|
ExtractorError,
|
||||||
|
NO_DEFAULT,
|
||||||
)
|
)
|
||||||
|
|
||||||
|
|
||||||
class EllenTVIE(InfoExtractor):
|
class EllenTVIE(InfoExtractor):
|
||||||
_VALID_URL = r'https?://(?:www\.)?(?:ellentv|ellentube)\.com/videos/(?P<id>[a-z0-9_-]+)'
|
_VALID_URL = r'https?://(?:www\.)?(?:ellentv|ellentube)\.com/videos/(?P<id>[a-z0-9_-]+)'
|
||||||
_TEST = {
|
_TESTS = [{
|
||||||
'url': 'http://www.ellentv.com/videos/0-ipq1gsai/',
|
'url': 'http://www.ellentv.com/videos/0-ipq1gsai/',
|
||||||
'md5': '4294cf98bc165f218aaa0b89e0fd8042',
|
'md5': '4294cf98bc165f218aaa0b89e0fd8042',
|
||||||
'info_dict': {
|
'info_dict': {
|
||||||
@ -22,24 +23,47 @@ class EllenTVIE(InfoExtractor):
|
|||||||
'timestamp': 1428035648,
|
'timestamp': 1428035648,
|
||||||
'upload_date': '20150403',
|
'upload_date': '20150403',
|
||||||
'uploader_id': 'batchUser',
|
'uploader_id': 'batchUser',
|
||||||
}
|
},
|
||||||
}
|
}, {
|
||||||
|
# not available via http://widgets.ellentube.com/
|
||||||
|
'url': 'http://www.ellentv.com/videos/1-szkgu2m2/',
|
||||||
|
'info_dict': {
|
||||||
|
'id': '1_szkgu2m2',
|
||||||
|
'ext': 'flv',
|
||||||
|
'title': "Ellen's Amazingly Talented Audience",
|
||||||
|
'description': 'md5:86ff1e376ff0d717d7171590e273f0a5',
|
||||||
|
'timestamp': 1255140900,
|
||||||
|
'upload_date': '20091010',
|
||||||
|
'uploader_id': 'ellenkaltura@gmail.com',
|
||||||
|
},
|
||||||
|
'params': {
|
||||||
|
'skip_download': True,
|
||||||
|
},
|
||||||
|
}]
|
||||||
|
|
||||||
def _real_extract(self, url):
|
def _real_extract(self, url):
|
||||||
video_id = self._match_id(url)
|
video_id = self._match_id(url)
|
||||||
|
|
||||||
webpage = self._download_webpage(
|
URLS = ('http://widgets.ellentube.com/videos/%s' % video_id, url)
|
||||||
'http://widgets.ellentube.com/videos/%s' % video_id,
|
|
||||||
video_id)
|
|
||||||
|
|
||||||
partner_id = self._search_regex(
|
for num, url_ in enumerate(URLS, 1):
|
||||||
r"var\s+partnerId\s*=\s*'([^']+)", webpage, 'partner id')
|
webpage = self._download_webpage(
|
||||||
|
url_, video_id, fatal=num == len(URLS))
|
||||||
|
|
||||||
kaltura_id = self._search_regex(
|
default = NO_DEFAULT if num == len(URLS) else None
|
||||||
[r'id="kaltura_player_([^"]+)"',
|
|
||||||
r"_wb_entry_id\s*:\s*'([^']+)",
|
partner_id = self._search_regex(
|
||||||
r'data-kaltura-entry-id="([^"]+)'],
|
r"var\s+partnerId\s*=\s*'([^']+)", webpage, 'partner id',
|
||||||
webpage, 'kaltura id')
|
default=default)
|
||||||
|
|
||||||
|
kaltura_id = self._search_regex(
|
||||||
|
[r'id="kaltura_player_([^"]+)"',
|
||||||
|
r"_wb_entry_id\s*:\s*'([^']+)",
|
||||||
|
r'data-kaltura-entry-id="([^"]+)'],
|
||||||
|
webpage, 'kaltura id', default=default)
|
||||||
|
|
||||||
|
if partner_id and kaltura_id:
|
||||||
|
break
|
||||||
|
|
||||||
return self.url_result('kaltura:%s:%s' % (partner_id, kaltura_id), 'Kaltura')
|
return self.url_result('kaltura:%s:%s' % (partner_id, kaltura_id), 'Kaltura')
|
||||||
|
|
||||||
|
Loading…
Reference in New Issue
Block a user