projects
/
youtube-dl
/ blobdiff
commit
grep
author
committer
pickaxe
?
search:
re
summary
|
shortlog
|
log
|
commit
|
commitdiff
|
tree
raw
|
inline
| side by side
[tapely] Add new extractor (closes #3861)
[youtube-dl]
/
youtube_dl
/
extractor
/
yahoo.py
diff --git
a/youtube_dl/extractor/yahoo.py
b/youtube_dl/extractor/yahoo.py
index d84be25620eecb944845b74299510067772c583f..221341c138c76f09186dc06bf19025bdb85e6d87 100644
(file)
--- a/
youtube_dl/extractor/yahoo.py
+++ b/
youtube_dl/extractor/yahoo.py
@@
-15,7
+15,7
@@
from ..utils import (
class YahooIE(InfoExtractor):
IE_DESC = 'Yahoo screen and movies'
class YahooIE(InfoExtractor):
IE_DESC = 'Yahoo screen and movies'
- _VALID_URL = r'
https?://(?:screen|movies)\.yahoo\.com/.*?-(?P<id>[0-9]+)(?:-[a-z]+)?\.html
'
+ _VALID_URL = r'
(?P<url>https?://(?:screen|movies)\.yahoo\.com/.*?-(?P<id>[0-9]+)(?:-[a-z]+)?\.html)
'
_TESTS = [
{
'url': 'http://screen.yahoo.com/julian-smith-travis-legg-watch-214727115.html',
_TESTS = [
{
'url': 'http://screen.yahoo.com/julian-smith-travis-legg-watch-214727115.html',
@@
-38,20
+38,21
@@
class YahooIE(InfoExtractor):
},
},
{
},
},
{
- 'url': 'https://
movies.yahoo.com/video/world-loves-spider-man-190819223.html
',
- 'md5': '
410b7104aa9893b765bc22787a22f3d9
',
+ 'url': 'https://
screen.yahoo.com/community/community-sizzle-reel-203225340.html?format=embed
',
+ 'md5': '
60e8ac193d8fb71997caa8fce54c6460
',
'info_dict': {
'info_dict': {
- 'id': '
516ed8e2-2c4f-339f-a211-7a8b49d30845
',
+ 'id': '
4fe78544-8d48-39d8-97cd-13f205d9fcdb
',
'ext': 'mp4',
'ext': 'mp4',
- 'title':
'The World Loves Spider-Man'
,
- 'description': '
''People all over the world are celebrating the release of \"The Amazing Spider-Man 2.\" We're taking a look at the enthusiastic response Spider-Man has received from viewers all over the world.''
',
+ 'title':
"Yahoo Saves 'Community'"
,
+ 'description': '
md5:4d4145af2fd3de00cbb6c1d664105053
',
}
}
- }
+ }
,
]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
+ url = mobj.group('url')
webpage = self._download_webpage(url, video_id)
items_json = self._search_regex(
webpage = self._download_webpage(url, video_id)
items_json = self._search_regex(
@@
-60,7
+61,8
@@
class YahooIE(InfoExtractor):
if items_json is None:
CONTENT_ID_REGEXES = [
r'YUI\.namespace\("Media"\)\.CONTENT_ID\s*=\s*"([^"]+)"',
if items_json is None:
CONTENT_ID_REGEXES = [
r'YUI\.namespace\("Media"\)\.CONTENT_ID\s*=\s*"([^"]+)"',
- r'root\.App\.Cache\.context\.videoCache\.curVideo = \{"([^"]+)"'
+ r'root\.App\.Cache\.context\.videoCache\.curVideo = \{"([^"]+)"',
+ r'"first_videoid"\s*:\s*"([^"]+)"',
]
long_id = self._search_regex(CONTENT_ID_REGEXES, webpage, 'content ID')
video_id = long_id
]
long_id = self._search_regex(CONTENT_ID_REGEXES, webpage, 'content ID')
video_id = long_id