[foxnews] Support Fox News Articles (closes #10598)

This commit is contained in:
Yen Chi Hsuan 2016-09-11 18:32:45 +08:00
parent 2cb93afcd8
commit 2cdbc06a1f
No known key found for this signature in database
GPG key ID: 3FDDD575826C5C30
3 changed files with 39 additions and 3 deletions

View file

@ -1,6 +1,7 @@
version <unreleased> version <unreleased>
Extractors Extractors
+ [foxnews] Support Fox News articles (#10598)
* [iwara] Fix extraction after relaunch (#10462, #3215) * [iwara] Fix extraction after relaunch (#10462, #3215)
* [newgrounds] Fix uploader extraction (#10584) * [newgrounds] Fix uploader extraction (#10584)

View file

@ -292,6 +292,7 @@
from .fox import FOXIE from .fox import FOXIE
from .foxgay import FoxgayIE from .foxgay import FoxgayIE
from .foxnews import ( from .foxnews import (
FoxNewsVideoIE,
FoxNewsIE, FoxNewsIE,
FoxNewsInsiderIE, FoxNewsInsiderIE,
) )

View file

@ -6,7 +6,8 @@
from .common import InfoExtractor from .common import InfoExtractor
class FoxNewsIE(AMPIE): class FoxNewsVideoIE(AMPIE):
IE_NAME = 'foxnews:video'
IE_DESC = 'Fox News and Fox Business Video' IE_DESC = 'Fox News and Fox Business Video'
_VALID_URL = r'https?://(?P<host>video\.(?:insider\.)?fox(?:news|business)\.com)/v/(?:video-embed\.html\?video_id=)?(?P<id>\d+)' _VALID_URL = r'https?://(?P<host>video\.(?:insider\.)?fox(?:news|business)\.com)/v/(?:video-embed\.html\?video_id=)?(?P<id>\d+)'
_TESTS = [ _TESTS = [
@ -66,6 +67,35 @@ def _real_extract(self, url):
return info return info
class FoxNewsIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?foxnews\.com/(?!v)([^/]+/)+(?P<id>[a-z-]+)'
IE_NAME = 'foxnews'
_TEST = {
'url': 'http://www.foxnews.com/politics/2016/09/08/buzz-about-bud-clinton-camp-denies-claims-wore-earpiece-at-forum.html',
'md5': '62aa5a781b308fdee212ebb6f33ae7ef',
'info_dict': {
'id': '5116295019001',
'ext': 'mp4',
'title': 'Trump and Clinton asked to defend positions on Iraq War',
'description': 'Veterans react on \'The Kelly File\'',
'timestamp': 1473299755,
'upload_date': '20160908',
},
}
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
video_id = self._html_search_regex(
r'data-video-id=([\'"])(?P<id>[^\'"]+)\1',
webpage, 'video ID', group='id')
return self.url_result(
'http://video.foxnews.com/v/' + video_id,
FoxNewsVideoIE.ie_key())
class FoxNewsInsiderIE(InfoExtractor): class FoxNewsInsiderIE(InfoExtractor):
_VALID_URL = r'https?://insider\.foxnews\.com/([^/]+/)+(?P<id>[a-z-]+)' _VALID_URL = r'https?://insider\.foxnews\.com/([^/]+/)+(?P<id>[a-z-]+)'
IE_NAME = 'foxnews:insider' IE_NAME = 'foxnews:insider'
@ -83,7 +113,11 @@ class FoxNewsInsiderIE(InfoExtractor):
'upload_date': '20160825', 'upload_date': '20160825',
'thumbnail': 're:^https?://.*\.jpg$', 'thumbnail': 're:^https?://.*\.jpg$',
}, },
'add_ie': [FoxNewsIE.ie_key()], 'params': {
# m3u8 download
'skip_download': True,
},
'add_ie': [FoxNewsVideoIE.ie_key()],
} }
def _real_extract(self, url): def _real_extract(self, url):
@ -98,7 +132,7 @@ def _real_extract(self, url):
return { return {
'_type': 'url_transparent', '_type': 'url_transparent',
'ie_key': FoxNewsIE.ie_key(), 'ie_key': FoxNewsVideoIE.ie_key(),
'url': embed_url, 'url': embed_url,
'display_id': display_id, 'display_id': display_id,
'title': title, 'title': title,