[foxnews:insider] Add new extractor

Closes #10445
pull/10542/head
Yen Chi Hsuan 2016-09-03 18:16:19 +08:00
parent cf0efe9636
commit cdc783510b
No known key found for this signature in database
GPG Key ID: 3FDDD575826C5C30
3 changed files with 52 additions and 2 deletions

View File

@ -1,6 +1,7 @@
version <unreleased>
Extractors
+ [foxnews] Add support for FoxNews Insider (#10445)
+ [fc2] Recognize Flash player URLs (#10512)

View File

@ -287,7 +287,10 @@ from .formula1 import Formula1IE
from .fourtube import FourTubeIE
from .fox import FOXIE
from .foxgay import FoxgayIE
from .foxnews import FoxNewsIE
from .foxnews import (
FoxNewsIE,
FoxNewsInsiderIE,
)
from .foxsports import FoxSportsIE
from .franceculture import FranceCultureIE
from .franceinter import FranceInterIE

View File

@ -3,11 +3,12 @@ from __future__ import unicode_literals
import re
from .amp import AMPIE
from .common import InfoExtractor
class FoxNewsIE(AMPIE):
IE_DESC = 'Fox News and Fox Business Video'
_VALID_URL = r'https?://(?P<host>video\.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 = [
{
'url': 'http://video.foxnews.com/v/3937480/frozen-in-time/#sp=show-clips',
@ -49,6 +50,11 @@ class FoxNewsIE(AMPIE):
'url': 'http://video.foxbusiness.com/v/4442309889001',
'only_matching': True,
},
{
# From http://insider.foxnews.com/2016/08/25/univ-wisconsin-student-group-pushing-silence-certain-words
'url': 'http://video.insider.foxnews.com/v/video-embed.html?video_id=5099377331001&autoplay=true&share_url=http://insider.foxnews.com/2016/08/25/univ-wisconsin-student-group-pushing-silence-certain-words&share_title=Student%20Group:%20Saying%20%27Politically%20Correct,%27%20%27Trash%27%20and%20%27Lame%27%20Is%20Offensive&share=true',
'only_matching': True,
},
]
def _real_extract(self, url):
@ -58,3 +64,43 @@ class FoxNewsIE(AMPIE):
'http://%s/v/feed/video/%s.js?template=fox' % (host, video_id))
info['id'] = video_id
return info
class FoxNewsInsiderIE(InfoExtractor):
_VALID_URL = r'https?://insider\.foxnews\.com/([^/]+/)+(?P<id>[a-z-]+)'
IE_NAME = 'foxnews:insider'
_TEST = {
'url': 'http://insider.foxnews.com/2016/08/25/univ-wisconsin-student-group-pushing-silence-certain-words',
'md5': 'a10c755e582d28120c62749b4feb4c0c',
'info_dict': {
'id': '5099377331001',
'display_id': 'univ-wisconsin-student-group-pushing-silence-certain-words',
'ext': 'mp4',
'title': 'Student Group: Saying \'Politically Correct,\' \'Trash\' and \'Lame\' Is Offensive',
'description': 'Is campus censorship getting out of control?',
'timestamp': 1472168725,
'upload_date': '20160825',
'thumbnail': 're:^https?://.*\.jpg$',
},
'add_ie': [FoxNewsIE.ie_key()],
}
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
embed_url = self._html_search_meta('embedUrl', webpage, 'embed URL')
title = self._og_search_title(webpage)
description = self._og_search_description(webpage)
return {
'_type': 'url_transparent',
'ie_key': FoxNewsIE.ie_key(),
'url': embed_url,
'display_id': display_id,
'title': title,
'description': description,
}