[seeker] Add new extractor(closes #9619)

This commit is contained in:
Remita Amine 2016-06-01 21:20:02 +01:00
parent f4e4aa9b6b
commit 4a684895c0
2 changed files with 62 additions and 1 deletions

View file

@ -639,7 +639,10 @@
from .restudy import RestudyIE from .restudy import RestudyIE
from .reuters import ReutersIE from .reuters import ReutersIE
from .reverbnation import ReverbNationIE from .reverbnation import ReverbNationIE
from .revision3 import Revision3IE from .revision3 import (
Revision3EmbedIE,
Revision3IE,
)
from .rice import RICEIE from .rice import RICEIE
from .ringtv import RingTVIE from .ringtv import RingTVIE
from .ro220 import Ro220IE from .ro220 import Ro220IE
@ -678,6 +681,7 @@
from .screencastomatic import ScreencastOMaticIE from .screencastomatic import ScreencastOMaticIE
from .screenjunkies import ScreenJunkiesIE from .screenjunkies import ScreenJunkiesIE
from .screenwavemedia import ScreenwaveMediaIE, TeamFourIE from .screenwavemedia import ScreenwaveMediaIE, TeamFourIE
from .seeker import SeekerIE
from .senateisvp import SenateISVPIE from .senateisvp import SenateISVPIE
from .sendtonews import SendtoNewsIE from .sendtonews import SendtoNewsIE
from .servingsys import ServingSysIE from .servingsys import ServingSysIE

View file

@ -0,0 +1,57 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
class SeekerIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?seeker\.com/(?P<display_id>.*)-(?P<article_id>\d+)\.html'
_TESTS = [{
# player.loadRevision3Item
'url': 'http://www.seeker.com/should-trump-be-required-to-release-his-tax-returns-1833805621.html',
'md5': '30c1dc4030cc715cf05b423d0947ac18',
'info_dict': {
'id': '76243',
'ext': 'webm',
'title': 'Should Trump Be Required To Release His Tax Returns?',
'description': 'Donald Trump has been secretive about his "big," "beautiful" tax returns. So what can we learn if he decides to release them?',
'uploader': 'Seeker Daily',
'uploader_id': 'seekerdaily',
}
}, {
'url': 'http://www.seeker.com/changes-expected-at-zoos-following-recent-gorilla-lion-shootings-1834116536.html',
'playlist': [
{
'md5': '83bcd157cab89ad7318dd7b8c9cf1306',
'info_dict': {
'id': '67558',
'ext': 'mp4',
'title': 'The Pros & Cons Of Zoos',
'description': 'Zoos are often depicted as a terrible place for animals to live, but is there any truth to this?',
'uploader': 'DNews',
'uploader_id': 'dnews',
},
}
],
'info_dict': {
'id': '1834116536',
'title': 'After Gorilla Killing, Changes Ahead for Zoos',
'description': 'The largest association of zoos and others are hoping to learn from recent incidents that led to the shooting deaths of a gorilla and two lions.',
},
}]
def _real_extract(self, url):
display_id, article_id = re.match(self._VALID_URL, url).groups()
webpage = self._download_webpage(url, display_id)
mobj = re.search(r"player\.loadRevision3Item\('([^']+)'\s*,\s*(\d+)\);", webpage)
if mobj:
playlist_type, playlist_id = mobj.groups()
return self.url_result(
'revision3:%s:%s' % (playlist_type, playlist_id), 'Revision3Embed', playlist_id)
else:
entries = [self.url_result('revision3:video_id:%s' % video_id, 'Revision3Embed', video_id) for video_id in re.findall(
r'<iframe[^>]+src=[\'"](?:https?:)?//api\.seekernetwork\.com/player/embed\?videoId=(\d+)', webpage)]
return self.playlist_result(
entries, article_id, self._og_search_title(webpage), self._og_search_description(webpage))