[CPTwentyFour] Add extractor (#1769)

Closes #1768
Authored by: Ashish0804
This commit is contained in:
Ashish Gupta 2021-11-27 12:01:42 +05:30 committed by GitHub
parent cf1f13b817
commit 3938a9212c
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 38 additions and 2 deletions

View File

@ -943,7 +943,10 @@
NicovideoSearchIE, NicovideoSearchIE,
NicovideoSearchURLIE, NicovideoSearchURLIE,
) )
from .ninecninemedia import NineCNineMediaIE from .ninecninemedia import (
NineCNineMediaIE,
CPTwentyFourIE,
)
from .ninegag import NineGagIE from .ninegag import NineGagIE
from .ninenow import NineNowIE from .ninenow import NineNowIE
from .nintendo import NintendoIE from .nintendo import NintendoIE

View File

@ -1,7 +1,6 @@
# coding: utf-8 # coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
float_or_none, float_or_none,
@ -99,3 +98,37 @@ def _real_extract(self, url):
} }
return info return info
class CPTwentyFourIE(InfoExtractor):
IE_NAME = 'cp24'
_GEO_COUNTRIES = ['CA']
_VALID_URL = r'https?://(?:www\.)?cp24\.com/news/(?P<id>[^?#]+)'
_TESTS = [{
'url': 'https://www.cp24.com/news/video-shows-atm-being-ripped-out-of-business-by-pickup-truck-driver-in-mississauga-1.5676877',
'info_dict': {
'id': '2328005',
'ext': 'mp4',
'title': 'WATCH: Truck rips ATM from Mississauga business',
'description': 'md5:cf7498480885f080a754389a2b2f7073',
'timestamp': 1637618377,
'episode_number': None,
'season': 'Season 0',
'season_number': 0,
'season_id': 57974,
'series': 'CTV News Toronto',
'duration': 26.86,
'thumbnail': 'http://images2.9c9media.com/image_asset/2014_11_5_2eb609a0-475b-0132-fbd6-34b52f6f1279_jpg_2000x1125.jpg',
'upload_date': '20211122',
},
'params': {'skip_download': True, 'format': 'bv'}
}]
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
id, destination = self._search_regex(
r'getAuthStates\("(?P<id>[^"]+)",\s?"(?P<destination>[^"]+)"\);',
webpage, 'video id and destination', group=('id', 'destination'))
return self.url_result(f'9c9media:{destination}:{id}', ie=NineCNineMediaIE.ie_key(), video_id=id)