[drtv] Add support for dr.dk/nyheder

It's the same video player, the only difference is that the video player
is loaded differently, and certain metadata (title and description) is
not available under dr.dk/mu, so make it by default get that from some
of the html meta tags.

Skip the dr.dk/tv test

dr.dk/tv videos are only available for between 7 and 90 days due to
Danish law, and in certain cases may be readded. Skip this test as it is
no longer available.
This commit is contained in:
Sebastian Blunt 2016-09-02 14:48:56 +02:00 committed by Sergey M․
parent 349fc5c705
commit 5e9e3d0f6b
No known key found for this signature in database
GPG Key ID: 2C393E0F18A9236D
1 changed files with 22 additions and 6 deletions

View File

@ -5,13 +5,14 @@ from .common import InfoExtractor
from ..utils import ( from ..utils import (
ExtractorError, ExtractorError,
parse_iso8601, parse_iso8601,
remove_end,
) )
class DRTVIE(InfoExtractor): class DRTVIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?dr\.dk/tv/se/(?:[^/]+/)*(?P<id>[\da-z-]+)(?:[/#?]|$)' _VALID_URL = r'https?://(?:www\.)?dr\.dk/(?:tv/se|nyheder)/(?:[^/]+/)*(?P<id>[\da-z-]+)(?:[/#?]|$)'
_TEST = { _TESTS = [{
'url': 'https://www.dr.dk/tv/se/boern/ultra/panisk-paske/panisk-paske-5', 'url': 'https://www.dr.dk/tv/se/boern/ultra/panisk-paske/panisk-paske-5',
'md5': 'dc515a9ab50577fa14cc4e4b0265168f', 'md5': 'dc515a9ab50577fa14cc4e4b0265168f',
'info_dict': { 'info_dict': {
@ -23,7 +24,20 @@ class DRTVIE(InfoExtractor):
'upload_date': '20150322', 'upload_date': '20150322',
'duration': 1455, 'duration': 1455,
}, },
} 'skip': 'Video is no longer available',
}, {
'url': 'https://www.dr.dk/nyheder/indland/live-christianias-rydning-af-pusher-street-er-i-gang',
'md5': '2ada5074f9e79afc0d324a8e9784d850',
'info_dict': {
'id': 'christiania-pusher-street-ryddes-drdkrjpo',
'ext': 'mp4',
'title': 'LIVE Christianias rydning af Pusher Street er i gang',
'description': '- Det er det fedeste, der er sket i 20 år, fortæller christianit til DR Nyheder.',
'timestamp': 1472800279,
'upload_date': '20160902',
'duration': 131.4,
}
}]
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
@ -35,7 +49,8 @@ class DRTVIE(InfoExtractor):
'Video %s is not available' % video_id, expected=True) 'Video %s is not available' % video_id, expected=True)
video_id = self._search_regex( video_id = self._search_regex(
r'data-(?:material-identifier|episode-slug)="([^"]+)"', (r'data-(?:material-identifier|episode-slug)="([^"]+)"',
r'data-resource="[^>"]+mu/programcard/expanded/([^"]+)"'),
webpage, 'video id') webpage, 'video id')
programcard = self._download_json( programcard = self._download_json(
@ -43,8 +58,9 @@ class DRTVIE(InfoExtractor):
video_id, 'Downloading video JSON') video_id, 'Downloading video JSON')
data = programcard['Data'][0] data = programcard['Data'][0]
title = data['Title'] title = remove_end(self._og_search_title(webpage), ' | TV | DR') or data['Title']
description = data['Description'] description = self._og_search_description(webpage) or data['Description']
timestamp = parse_iso8601(data['CreatedTime']) timestamp = parse_iso8601(data['CreatedTime'])
thumbnail = None thumbnail = None