w/youtube-dl
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

[spiegel] Add support for nexx videos (closes #15285)

Browse source
This commit is contained in:
Sergey M․ 2018-01-17 22:03:56 +07:00
parent 1370dba59f
commit 4471affc34
No known key found for this signature in database
GPG key ID: 2C393E0F18A9236D
1 changed files with 16 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

17
youtube_dl/extractor/spiegel.py
View file

@ -4,7 +4,10 @@ from __future__ import unicode_literals
import re import re
from .common import InfoExtractor from .common import InfoExtractor
from .nexx import NexxEmbedIE from .nexx import (
NexxIE,
NexxEmbedIE,
)
from .spiegeltv import SpiegeltvIE from .spiegeltv import SpiegeltvIE
from ..compat import compat_urlparse from ..compat import compat_urlparse
from ..utils import ( from ..utils import (
@ -51,6 +54,10 @@ class SpiegelIE(InfoExtractor):
}, { }, {
'url': 'http://www.spiegel.de/video/astronaut-alexander-gerst-von-der-iss-station-beantwortet-fragen-video-1519126-iframe.html', 'url': 'http://www.spiegel.de/video/astronaut-alexander-gerst-von-der-iss-station-beantwortet-fragen-video-1519126-iframe.html',
'only_matching': True, 'only_matching': True,
}, {
# nexx video
'url': 'http://www.spiegel.de/video/spiegel-tv-magazin-ueber-guellekrise-in-schleswig-holstein-video-99012776.html',
'only_matching': True,
}] }]
def _real_extract(self, url): def _real_extract(self, url):
@ -61,6 +68,14 @@ class SpiegelIE(InfoExtractor):
if SpiegeltvIE.suitable(handle.geturl()): if SpiegeltvIE.suitable(handle.geturl()):
return self.url_result(handle.geturl(), 'Spiegeltv') return self.url_result(handle.geturl(), 'Spiegeltv')
nexx_id = self._search_regex(
r'nexxOmniaId\s*:\s*(\d+)', webpage, 'nexx id', default=None)
if nexx_id:
domain_id = NexxIE._extract_domain_id(webpage) or '748'
return self.url_result(
'nexx:%s:%s' % (domain_id, nexx_id), ie=NexxIE.ie_key(),
video_id=nexx_id)
video_data = extract_attributes(self._search_regex(r'(<div[^>]+id="spVideoElements"[^>]+>)', webpage, 'video element', default='')) video_data = extract_attributes(self._search_regex(r'(<div[^>]+id="spVideoElements"[^>]+>)', webpage, 'video element', default=''))
title = video_data.get('data-video-title') or get_element_by_attribute('class', 'module-title', webpage) title = video_data.get('data-video-title') or get_element_by_attribute('class', 'module-title', webpage)