[spiegel] Fix extraction (closes #24206, closes #24767)

Code picked from PR #24767 since original repo is not available due to takedown.
pull/27078/head
Sergey M․ 2020-11-18 04:09:02 +07:00
parent 2864179293
commit 2d7a29081c
No known key found for this signature in database
GPG Key ID: 2C393E0F18A9236D
3 changed files with 29 additions and 152 deletions

View File

@ -1054,8 +1054,7 @@ from .spankbang import (
SpankBangPlaylistIE, SpankBangPlaylistIE,
) )
from .spankwire import SpankwireIE from .spankwire import SpankwireIE
from .spiegel import SpiegelIE, SpiegelArticleIE from .spiegel import SpiegelIE
from .spiegeltv import SpiegeltvIE
from .spike import ( from .spike import (
BellatorIE, BellatorIE,
ParamountNetworkIE, ParamountNetworkIE,

View File

@ -1,159 +1,54 @@
# coding: utf-8 # coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
import re
from .common import InfoExtractor from .common import InfoExtractor
from .nexx import ( from .jwplatform import JWPlatformIE
NexxIE,
NexxEmbedIE,
)
from .spiegeltv import SpiegeltvIE
from ..compat import compat_urlparse
from ..utils import (
parse_duration,
strip_or_none,
unified_timestamp,
)
class SpiegelIE(InfoExtractor): class SpiegelIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?spiegel\.de/video/[^/]*-(?P<id>[0-9]+)(?:-embed|-iframe)?(?:\.html)?(?:#.*)?$' _UUID_RE = r'[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12}'
_VALID_URL = r'https?://(?:www\.)?(?:spiegel|manager-magazin)\.de(?:/[^/]+)+/[^/]*-(?P<id>[0-9]+|%s)(?:-embed|-iframe)?(?:\.html)?(?:#.*)?$' % _UUID_RE
_TESTS = [{ _TESTS = [{
'url': 'http://www.spiegel.de/video/vulkan-tungurahua-in-ecuador-ist-wieder-aktiv-video-1259285.html', 'url': 'http://www.spiegel.de/video/vulkan-tungurahua-in-ecuador-ist-wieder-aktiv-video-1259285.html',
'md5': 'b57399839d055fccfeb9a0455c439868', 'md5': '50c7948883ec85a3e431a0a44b7ad1d6',
'info_dict': { 'info_dict': {
'id': '563747', 'id': 'II0BUyxY',
'display_id': '1259285',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Vulkanausbruch in Ecuador: Der "Feuerschlund" ist wieder aktiv', 'title': 'Vulkan Tungurahua in Ecuador ist wieder aktiv - DER SPIEGEL - Wissenschaft',
'description': 'md5:8029d8310232196eb235d27575a8b9f4', 'description': 'md5:8029d8310232196eb235d27575a8b9f4',
'duration': 49, 'duration': 48.0,
'upload_date': '20130311', 'upload_date': '20130311',
'timestamp': 1362994320, 'timestamp': 1362997920,
}, },
}, { }, {
'url': 'http://www.spiegel.de/video/schach-wm-videoanalyse-des-fuenften-spiels-video-1309159.html', 'url': 'http://www.spiegel.de/video/schach-wm-videoanalyse-des-fuenften-spiels-video-1309159.html',
'md5': '5b6c2f4add9d62912ed5fc78a1faed80',
'info_dict': {
'id': '580988',
'ext': 'mp4',
'title': 'Schach-WM in der Videoanalyse: Carlsen nutzt die Fehlgriffe des Titelverteidigers',
'description': 'md5:c2322b65e58f385a820c10fa03b2d088',
'duration': 983,
'upload_date': '20131115',
'timestamp': 1384546642,
},
}, {
'url': 'http://www.spiegel.de/video/astronaut-alexander-gerst-von-der-iss-station-beantwortet-fragen-video-1519126-embed.html',
'md5': '97b91083a672d72976faa8433430afb9',
'info_dict': {
'id': '601883',
'ext': 'mp4',
'description': 'SPIEGEL ONLINE-Nutzer durften den deutschen Astronauten Alexander Gerst über sein Leben auf der ISS-Station befragen. Hier kommen seine Antworten auf die besten sechs Fragen.',
'title': 'Fragen an Astronaut Alexander Gerst: "Bekommen Sie die Tageszeiten mit?"',
'upload_date': '20140904',
'timestamp': 1409834160,
}
}, {
'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': 'https://www.spiegel.de/video/eifel-zoo-aufregung-um-ausgebrochene-raubtiere-video-99018031.html',
'only_matching': True,
}, {
'url': 'https://www.spiegel.de/panorama/urteile-im-goldmuenzenprozess-haftstrafen-fuer-clanmitglieder-a-aae8df48-43c1-4c61-867d-23f0a2d254b7',
'only_matching': True,
}, {
'url': 'http://www.spiegel.de/video/spiegel-tv-magazin-ueber-guellekrise-in-schleswig-holstein-video-99012776.html', 'url': 'http://www.spiegel.de/video/spiegel-tv-magazin-ueber-guellekrise-in-schleswig-holstein-video-99012776.html',
'only_matching': True, 'only_matching': True,
}] }, {
def _real_extract(self, url):
video_id = self._match_id(url)
metadata_url = 'http://www.spiegel.de/video/metadata/video-%s.json' % video_id
handle = self._request_webpage(metadata_url, video_id)
# 302 to spiegel.tv, like http://www.spiegel.de/video/der-film-zum-wochenende-die-wahrheit-ueber-maenner-video-99003272.html
if SpiegeltvIE.suitable(handle.geturl()):
return self.url_result(handle.geturl(), 'Spiegeltv')
video_data = self._parse_json(self._webpage_read_content(
handle, metadata_url, video_id), video_id)
title = video_data['title']
nexx_id = video_data['nexxOmniaId']
domain_id = video_data.get('nexxOmniaDomain') or '748'
return {
'_type': 'url_transparent',
'id': video_id,
'url': 'nexx:%s:%s' % (domain_id, nexx_id),
'title': title,
'description': strip_or_none(video_data.get('teaser')),
'duration': parse_duration(video_data.get('duration')),
'timestamp': unified_timestamp(video_data.get('datum')),
'ie_key': NexxIE.ie_key(),
}
class SpiegelArticleIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?spiegel\.de/(?!video/)[^?#]*?-(?P<id>[0-9]+)\.html'
IE_NAME = 'Spiegel:Article'
IE_DESC = 'Articles on spiegel.de'
_TESTS = [{
'url': 'http://www.spiegel.de/sport/sonst/badminton-wm-die-randsportart-soll-populaerer-werden-a-987092.html', 'url': 'http://www.spiegel.de/sport/sonst/badminton-wm-die-randsportart-soll-populaerer-werden-a-987092.html',
'info_dict': { 'only_matching': True,
'id': '1516455',
'ext': 'mp4',
'title': 'Faszination Badminton: Nennt es bloß nicht Federball',
'description': 're:^Patrick Kämnitz gehört.{100,}',
'upload_date': '20140825',
},
}, {
'url': 'http://www.spiegel.de/wissenschaft/weltall/astronaut-alexander-gerst-antwortet-spiegel-online-lesern-a-989876.html',
'info_dict': {
},
'playlist_count': 6,
}, {
# Nexx iFrame embed
'url': 'http://www.spiegel.de/sptv/spiegeltv/spiegel-tv-ueber-schnellste-katapult-achterbahn-der-welt-taron-a-1137884.html',
'info_dict': {
'id': '161464',
'ext': 'mp4',
'title': 'Nervenkitzel Achterbahn',
'alt_title': 'Karussellbauer in Deutschland',
'description': 'md5:ffe7b1cc59a01f585e0569949aef73cc',
'release_year': 2005,
'creator': 'SPIEGEL TV',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 2761,
'timestamp': 1394021479,
'upload_date': '20140305',
},
'params': {
'format': 'bestvideo',
'skip_download': True,
},
}] }]
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
media_id = self._html_search_regex(
# Single video on top of the page r'(&#34;|["\'])mediaId\1\s*:\s*(&#34;|["\'])(?P<id>(?:(?!\2).)+)\2',
video_link = self._search_regex( webpage, 'media id', group='id')
r'<a href="([^"]+)" onclick="return spOpenVideo\(this,', webpage, return {
'video page URL', default=None) '_type': 'url_transparent',
if video_link: 'id': video_id,
video_url = compat_urlparse.urljoin( 'display_id': video_id,
self.http_scheme() + '//spiegel.de/', video_link) 'url': 'jwplatform:%s' % media_id,
return self.url_result(video_url) 'title': self._og_search_title(webpage, default=None),
'ie_key': JWPlatformIE.ie_key(),
# Multiple embedded videos }
embeds = re.findall(
r'<div class="vid_holder[0-9]+.*?</div>\s*.*?url\s*=\s*"([^"]+)"',
webpage)
entries = [
self.url_result(compat_urlparse.urljoin(
self.http_scheme() + '//spiegel.de/', embed_path))
for embed_path in embeds]
if embeds:
return self.playlist_result(entries)
return self.playlist_from_matches(
NexxEmbedIE._extract_urls(webpage), ie=NexxEmbedIE.ie_key())

View File

@ -1,17 +0,0 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from .nexx import NexxIE
class SpiegeltvIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?spiegel\.tv/videos/(?P<id>\d+)'
_TEST = {
'url': 'http://www.spiegel.tv/videos/161681-flug-mh370/',
'only_matching': True,
}
def _real_extract(self, url):
return self.url_result(
'https://api.nexx.cloud/v3/748/videos/byid/%s'
% self._match_id(url), ie=NexxIE.ie_key())