aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/spiegel.py
diff options
context:
space:
mode:
Diffstat (limited to 'youtube_dl/extractor/spiegel.py')
-rw-r--r--youtube_dl/extractor/spiegel.py144
1 files changed, 30 insertions, 114 deletions
diff --git a/youtube_dl/extractor/spiegel.py b/youtube_dl/extractor/spiegel.py
index 39a7aaf9d..2da32b9b2 100644
--- a/youtube_dl/extractor/spiegel.py
+++ b/youtube_dl/extractor/spiegel.py
@@ -1,138 +1,54 @@
-# encoding: utf-8
+# coding: utf-8
from __future__ import unicode_literals
-import re
-
from .common import InfoExtractor
-from ..compat import compat_urlparse
-from .spiegeltv import SpiegeltvIE
+from .jwplatform import JWPlatformIE
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 = [{
'url': 'http://www.spiegel.de/video/vulkan-tungurahua-in-ecuador-ist-wieder-aktiv-video-1259285.html',
- 'md5': '2c2754212136f35fb4b19767d242f66e',
+ 'md5': '50c7948883ec85a3e431a0a44b7ad1d6',
'info_dict': {
- 'id': '1259285',
+ 'id': 'II0BUyxY',
+ 'display_id': '1259285',
'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',
- 'duration': 49,
+ 'duration': 48.0,
+ 'upload_date': '20130311',
+ 'timestamp': 1362997920,
},
}, {
'url': 'http://www.spiegel.de/video/schach-wm-videoanalyse-des-fuenften-spiels-video-1309159.html',
- 'md5': 'f2cdf638d7aa47654e251e1aee360af1',
- 'info_dict': {
- 'id': '1309159',
- 'ext': 'mp4',
- 'title': 'Schach-WM in der Videoanalyse: Carlsen nutzt die Fehlgriffe des Titelverteidigers',
- 'description': 'md5:c2322b65e58f385a820c10fa03b2d088',
- 'duration': 983,
- },
+ 'only_matching': True,
}, {
- 'url': 'http://www.spiegel.de/video/astronaut-alexander-gerst-von-der-iss-station-beantwortet-fragen-video-1519126-embed.html',
- 'md5': 'd8eeca6bfc8f1cd6f490eb1f44695d51',
- 'info_dict': {
- 'id': '1519126',
- '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?"',
- }
+ '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/astronaut-alexander-gerst-von-der-iss-station-beantwortet-fragen-video-1519126-iframe.html',
+ 'url': 'http://www.spiegel.de/video/spiegel-tv-magazin-ueber-guellekrise-in-schleswig-holstein-video-99012776.html',
+ 'only_matching': True,
+ }, {
+ 'url': 'http://www.spiegel.de/sport/sonst/badminton-wm-die-randsportart-soll-populaerer-werden-a-987092.html',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
- webpage, handle = self._download_webpage_handle(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')
-
- title = re.sub(r'\s+', ' ', self._html_search_regex(
- r'(?s)<(?:h1|div) class="module-title"[^>]*>(.*?)</(?:h1|div)>',
- webpage, 'title'))
- description = self._html_search_meta('description', webpage, 'description')
-
- base_url = self._search_regex(
- [r'server\s*:\s*(["\'])(?P<url>.+?)\1', r'var\s+server\s*=\s*"(?P<url>[^"]+)\"'],
- webpage, 'server URL', group='url')
-
- xml_url = base_url + video_id + '.xml'
- idoc = self._download_xml(xml_url, video_id)
-
- formats = []
- for n in list(idoc):
- if n.tag.startswith('type') and n.tag != 'type6':
- format_id = n.tag.rpartition('type')[2]
- video_url = base_url + n.find('./filename').text
- formats.append({
- 'format_id': format_id,
- 'url': video_url,
- 'width': int(n.find('./width').text),
- 'height': int(n.find('./height').text),
- 'abr': int(n.find('./audiobitrate').text),
- 'vbr': int(n.find('./videobitrate').text),
- 'vcodec': n.find('./codec').text,
- 'acodec': 'MP4A',
- })
- duration = float(idoc[0].findall('./duration')[0].text)
-
- self._check_formats(formats, video_id)
- self._sort_formats(formats)
-
+ webpage = self._download_webpage(url, video_id)
+ media_id = self._html_search_regex(
+ r'(&#34;|["\'])mediaId\1\s*:\s*(&#34;|["\'])(?P<id>(?:(?!\2).)+)\2',
+ webpage, 'media id', group='id')
return {
+ '_type': 'url_transparent',
'id': video_id,
- 'title': title,
- 'description': description,
- 'duration': duration,
- 'formats': formats,
+ 'display_id': video_id,
+ 'url': 'jwplatform:%s' % media_id,
+ 'title': self._og_search_title(webpage, default=None),
+ 'ie_key': JWPlatformIE.ie_key(),
}
-
-
-class SpiegelArticleIE(InfoExtractor):
- _VALID_URL = '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',
- 'info_dict': {
- 'id': '1516455',
- 'ext': 'mp4',
- 'title': 'Faszination Badminton: Nennt es bloß nicht Federball',
- 'description': 're:^Patrick Kämnitz gehört.{100,}',
- },
- }, {
- 'url': 'http://www.spiegel.de/wissenschaft/weltall/astronaut-alexander-gerst-antwortet-spiegel-online-lesern-a-989876.html',
- 'info_dict': {
-
- },
- 'playlist_count': 6,
- }]
-
- def _real_extract(self, url):
- video_id = self._match_id(url)
- webpage = self._download_webpage(url, video_id)
-
- # Single video on top of the page
- video_link = self._search_regex(
- r'<a href="([^"]+)" onclick="return spOpenVideo\(this,', webpage,
- 'video page URL', default=None)
- if video_link:
- video_url = compat_urlparse.urljoin(
- self.http_scheme() + '//spiegel.de/', video_link)
- return self.url_result(video_url)
-
- # 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
- ]
- return self.playlist_result(entries)
generated by cgit v1.2.3 (git 2.26.2) at 2025-11-02 07:46:03 +0000