[spiegel] Fix extractor

youtube_dl/extractor/extractors.py

@@ -1041,8 +1041,7 @@ from .spankbang import (
     SpankBangPlaylistIE,
 )
 from .spankwire import SpankwireIE
-from .spiegel import SpiegelIE, SpiegelArticleIE
+from .spiegel import SpiegelIE
-from .spiegeltv import SpiegeltvIE
 from .spike import (
     BellatorIE,
     ParamountNetworkIE,

youtube_dl/extractor/spiegel.py

@@ -1,159 +1,81 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import re
-
 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):
-    _VALID_URL = r'https?://(?:www\.)?spiegel\.de/video/[^/]*-(?P<id>[0-9]+)(?:-embed|-iframe)?(?:\.html)?(?:#.*)?$'
+    _UUID_RE = r'[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12}'
+    _VALID_URL = r'https?://(?:www\.)?spiegel\.de(?:/[^/]+)+/[^/]*-(?P<id>[0-9]+|%s)(?:-embed|-iframe)?(?:\.html)?(?:#.*)?$' % _UUID_RE
     _TESTS = [{
         'url': 'http://www.spiegel.de/video/vulkan-tungurahua-in-ecuador-ist-wieder-aktiv-video-1259285.html',
-        'md5': 'b57399839d055fccfeb9a0455c439868',
+        'md5': '50c7948883ec85a3e431a0a44b7ad1d6',
         'info_dict': {
-            'id': '563747',
+            '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': 1362994320,
+            'timestamp': 1362997920,
         },
     }, {
         'url': 'http://www.spiegel.de/video/schach-wm-videoanalyse-des-fuenften-spiels-video-1309159.html',
-        'md5': '5b6c2f4add9d62912ed5fc78a1faed80',
+        'md5': '103904ada1044098f20c34b579eb7cd5',
         'info_dict': {
-            'id': '580988',
+            'id': 'ALIzWLZJ',
+            'display_id': '1309159',
             'ext': 'mp4',
-            'title': 'Schach-WM in der Videoanalyse: Carlsen nutzt die Fehlgriffe des Titelverteidigers',
+            'title': 'Schach-WM: Videoanalyse des fünften Spiels - DER SPIEGEL - Sport',
             'description': 'md5:c2322b65e58f385a820c10fa03b2d088',
             'duration': 983,
             'upload_date': '20131115',
-            'timestamp': 1384546642,
+            'timestamp': 1384550242,
         },
     }, {
-        'url': 'http://www.spiegel.de/video/astronaut-alexander-gerst-von-der-iss-station-beantwortet-fragen-video-1519126-embed.html',
+        'url': 'https://www.spiegel.de/video/eifel-zoo-aufregung-um-ausgebrochene-raubtiere-video-99018031.html',
-        'md5': '97b91083a672d72976faa8433430afb9',
+        'md5': '8089007d406837b8f320fa5a97d22b20',
         'info_dict': {
-            'id': '601883',
+            'id': 'FMLessGS',
+            'display_id': '99018031',
             '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': 'Eifel-Zoo: Aufregung um ausgebrochene Raubtiere - DER SPIEGEL - Panorama',
-            'title': 'Fragen an Astronaut Alexander Gerst: "Bekommen Sie die Tageszeiten mit?"',
+            'description': 'md5:7d7a7d9066526203c001bad6ca84c4bf',
-            'upload_date': '20140904',
+            'duration': 112.0,
-            'timestamp': 1409834160,
+            'timestamp': 1527874810,
-        }
+            'upload_date': '20180601',
+        },
     }, {
-        'url': 'http://www.spiegel.de/video/astronaut-alexander-gerst-von-der-iss-station-beantwortet-fragen-video-1519126-iframe.html',
+        'url': 'https://www.spiegel.de/panorama/urteile-im-goldmuenzenprozess-haftstrafen-fuer-clanmitglieder-a-aae8df48-43c1-4c61-867d-23f0a2d254b7',
-        'only_matching': True,
+        'md5': '41eeb224bf869e90606bb7d68f5bdd21',
+        'info_dict': {
+            'id': 'RM8hNagK',
+            'display_id': 'aae8df48-43c1-4c61-867d-23f0a2d254b7',
+            'ext': 'mp4',
+            'title': 'Haftstrafen für Clanmitglieder: SPIEGEL TV über Urteile im Goldmünzenprozess - DER SPIEGEL - Panorama',
+            'description': 'md5:eb1ead19809f8cca2e35c22077e2f792',
+            'timestamp': 1582618271,
+            'upload_date': '20200225'
+        },
     }, {
-        # 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):
-        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',
-        '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):
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
-
+        media_id = self._html_search_regex(r'&#34;mediaId&#34;:&#34;(\w+)&#34;', webpage, "media id")
-        # Single video on top of the page
+        return {
-        video_link = self._search_regex(
+            '_type': 'url_transparent',
-            r'<a href="([^"]+)" onclick="return spOpenVideo\(this,', webpage,
+            'id': video_id,
-            'video page URL', default=None)
+            'display_id': video_id,
-        if video_link:
+            'url': 'jwplatform:%s' % media_id,
-            video_url = compat_urlparse.urljoin(
+            'title': self._og_search_title(webpage),
-                self.http_scheme() + '//spiegel.de/', video_link)
+            'ie_key': JWPlatformIE.ie_key(),
-            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]
-        if embeds:
-            return self.playlist_result(entries)
-
-        return self.playlist_from_matches(
-            NexxEmbedIE._extract_urls(webpage), ie=NexxEmbedIE.ie_key())

youtube_dl/extractor/spiegeltv.py

@@ -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())