[spiegel] Modernize

[youtube-dl] / youtube_dl / extractor / spiegel.py

diff --git a/youtube_dl/extractor/spiegel.py b/youtube_dl/extractor/spiegel.py
index 340a38440d02ad28b5eb6ab19916eee870818c35..4b4da43d1da12356705d275139ccbb409e5f1f85 100644 (file)
--- a/youtube_dl/extractor/spiegel.py
+++ b/youtube_dl/extractor/spiegel.py
@@ -4,10 +4,11 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..utils import compat_urlparse
 
 
 class SpiegelIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?spiegel\.de/video/[^/]*-(?P<videoID>[0-9]+)(?:\.html)?(?:#.*)?$'
+    _VALID_URL = r'https?://(?:www\.)?spiegel\.de/video/[^/]*-(?P<id>[0-9]+)(?:\.html)?(?:#.*)?$'
     _TESTS = [{
         'url': 'http://www.spiegel.de/video/vulkan-tungurahua-in-ecuador-ist-wieder-aktiv-video-1259285.html',
         'md5': '2c2754212136f35fb4b19767d242f66e',
@@ -28,22 +29,10 @@ class SpiegelIE(InfoExtractor):
             'description': 'md5:c2322b65e58f385a820c10fa03b2d088',
             'duration': 983,
         },
-    }, {
-        'url': 'http://www.spiegel.de/video/johann-westhauser-videobotschaft-des-hoehlenforschers-video-1502367.html',
-        'md5': '54f58ba0e752e3c07bc2a26222dd0acf',
-        'info_dict': {
-            'id': '1502367',
-            'ext': 'mp4',
-            'title': 'Videobotschaft: Höhlenforscher Westhauser dankt seinen Rettern',
-            'description': 'md5:c6f1ec11413ebd1088b6813943e5fc91',
-            'duration': 42,
-        },
     }]
 
     def _real_extract(self, url):
-        m = re.match(self._VALID_URL, url)
-        video_id = m.group('videoID')
-
+        video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
         title = self._html_search_regex(
@@ -82,3 +71,33 @@ class SpiegelIE(InfoExtractor):
             'duration': duration,
             'formats': formats,
         }
+
+
+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'
+    _TEST = {
+        '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,}',
+        },
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+        video_link = self._search_regex(
+            r'<a href="([^"]+)" onclick="return spOpenVideo\(this,', webpage,
+            'video page URL')
+        video_url = compat_urlparse.urljoin(
+            self.http_scheme() + '//spiegel.de/', video_link)
+
+        return {
+            '_type': 'url',
+            'url': video_url,
+        }