about summary refs log tree commit diff
path: root/youtube_dl/extractor/spiegel.py
diff options
context:
space:
mode:
authorPhilipp Hagemeister <phihag@phihag.de>2013-06-23 22:22:08 +0200
committerPhilipp Hagemeister <phihag@phihag.de>2013-06-23 22:22:08 +0200
commit49f5f315fd4640d20107e02195a91108a8223449 (patch)
treedfb28c645e0bded273d0e65f09df84619802dc30 /youtube_dl/extractor/spiegel.py
parent97d2db017c67bedd1e50d149b51d60fcbfd26041 (diff)
downloadyoutube-dl-49f5f315fd4640d20107e02195a91108a8223449.tar.gz
youtube-dl-49f5f315fd4640d20107e02195a91108a8223449.tar.xz
youtube-dl-49f5f315fd4640d20107e02195a91108a8223449.zip
[Spiegel] move into own file
Diffstat (limited to 'youtube_dl/extractor/spiegel.py')
-rw-r--r--youtube_dl/extractor/spiegel.py37
1 files changed, 37 insertions, 0 deletions
diff --git a/youtube_dl/extractor/spiegel.py b/youtube_dl/extractor/spiegel.py
new file mode 100644
index 000000000..98a65b78b
--- /dev/null
+++ b/youtube_dl/extractor/spiegel.py
@@ -0,0 +1,37 @@
+import re
+import xml.etree.ElementTree
+
+from .common import InfoExtractor
+
+
+class SpiegelIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?spiegel\.de/video/[^/]*-(?P<videoID>[0-9]+)(?:\.html)?(?:#.*)?$'
+
+    def _real_extract(self, url):
+        m = re.match(self._VALID_URL, url)
+        video_id = m.group('videoID')
+
+        webpage = self._download_webpage(url, video_id)
+
+        video_title = self._html_search_regex(r'<div class="module-title">(.*?)</div>',
+            webpage, u'title')
+
+        xml_url = u'http://video2.spiegel.de/flash/' + video_id + u'.xml'
+        xml_code = self._download_webpage(xml_url, video_id,
+                    note=u'Downloading XML', errnote=u'Failed to download XML')
+
+        idoc = xml.etree.ElementTree.fromstring(xml_code)
+        last_type = idoc[-1]
+        filename = last_type.findall('./filename')[0].text
+        duration = float(last_type.findall('./duration')[0].text)
+
+        video_url = 'http://video2.spiegel.de/flash/' + filename
+        video_ext = filename.rpartition('.')[2]
+        info = {
+            'id': video_id,
+            'url': video_url,
+            'ext': video_ext,
+            'title': video_title,
+            'duration': duration,
+        }
+        return [info]