[youtube] Fix extraction.
[youtube-dl] / youtube_dl / extractor / bild.py
index 3a822a5c0afd695766ffa21c168cecec2d1eca78..b8dfbd42b429beb8f530076b1efdee571ec4d855 100644 (file)
@@ -1,46 +1,40 @@
-from __future__ import unicode_literals\r
-\r
-import re\r
-\r
-from .common import InfoExtractor\r
-\r
-\r
-class BildIE(InfoExtractor):\r
-    IE_NAME = 'bild'\r
-    _TEST = {\r
-        'url': 'http://www.bild.de/video/clip/apple-ipad-air/das-koennen-die-neuen-ipads-38184146.bild.html',\r
-        'info_dict': {\r
-            'id': '38184146',\r
-            'title': 'BILD hat sie getestet',\r
-            'thumbnail': 'http://bilder.bild.de/fotos/stand-das-koennen-die-neuen-ipads-38184138/Bild/1.bild.jpg',\r
-            'duration': 196,\r
-        }\r
-    }\r
-    \r
-    #http://www.bild.de/video/clip/apple-ipad-air/das-koennen-die-neuen-ipads-38184146.bild.html\r
-    _VALID_URL = r'http?://(?:www\.)?bild\.de/(?:[^/]+/)+(?P<display_id>[^/]+)-(?P<id>\d+)(?:,auto=true)?\.bild\.html'\r
-    \r
-    def _real_extract(self, url):\r
-        m = re.match(self._VALID_URL, url)\r
-        video_id = m.group('id')\r
-        \r
-        #webpage = self._download_webpage(url, video_id)\r
-        \r
-        xml_url = url.split(".bild.html")[0]+",view=xml.bild.xml"\r
-        \r
-        doc = self._download_xml(xml_url, video_id)\r
-        \r
-        video_url = doc.attrib['src']\r
-        title = doc.attrib['ueberschrift']\r
-        description = doc.attrib['text']\r
-        thumbnail = doc.attrib['img']\r
-        duration = int(doc.attrib['duration'])/1000\r
-\r
-        return {\r
-            'id': video_id,\r
-            'title': title,\r
-            'description': description,\r
-            'url': video_url,\r
-            'thumbnail': thumbnail,\r
-            'duration': duration,\r
-        }\r
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    unescapeHTML,
+)
+
+
+class BildIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?bild\.de/(?:[^/]+/)+(?P<display_id>[^/]+)-(?P<id>\d+)(?:,auto=true)?\.bild\.html'
+    IE_DESC = 'Bild.de'
+    _TEST = {
+        'url': 'http://www.bild.de/video/clip/apple-ipad-air/das-koennen-die-neuen-ipads-38184146.bild.html',
+        'md5': 'dd495cbd99f2413502a1713a1156ac8a',
+        'info_dict': {
+            'id': '38184146',
+            'ext': 'mp4',
+            'title': 'Das können die  neuen iPads',
+            'description': 'md5:a4058c4fa2a804ab59c00d7244bbf62f',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'duration': 196,
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        video_data = self._download_json(
+            url.split('.bild.html')[0] + ',view=json.bild.html', video_id)
+
+        return {
+            'id': video_id,
+            'title': unescapeHTML(video_data['title']).strip(),
+            'description': unescapeHTML(video_data.get('description')),
+            'url': video_data['clipList'][0]['srces'][0]['src'],
+            'thumbnail': video_data.get('poster'),
+            'duration': int_or_none(video_data.get('durationSec')),
+        }