[youtube] Fix extraction.

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

diff --git a/youtube_dl/extractor/dhm.py b/youtube_dl/extractor/dhm.py
index 80ee40018197d7ace7e9105d1535e6c17058f5c3..aee72a6ed1e2daac661887b2ed225e898635c71b 100644 (file)
--- a/youtube_dl/extractor/dhm.py
+++ b/youtube_dl/extractor/dhm.py
@@ -1,17 +1,14 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..utils import (
-    xpath_text,
-    parse_duration,
-)
+from ..utils import parse_duration
 
 
 class DHMIE(InfoExtractor):
     IE_DESC = 'Filmarchiv - Deutsches Historisches Museum'
-    _VALID_URL = r'http://www\.dhm\.de/filmarchiv/die-filme/(?P<id>[^/]+)'
+    _VALID_URL = r'https?://(?:www\.)?dhm\.de/filmarchiv/(?:[^/]+/)+(?P<id>[^/]+)'
 
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.dhm.de/filmarchiv/die-filme/the-marshallplan-at-work-in-west-germany/',
         'md5': '11c475f670209bf6acca0b2b7ef51827',
         'info_dict': {
@@ -20,45 +17,43 @@ class DHMIE(InfoExtractor):
             'title': 'MARSHALL PLAN AT WORK IN WESTERN GERMANY, THE',
             'description': 'md5:1fabd480c153f97b07add61c44407c82',
             'duration': 660,
-            'thumbnail': 're:^https?://.*\.jpg$',
-        }
-    }
+            'thumbnail': r're:^https?://.*\.jpg$',
+        },
+    }, {
+        'url': 'http://www.dhm.de/filmarchiv/02-mapping-the-wall/peter-g/rolle-1/',
+        'md5': '09890226332476a3e3f6f2cb74734aa5',
+        'info_dict': {
+            'id': 'rolle-1',
+            'ext': 'flv',
+            'title': 'ROLLE 1',
+            'thumbnail': r're:^https?://.*\.jpg$',
+        },
+    }]
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
+        playlist_id = self._match_id(url)
 
-        webpage = self._download_webpage(url, video_id)
+        webpage = self._download_webpage(url, playlist_id)
 
         playlist_url = self._search_regex(
             r"file\s*:\s*'([^']+)'", webpage, 'playlist url')
 
-        playlist = self._download_xml(playlist_url, video_id)
-
-        track = playlist.find(
-            './{http://xspf.org/ns/0/}trackList/{http://xspf.org/ns/0/}track')
-
-        video_url = xpath_text(
-            track, './{http://xspf.org/ns/0/}location',
-            'video url', fatal=True)
-        thumbnail = xpath_text(
-            track, './{http://xspf.org/ns/0/}image',
-            'thumbnail')
+        entries = self._extract_xspf_playlist(playlist_url, playlist_id)
 
         title = self._search_regex(
             [r'dc:title="([^"]+)"', r'<title> &raquo;([^<]+)</title>'],
             webpage, 'title').strip()
         description = self._html_search_regex(
             r'<p><strong>Description:</strong>(.+?)</p>',
-            webpage, 'description', fatal=False)
+            webpage, 'description', default=None)
         duration = parse_duration(self._search_regex(
             r'<em>Length\s*</em>\s*:\s*</strong>([^<]+)',
-            webpage, 'duration', fatal=False))
+            webpage, 'duration', default=None))
 
-        return {
-            'id': video_id,
-            'url': video_url,
+        entries[0].update({
             'title': title,
             'description': description,
             'duration': duration,
-            'thumbnail': thumbnail,
-        }
+        })
+
+        return self.playlist_result(entries, playlist_id)