youtube-dl

commit 20d729228ce27cd9a242b6aea31b481c2dc0cde7
parent cb88671e37a9fbb964ee0b2ab46031195f2aab1e
Author: Sergey M․ <dstftw@gmail.com>
Date:   Sat, 28 Mar 2015 22:30:27 +0600

Merge branch 'ossi96-dhm'

Diffstat:
M
youtube_dl/extractor/__init__.py
 | 
1
+
A
youtube_dl/extractor/dhm.py
 | 
64
++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++

2 files changed, 65 insertions(+), 0 deletions(-)
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
@@ -106,6 +106,7 @@ from .dbtv import DBTVIE
 from .dctp import DctpTvIE
 from .deezer import DeezerPlaylistIE
 from .dfb import DFBIE
+from .dhm import DHMIE
 from .dotsub import DotsubIE
 from .douyutv import DouyuTVIE
 from .dreisat import DreiSatIE
diff --git a/youtube_dl/extractor/dhm.py b/youtube_dl/extractor/dhm.py
@@ -0,0 +1,64 @@
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    xpath_text,
+    parse_duration,
+)
+
+
+class DHMIE(InfoExtractor):
+    IE_DESC = 'Filmarchiv - Deutsches Historisches Museum'
+    _VALID_URL = r'http://www\.dhm\.de/filmarchiv/die-filme/(?P<id>[^/]+)'
+
+    _TEST = {
+        'url': 'http://www.dhm.de/filmarchiv/die-filme/the-marshallplan-at-work-in-west-germany/',
+        'md5': '11c475f670209bf6acca0b2b7ef51827',
+        'info_dict': {
+            'id': 'the-marshallplan-at-work-in-west-germany',
+            'ext': 'flv',
+            'title': 'MARSHALL PLAN AT WORK IN WESTERN GERMANY, THE',
+            'description': 'md5:1fabd480c153f97b07add61c44407c82',
+            'duration': 660,
+            'thumbnail': 're:^https?://.*\.jpg$',
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_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')
+
+        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)
+        duration = parse_duration(self._search_regex(
+            r'<em>Length\s*</em>\s*:\s*</strong>([^<]+)',
+            webpage, 'duration', fatal=False))
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'title': title,
+            'description': description,
+            'duration': duration,
+            'thumbnail': thumbnail,
+        }