Added an IE for Dump.com

diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index be7616edcf20c81bd95612489cf7394eaabf06ce..7ad5d9318882db08b9a2c2d3fa116ad85717b71b 100644 (file)
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -69,6 +69,7 @@ from .dfb import DFBIE
 from .dotsub import DotsubIE
 from .dreisat import DreiSatIE
 from .drtv import DRTVIE
+from .dump import DumpIE
 from .defense import DefenseGouvFrIE
 from .discovery import DiscoveryIE
 from .divxstage import DivxStageIE

diff --git a/youtube_dl/extractor/dump.py b/youtube_dl/extractor/dump.py
new file mode 100644 (file)
index 0000000..cfa71bd
--- /dev/null
+++ b/youtube_dl/extractor/dump.py
@@ -0,0 +1,39 @@
+# encoding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+)
+
+class DumpIE(InfoExtractor):
+    _VALID_URL = r'^https?://(?:www\.)?dump\.com/(?P<id>[a-zA-Z0-9]+)/'
+
+    def _real_extract(self, url):
+        m = re.match(self._VALID_URL, url)
+        video_id = m.group('id')
+
+        # Note: There is an easier-to-parse configuration at
+        # http://www.aparat.com/video/video/config/videohash/%video_id
+        # but the URL in there does not work
+
+        webpage = self._download_webpage(url, video_id)
+
+        try:
+            video_url = re.findall(r'file","(.+?.flv)"', webpage)[-1]
+        except IndexError:
+            raise ExtractorError(u'No video URL found')
+
+        thumb = re.findall('<meta property="og:image" content="(.+?)"',webpage)[0]
+
+        title = self._search_regex(r'<b>([^"]+)</b>', webpage, u'title')
+
+        return {
+            'id': video_id,
+            'title': title,
+            'url': video_url,
+            'ext': 'flv',
+            'thumbnail': thumb,
+        }