youtube-dl

commit 91dff03217fabf34b04f2ee811dfd98149739678
parent a200f4cee21093975d881190c6ff4227f5490594
Author: Philipp Hagemeister <phihag@phihag.de>
Date:   Fri, 22 Aug 2014 01:43:19 +0200

[dump] Modernize (#3565)

Diffstat:
M
youtube_dl/extractor/dump.py
 | 
33
++++++++++++---------------------

1 file changed, 12 insertions(+), 21 deletions(-)
diff --git a/youtube_dl/extractor/dump.py b/youtube_dl/extractor/dump.py
@@ -4,19 +4,19 @@ 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]+)/'
 
     _TEST = {
-        u'url': u'http://www.dump.com/oneus/',
-        u'file': u'oneus.flv',
-        u'md5': u'ad71704d1e67dfd9e81e3e8b42d69d99',
-        u'info_dict': {
-            u"title": u"He's one of us.",
+        'url': 'http://www.dump.com/oneus/',
+        'md5': 'ad71704d1e67dfd9e81e3e8b42d69d99',
+        'info_dict': {
+            'id': 'oneus',
+            'ext': 'flv',
+            'title': "He's one of us.",
+            'thumbnail': 're:^https?://.*\.jpg$',
         },
     }
 
@@ -24,25 +24,16 @@ class DumpIE(InfoExtractor):
         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)
+        video_url = self._search_regex(
+            r's1.addVariable\("file",\s*"([^"]+)"', webpage, 'video URL')
 
-        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')
+        thumb = self._og_search_thumbnail(webpage)
+        title = self._search_regex(r'<b>([^"]+)</b>', webpage, 'title')
 
         return {
             'id': video_id,
             'title': title,
             'url': video_url,
-            'ext': 'flv',
             'thumbnail': thumb,
         }