Correct some extractor _VALID_URL regexes

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

diff --git a/youtube_dl/extractor/archiveorg.py b/youtube_dl/extractor/archiveorg.py
index 29cb9bdee1e032fc6c316a4b6806a22f55ffb662..a8394bfb0d35487d4a0aa038de05805b074b64ca 100644 (file)
--- a/youtube_dl/extractor/archiveorg.py
+++ b/youtube_dl/extractor/archiveorg.py
@@ -11,7 +11,7 @@ from ..utils import (
 class ArchiveOrgIE(InfoExtractor):
     IE_NAME = 'archive.org'
     IE_DESC = 'archive.org videos'
-    _VALID_URL = r'(?:https?://)?(?:www\.)?archive.org/details/(?P<id>[^?/]+)(?:[?].*)?$'
+    _VALID_URL = r'(?:https?://)?(?:www\.)?archive\.org/details/(?P<id>[^?/]+)(?:[?].*)?$'
     _TEST = {
         u"url": u"http://archive.org/details/XD300-23_68HighlightsAResearchCntAugHumanIntellect",
         u'file': u'XD300-23_68HighlightsAResearchCntAugHumanIntellect.ogv',
@@ -46,8 +46,11 @@ class ArchiveOrgIE(InfoExtractor):
             for fn,fdata in data['files'].items()
             if 'Video' in fdata['format']]
         formats.sort(key=lambda fdata: fdata['file_size'])
+        for f in formats:
+            f['ext'] = determine_ext(f['url'])
 
         info = {
+            '_type': 'video',
             'id': video_id,
             'title': title,
             'formats': formats,
@@ -60,7 +63,6 @@ class ArchiveOrgIE(InfoExtractor):
             info['thumbnail'] = thumbnail
 
         # TODO: Remove when #980 has been merged
-        info['url'] = formats[-1]['url']
-        info['ext'] = determine_ext(formats[-1]['url'])
+        info.update(formats[-1])
 
-        return self.video_result(info)
\ No newline at end of file
+        return info