Merge tag 'upstream/2013.12.23'

[youtubedl] / youtube_dl / extractor / archiveorg.py

diff --git a/youtube_dl/extractor/archiveorg.py b/youtube_dl/extractor/archiveorg.py
index 7efd1d82324c5397bb6d6f10e1bfa993a2531584..8bb546410f7a7486bdaa964bc724cf2c501e8851 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'
 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',
     _TEST = {
         u"url": u"http://archive.org/details/XD300-23_68HighlightsAResearchCntAugHumanIntellect",
         u'file': u'XD300-23_68HighlightsAResearchCntAugHumanIntellect.ogv',


@@ -46,8 +46,10 @@ class ArchiveOrgIE(InfoExtractor):
             for fn,fdata in data['files'].items()
             if 'Video' in fdata['format']]
         formats.sort(key=lambda fdata: fdata['file_size'])
             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 = {
+        return {

             '_type': 'video',
             'id': video_id,
             'title': title,
             '_type': 'video',
             'id': video_id,
             'title': title,


@@ -55,13 +57,5 @@ class ArchiveOrgIE(InfoExtractor):
             'description': description,
             'uploader': uploader,
             'upload_date': upload_date,
             'description': description,
             'uploader': uploader,
             'upload_date': upload_date,

+            'thumbnail': data.get('misc', {}).get('image'),

         }
         }

-        thumbnail = data.get('misc', {}).get('image')
-        if thumbnail:
-            info['thumbnail'] = thumbnail
-
-        # TODO: Remove when #980 has been merged
-        info['url'] = formats[-1]['url']
-        info['ext'] = determine_ext(formats[-1]['url'])
-
-        return info
\ No newline at end of file