[archiveorg] Fix and improve extraction (closes #21330, closes #23586, closes #25277, closes #26780, closes #27109, closes #27236, closes #28063)

1 files changed, 42 insertions, 12 deletions

diff --git a/youtube_dl/extractor/archiveorg.py b/youtube_dl/extractor/archiveorg.py
index c79c58e82..e42ed5e79 100644
--- a/youtube_dl/extractor/archiveorg.py
+++ b/youtube_dl/extractor/archiveorg.py
@@ -2,15 +2,17 @@ from __future__ import unicode_literals
 
 from .common import InfoExtractor
 from ..utils import (
-    unified_strdate,
     clean_html,
+    extract_attributes,
+    unified_strdate,
+    unified_timestamp,
 )
 
 
 class ArchiveOrgIE(InfoExtractor):
     IE_NAME = 'archive.org'
     IE_DESC = 'archive.org videos'
-    _VALID_URL = r'https?://(?:www\.)?archive\.org/(?:details|embed)/(?P<id>[^/?#]+)(?:[?].*)?$'
+    _VALID_URL = r'https?://(?:www\.)?archive\.org/(?:details|embed)/(?P<id>[^/?#&]+)'
     _TESTS = [{
         'url': 'http://archive.org/details/XD300-23_68HighlightsAResearchCntAugHumanIntellect',
         'md5': '8af1d4cf447933ed3c7f4871162602db',
@@ -19,8 +21,11 @@ class ArchiveOrgIE(InfoExtractor):
             'ext': 'ogg',
             'title': '1968 Demo - FJCC Conference Presentation Reel #1',
             'description': 'md5:da45c349df039f1cc8075268eb1b5c25',
-            'upload_date': '19681210',
-            'uploader': 'SRI International'
+            'creator': 'SRI International',
+            'release_date': '19681210',
+            'uploader': 'SRI International',
+            'timestamp': 1268695290,
+            'upload_date': '20100315',
         }
     }, {
         'url': 'https://archive.org/details/Cops1922',
@@ -29,22 +34,43 @@ class ArchiveOrgIE(InfoExtractor):
             'id': 'Cops1922',
             'ext': 'mp4',
             'title': 'Buster Keaton\'s "Cops" (1922)',
-            'description': 'md5:89e7c77bf5d965dd5c0372cfb49470f6',
+            'description': 'md5:43a603fd6c5b4b90d12a96b921212b9c',
+            'timestamp': 1387699629,
+            'upload_date': '20131222',
         }
     }, {
         'url': 'http://archive.org/embed/XD300-23_68HighlightsAResearchCntAugHumanIntellect',
         'only_matching': True,
+    }, {
+        'url': 'https://archive.org/details/MSNBCW_20131125_040000_To_Catch_a_Predator/',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
         webpage = self._download_webpage(
             'http://archive.org/embed/' + video_id, video_id)
-        jwplayer_playlist = self._parse_json(self._search_regex(
-            r"(?s)Play\('[^']+'\s*,\s*(\[.+\])\s*,\s*{.*?}\)",
-            webpage, 'jwplayer playlist'), video_id)
-        info = self._parse_jwplayer_data(
-            {'playlist': jwplayer_playlist}, video_id, base_url=url)
+
+        playlist = None
+        play8 = self._search_regex(
+            r'(<[^>]+\bclass=["\']js-play8-playlist[^>]+>)', webpage,
+            'playlist', default=None)
+        if play8:
+            attrs = extract_attributes(play8)
+            playlist = attrs.get('value')
+        if not playlist:
+            # Old jwplayer fallback
+            playlist = self._search_regex(
+                r"(?s)Play\('[^']+'\s*,\s*(\[.+\])\s*,\s*{.*?}\)",
+                webpage, 'jwplayer playlist', default='[]')
+        jwplayer_playlist = self._parse_json(playlist, video_id, fatal=False)
+        if jwplayer_playlist:
+            info = self._parse_jwplayer_data(
+                {'playlist': jwplayer_playlist}, video_id, base_url=url)
+        else:
+            # HTML5 media fallback
+            info = self._parse_html5_media_entries(url, webpage, video_id)[0]
+            info['id'] = video_id
 
         def get_optional(metadata, field):
             return metadata.get(field, [None])[0]
@@ -58,8 +84,12 @@ class ArchiveOrgIE(InfoExtractor):
             'description': clean_html(get_optional(metadata, 'description')),
         })
         if info.get('_type') != 'playlist':
+            creator = get_optional(metadata, 'creator')
             info.update({
-                'uploader': get_optional(metadata, 'creator'),
-                'upload_date': unified_strdate(get_optional(metadata, 'date')),
+                'creator': creator,
+                'release_date': unified_strdate(get_optional(metadata, 'date')),
+                'uploader': get_optional(metadata, 'publisher') or creator,
+                'timestamp': unified_timestamp(get_optional(metadata, 'publicdate')),
+                'language': get_optional(metadata, 'language'),
             })
         return info