[generic] exclude urls with xml ext from valid video urls(closes #10768)(closes ...

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

diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py
index cb6308d29e16989b46c2a2036f610f5e9083eb53..36d23d2f37181a37e3ba79db9c9e65ec42d7d960 100644 (file)
--- a/youtube_dl/extractor/generic.py
+++ b/youtube_dl/extractor/generic.py
@@ -730,6 +730,21 @@ class GenericIE(InfoExtractor):
                 'skip_download': True,
             }
         },
+        # YouTube <object> embed
+        {
+            'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
+            'md5': '516718101ec834f74318df76259fb3cc',
+            'info_dict': {
+                'id': 'msN87y-iEx0',
+                'ext': 'webm',
+                'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
+                'upload_date': '20080526',
+                'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
+                'uploader': 'Christopher Sykes',
+                'uploader_id': 'ChristopherJSykes',
+            },
+            'add_ie': ['Youtube'],
+        },
         # Camtasia studio
         {
             'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
@@ -902,12 +917,13 @@ class GenericIE(InfoExtractor):
         },
         # LazyYT
         {
-            'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
+            'url': 'https://skiplagged.com/',
             'info_dict': {
-                'id': '1986',
-                'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
+                'id': 'skiplagged',
+                'title': 'Skiplagged: The smart way to find cheap flights',
             },
-            'playlist_mincount': 2,
+            'playlist_mincount': 1,
+            'add_ie': ['Youtube'],
         },
         # Cinchcast embed
         {
@@ -990,6 +1006,20 @@ class GenericIE(InfoExtractor):
                 'thumbnail': r're:^https?://.*\.jpg$',
             },
         },
+        {
+            # JWPlayer config passed as variable
+            'url': 'http://www.txxx.com/videos/3326530/ariele/',
+            'info_dict': {
+                'id': '3326530_hq',
+                'ext': 'mp4',
+                'title': 'ARIELE | Tube Cup',
+                'uploader': 'www.txxx.com',
+                'age_limit': 18,
+            },
+            'params': {
+                'skip_download': True,
+            }
+        },
         # rtl.nl embed
         {
             'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
@@ -1065,6 +1095,21 @@ class GenericIE(InfoExtractor):
             },
             'add_ie': ['Kaltura'],
         },
+        {
+            # Kaltura iframe embed
+            'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
+            'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
+            'info_dict': {
+                'id': '0_f2cfbpwy',
+                'ext': 'mp4',
+                'title': 'I. M. Pei: A Centennial Celebration',
+                'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
+                'upload_date': '20170403',
+                'uploader_id': 'batchUser',
+                'timestamp': 1491232186,
+            },
+            'add_ie': ['Kaltura'],
+        },
         # Eagle.Platform embed (generic URL)
         {
             'url': 'http://lenta.ru/news/2015/03/06/navalny/',
@@ -1908,6 +1953,7 @@ class GenericIE(InfoExtractor):
                 data-video-url=|
                 <embed[^>]+?src=|
                 embedSWF\(?:\s*|
+                <object[^>]+data=|
                 new\s+SWFObject\(
             )
             (["\'])
@@ -2549,18 +2595,14 @@ class GenericIE(InfoExtractor):
                 self._sort_formats(entry['formats'])
             return self.playlist_result(entries)
 
-        jwplayer_data_str = self._find_jwplayer_data(webpage)
-        if jwplayer_data_str:
-            try:
-                jwplayer_data = self._parse_json(
-                    jwplayer_data_str, video_id, transform_source=js_to_json)
-                info = self._parse_jwplayer_data(
-                    jwplayer_data, video_id, require_title=False)
-                if not info.get('title'):
-                    info['title'] = video_title
-                return info
-            except ExtractorError:
-                pass
+        jwplayer_data = self._find_jwplayer_data(
+            webpage, video_id, transform_source=js_to_json)
+        if jwplayer_data:
+            info = self._parse_jwplayer_data(
+                jwplayer_data, video_id, require_title=False, base_url=url)
+            if not info.get('title'):
+                info['title'] = video_title
+            return info
 
         def check_video(vurl):
             if YoutubeIE.suitable(vurl):
@@ -2569,7 +2611,7 @@ class GenericIE(InfoExtractor):
                 return True
             vpath = compat_urlparse.urlparse(vurl).path
             vext = determine_ext(vpath)
-            return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js')
+            return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
 
         def filter_video(urls):
             return list(filter(check_video, urls))
@@ -2635,11 +2677,14 @@ class GenericIE(InfoExtractor):
                     found = re.search(REDIRECT_REGEX, refresh_header)
             if found:
                 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
-                self.report_following_redirect(new_url)
-                return {
-                    '_type': 'url',
-                    'url': new_url,
-                }
+                if new_url != url:
+                    self.report_following_redirect(new_url)
+                    return {
+                        '_type': 'url',
+                        'url': new_url,
+                    }
+                else:
+                    found = None
 
         if not found:
             # twitter:player is a https URL to iframe player that may or may not