youtube-dl

commit 66d40ae3a5b5f68b551831714ae693931ec6cffa
parent e6da9240d44774495a7ae0f2780bd42e4d2628f5
Author: Yen Chi Hsuan <yan12125@gmail.com>
Date:   Fri, 15 Apr 2016 17:23:55 +0800

Merge pull request #9041 from kasper93/master

[generic] Add support for LiveLeak embeds
Diffstat:
M
youtube_dl/extractor/generic.py
 | 
18
++++++++++++++++++
M
youtube_dl/extractor/liveleak.py
 | 
8
++++++++

2 files changed, 26 insertions(+), 0 deletions(-)
diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py
@@ -60,6 +60,7 @@ from .googledrive import GoogleDriveIE
 from .jwplatform import JWPlatformIE
 from .digiteka import DigitekaIE
 from .instagram import InstagramIE
+from .liveleak import LiveLeakIE
 
 
 class GenericIE(InfoExtractor):
@@ -1140,6 +1141,18 @@ class GenericIE(InfoExtractor):
                 'upload_date': '20160409',
             },
         },
+        # LiveLeak embed
+        {
+            'url': 'http://www.wykop.pl/link/3088787/',
+            'md5': 'ace83b9ed19b21f68e1b50e844fdf95d',
+            'info_dict': {
+                'id': '874_1459135191',
+                'ext': 'mp4',
+                'title': 'Man shows poor quality of new apartment building',
+                'description': 'The wall is like a sand pile.',
+                'uploader': 'Lake8737',
+            }
+        },
     ]
 
     def report_following_redirect(self, new_url):
@@ -1944,6 +1957,11 @@ class GenericIE(InfoExtractor):
         if instagram_embed_url is not None:
             return self.url_result(instagram_embed_url, InstagramIE.ie_key())
 
+        # Look for LiveLeak embeds
+        liveleak_url = LiveLeakIE._extract_url(webpage)
+        if liveleak_url:
+            return self.url_result(liveleak_url, 'LiveLeak')
+
         def check_video(vurl):
             if YoutubeIE.suitable(vurl):
                 return True
diff --git a/youtube_dl/extractor/liveleak.py b/youtube_dl/extractor/liveleak.py
@@ -53,6 +53,14 @@ class LiveLeakIE(InfoExtractor):
         }
     }]
 
+    @staticmethod
+    def _extract_url(webpage):
+        mobj = re.search(
+            r'<iframe[^>]+src="https?://(?:\w+\.)?liveleak\.com/ll_embed\?(?:.*?)i=(?P<id>[\w_]+)(?:.*)',
+            webpage)
+        if mobj:
+            return 'http://www.liveleak.com/view?i=%s' % mobj.group('id')
+
     def _real_extract(self, url):
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)