]> Raphaël G. Git Repositories - youtubedl/blobdiff - youtube_dl/extractor/buzzfeed.py
Merge changes from buster branch for the NMU while I was away.
[youtubedl] / youtube_dl / extractor / buzzfeed.py
index a40a1bbc47b38529b7a5191bb0a6aeb96c15c532..ec411091efe7dc15b28c7f4a3939bff89395fa59 100644 (file)
@@ -5,6 +5,7 @@ import json
 import re
 
 from .common import InfoExtractor
 import re
 
 from .common import InfoExtractor
+from .facebook import FacebookIE
 
 
 class BuzzFeedIE(InfoExtractor):
 
 
 class BuzzFeedIE(InfoExtractor):
@@ -20,11 +21,11 @@ class BuzzFeedIE(InfoExtractor):
             'info_dict': {
                 'id': 'aVCR29aE_OQ',
                 'ext': 'mp4',
             'info_dict': {
                 'id': 'aVCR29aE_OQ',
                 'ext': 'mp4',
+                'title': 'Angry Ram destroys a punching bag..',
+                'description': 'md5:c59533190ef23fd4458a5e8c8c872345',
                 'upload_date': '20141024',
                 'uploader_id': 'Buddhanz1',
                 'upload_date': '20141024',
                 'uploader_id': 'Buddhanz1',
-                'description': 'He likes to stay in shape with his heavy bag, he wont stop until its on the ground\n\nFollow Angry Ram on Facebook for regular updates -\nhttps://www.facebook.com/pages/Angry-Ram/1436897249899558?ref=hl',
-                'uploader': 'Buddhanz',
-                'title': 'Angry Ram destroys a punching bag',
+                'uploader': 'Angry Ram',
             }
         }]
     }, {
             }
         }]
     }, {
@@ -33,20 +34,38 @@ class BuzzFeedIE(InfoExtractor):
             'skip_download': True,  # Got enough YouTube download tests
         },
         'info_dict': {
             'skip_download': True,  # Got enough YouTube download tests
         },
         'info_dict': {
-            'description': 'Munchkin the Teddy Bear is back !',
+            'id': 'look-at-this-cute-dog-omg',
+            'description': 're:Munchkin the Teddy Bear is back ?!',
             'title': 'You Need To Stop What You\'re Doing And Watching This Dog Walk On A Treadmill',
         },
         'playlist': [{
             'info_dict': {
                 'id': 'mVmBL8B-In0',
                 'ext': 'mp4',
             'title': 'You Need To Stop What You\'re Doing And Watching This Dog Walk On A Treadmill',
         },
         'playlist': [{
             'info_dict': {
                 'id': 'mVmBL8B-In0',
                 'ext': 'mp4',
+                'title': 're:Munchkin the Teddy Bear gets her exercise',
+                'description': 'md5:28faab95cda6e361bcff06ec12fc21d8',
                 'upload_date': '20141124',
                 'uploader_id': 'CindysMunchkin',
                 'upload_date': '20141124',
                 'uploader_id': 'CindysMunchkin',
-                'description': '© 2014 Munchkin the Shih Tzu\nAll rights reserved\nFacebook: http://facebook.com/MunchkintheShihTzu',
-                'uploader': 'Munchkin the Shih Tzu',
-                'title': 'Munchkin the Teddy Bear gets her exercise',
+                'uploader': 're:^Munchkin the',
             },
         }]
             },
         }]
+    }, {
+        'url': 'http://www.buzzfeed.com/craigsilverman/the-most-adorable-crash-landing-ever#.eq7pX0BAmK',
+        'info_dict': {
+            'id': 'the-most-adorable-crash-landing-ever',
+            'title': 'Watch This Baby Goose Make The Most Adorable Crash Landing',
+            'description': 'This gosling knows how to stick a landing.',
+        },
+        'playlist': [{
+            'md5': '763ca415512f91ca62e4621086900a23',
+            'info_dict': {
+                'id': '971793786185728',
+                'ext': 'mp4',
+                'title': 'We set up crash pads so that the goslings on our roof would have a safe landi...',
+                'uploader': 'Calgary Outdoor Centre-University of Calgary',
+            },
+        }],
+        'add_ie': ['Facebook'],
     }]
 
     def _real_extract(self, url):
     }]
 
     def _real_extract(self, url):
@@ -65,6 +84,11 @@ class BuzzFeedIE(InfoExtractor):
                 continue
             entries.append(self.url_result(video['url']))
 
                 continue
             entries.append(self.url_result(video['url']))
 
+        facebook_urls = FacebookIE._extract_urls(webpage)
+        entries.extend([
+            self.url_result(facebook_url)
+            for facebook_url in facebook_urls])
+
         return {
             '_type': 'playlist',
             'id': playlist_id,
         return {
             '_type': 'playlist',
             'id': playlist_id,