youtube-dl

commit dbee18b5521edbfa1642c683ad2d317ba06e9d5b
parent 31d9ea4a3e641acfee8852c9324bd414047fce9e
Author: Abhishek Kedia <kedia.abhishek10@gmail.com>
Date:   Mon, 21 Dec 2015 01:50:07 +0100

Improve extraction (Closes #7918)

remove outer parentheses in if

Conflicts:
	youtube_dl/extractor/imgur.py

checked code with flake8

not returning list in case of single images.

using the fact that id with length 5 are albums and more are single videos.
Also for single videos ie ImgurIE both urls - http://imgur.com/gallery/oWeAMW2 and http://imgur.com/oWeAMW2 are equally fine. Change regex to allow thuis.
For albums urls - http://imgur.com/gallery/Q95ko and http://imgur.com/Q95ko are ok. Change regex to allow this also.

update description in ImgurIE Tests.
Also move single video test 'https://imgur.com/gallery/YcAQlkx' from ImgurAlbumIE to ImgurIE.

Diffstat:
M
youtube_dl/extractor/imgur.py
 | 
32
++++++++++++++++++++++----------

1 file changed, 22 insertions(+), 10 deletions(-)
diff --git a/youtube_dl/extractor/imgur.py b/youtube_dl/extractor/imgur.py
@@ -13,7 +13,7 @@ from ..utils import (
 
 
 class ImgurIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:i\.)?imgur\.com/(?!gallery)(?P<id>[a-zA-Z0-9]+)'
+    _VALID_URL = r'https?://(?:i\.)?imgur\.com/(gallery/)?(?P<id>[a-zA-Z0-9]{6,})'
 
     _TESTS = [{
         'url': 'https://i.imgur.com/A61SaA1.gifv',
@@ -21,7 +21,7 @@ class ImgurIE(InfoExtractor):
             'id': 'A61SaA1',
             'ext': 'mp4',
             'title': 're:Imgur GIF$|MRW gifv is up and running without any bugs$',
-            'description': 're:The origin of the Internet\'s most viral images$|The Internet\'s visual storytelling community\. Explore, share, and discuss the best visual stories the Internet has to offer\.$',
+            'description': 'Imgur: The most awesome images on the Internet.',
         },
     }, {
         'url': 'https://imgur.com/A61SaA1',
@@ -29,8 +29,17 @@ class ImgurIE(InfoExtractor):
             'id': 'A61SaA1',
             'ext': 'mp4',
             'title': 're:Imgur GIF$|MRW gifv is up and running without any bugs$',
-            'description': 're:The origin of the Internet\'s most viral images$|The Internet\'s visual storytelling community\. Explore, share, and discuss the best visual stories the Internet has to offer\.$',
+            'description': 'Imgur: The most awesome images on the Internet.',
         },
+    }, {
+        'url': 'https://imgur.com/gallery/YcAQlkx',
+        'info_dict': {
+            'id': 'YcAQlkx',
+            'ext': 'mp4',
+            'title': 'Classic Steve Carell gif...cracks me up everytime....damn the repost downvotes....',
+            'description': 'Imgur: The most awesome images on the Internet.'
+
+        }
     }]
 
     def _real_extract(self, url):
@@ -100,7 +109,7 @@ class ImgurIE(InfoExtractor):
 
 
 class ImgurAlbumIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:i\.)?imgur\.com/gallery/(?P<id>[a-zA-Z0-9]+)'
+    _VALID_URL = r'https?://(?:i\.)?imgur\.com/(gallery/)?(?P<id>[a-zA-Z0-9]{5})(?![a-zA-Z0-9])'
 
     _TEST = {
         'url': 'http://imgur.com/gallery/Q95ko',
@@ -113,12 +122,15 @@ class ImgurAlbumIE(InfoExtractor):
     def _real_extract(self, url):
         album_id = self._match_id(url)
 
-        album_images = self._download_json(
-            'http://imgur.com/gallery/%s/album_images/hit.json?all=true' % album_id,
-            album_id)['data']['images']
+        album_img_data = self._download_json(
+            'http://imgur.com/gallery/%s/album_images/hit.json?all=true' % album_id, album_id)['data']
 
-        entries = [
-            self.url_result('http://imgur.com/%s' % image['hash'])
-            for image in album_images if image.get('hash')]
+        if len(album_img_data) == 0:
+            return self.url_result('http://imgur.com/%s' % album_id)
+        else:
+            album_images = album_img_data['images']
+            entries = [
+                self.url_result('http://imgur.com/%s' % image['hash'])
+                for image in album_images if image.get('hash')]
 
         return self.playlist_result(entries, album_id)