w/youtube-dl
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

Improve extraction (Closes #7918)

Browse source 
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.
This commit is contained in:
Abhishek Kedia 2015-12-21 01:50:07 +01:00 committed by Sergey M․
parent 31d9ea4a3e
commit dbee18b552
1 changed files with 22 additions and 10 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

32
youtube_dl/extractor/imgur.py
View file

@ -13,7 +13,7 @@ from ..utils import (
class ImgurIE(InfoExtractor): 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 = [{ _TESTS = [{
'url': 'https://i.imgur.com/A61SaA1.gifv', 'url': 'https://i.imgur.com/A61SaA1.gifv',
@ -21,7 +21,7 @@ class ImgurIE(InfoExtractor):
'id': 'A61SaA1', 'id': 'A61SaA1',
'ext': 'mp4', 'ext': 'mp4',
'title': 're:Imgur GIF$|MRW gifv is up and running without any bugs$', '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', 'url': 'https://imgur.com/A61SaA1',
@ -29,8 +29,17 @@ class ImgurIE(InfoExtractor):
'id': 'A61SaA1', 'id': 'A61SaA1',
'ext': 'mp4', 'ext': 'mp4',
'title': 're:Imgur GIF$|MRW gifv is up and running without any bugs$', '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): def _real_extract(self, url):
@ -100,7 +109,7 @@ class ImgurIE(InfoExtractor):
class ImgurAlbumIE(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 = { _TEST = {
'url': 'http://imgur.com/gallery/Q95ko', 'url': 'http://imgur.com/gallery/Q95ko',
@ -113,12 +122,15 @@ class ImgurAlbumIE(InfoExtractor):
def _real_extract(self, url): def _real_extract(self, url):
album_id = self._match_id(url) album_id = self._match_id(url)
album_images = self._download_json( album_img_data = self._download_json(
'http://imgur.com/gallery/%s/album_images/hit.json?all=true' % album_id, 'http://imgur.com/gallery/%s/album_images/hit.json?all=true' % album_id, album_id)['data']
album_id)['data']['images']
entries = [ if len(album_img_data) == 0:
self.url_result('http://imgur.com/%s' % image['hash']) return self.url_result('http://imgur.com/%s' % album_id)
for image in album_images if image.get('hash')] 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) return self.playlist_result(entries, album_id)