]>
Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/imgur.py
1 from __future__
import unicode_literals
5 from .common
import InfoExtractor
14 class ImgurIE(InfoExtractor
):
15 _VALID_URL
= r
'https?://(?:i\.)?imgur\.com/(?!(?:a|gallery|(?:t(?:opic)?|r)/[^/]+)/)(?P<id>[a-zA-Z0-9]+)'
18 'url': 'https://i.imgur.com/A61SaA1.gifv',
22 'title': 're:Imgur GIF$|MRW gifv is up and running without any bugs$',
25 'url': 'https://imgur.com/A61SaA1',
26 'only_matching': True,
28 'url': 'https://i.imgur.com/crGpqCV.mp4',
29 'only_matching': True,
32 'url': 'https://i.imgur.com/jxBXAMC.gifv',
33 'only_matching': True,
36 def _real_extract(self
, url
):
37 video_id
= self
._match
_id
(url
)
38 webpage
= self
._download
_webpage
(
39 'https://i.imgur.com/{id}.gifv'.format(id=video_id
), video_id
)
41 width
= int_or_none(self
._og
_search
_property
(
42 'video:width', webpage
, default
=None))
43 height
= int_or_none(self
._og
_search
_property
(
44 'video:height', webpage
, default
=None))
46 video_elements
= self
._search
_regex
(
47 r
'(?s)<div class="video-elements">(.*?)</div>',
48 webpage
, 'video elements', default
=None)
49 if not video_elements
:
51 'No sources found for video %s. Maybe an image?' % video_id
,
55 for m
in re
.finditer(r
'<source\s+src="(?P<src>[^"]+)"\s+type="(?P<type>[^"]+)"', video_elements
):
57 'format_id': m
.group('type').partition('/')[2],
58 'url': self
._proto
_relative
_url
(m
.group('src')),
59 'ext': mimetype2ext(m
.group('type')),
63 'User-Agent': 'youtube-dl (like wget)',
67 gif_json
= self
._search
_regex
(
68 r
'(?s)var\s+videoItem\s*=\s*(\{.*?\})',
69 webpage
, 'GIF code', fatal
=False)
71 gifd
= self
._parse
_json
(
72 gif_json
, video_id
, transform_source
=js_to_json
)
82 'url': self
._proto
_relative
_url
(gifd
['gifUrl']),
83 'filesize': gifd
.get('size'),
85 'User-Agent': 'youtube-dl (like wget)',
89 self
._sort
_formats
(formats
)
94 'title': self
._og
_search
_title
(webpage
, default
=video_id
),
98 class ImgurGalleryIE(InfoExtractor
):
99 IE_NAME
= 'imgur:gallery'
100 _VALID_URL
= r
'https?://(?:i\.)?imgur\.com/(?:gallery|(?:t(?:opic)?|r)/[^/]+)/(?P<id>[a-zA-Z0-9]+)'
103 'url': 'http://imgur.com/gallery/Q95ko',
106 'title': 'Adding faces make every GIF better',
108 'playlist_count': 25,
110 'url': 'http://imgur.com/topic/Aww/ll5Vk',
111 'only_matching': True,
113 'url': 'https://imgur.com/gallery/YcAQlkx',
117 'title': 'Classic Steve Carell gif...cracks me up everytime....damn the repost downvotes....',
120 'url': 'http://imgur.com/topic/Funny/N8rOudd',
121 'only_matching': True,
123 'url': 'http://imgur.com/r/aww/VQcQPhM',
124 'only_matching': True,
127 def _real_extract(self
, url
):
128 gallery_id
= self
._match
_id
(url
)
130 data
= self
._download
_json
(
131 'https://imgur.com/gallery/%s.json' % gallery_id
,
132 gallery_id
)['data']['image']
134 if data
.get('is_album'):
136 self
.url_result('http://imgur.com/%s' % image
['hash'], ImgurIE
.ie_key(), image
['hash'])
137 for image
in data
['album_images']['images'] if image
.get('hash')]
138 return self
.playlist_result(entries
, gallery_id
, data
.get('title'), data
.get('description'))
140 return self
.url_result('http://imgur.com/%s' % gallery_id
, ImgurIE
.ie_key(), gallery_id
)
143 class ImgurAlbumIE(ImgurGalleryIE
):
144 IE_NAME
= 'imgur:album'
145 _VALID_URL
= r
'https?://(?:i\.)?imgur\.com/a/(?P<id>[a-zA-Z0-9]+)'
148 'url': 'http://imgur.com/a/j6Orj',
151 'title': 'A Literary Analysis of "Star Wars: The Force Awakens"',
153 'playlist_count': 12,