]>
Commit | Line | Data |
---|---|---|
3bf57053 PH |
1 | from __future__ import unicode_literals |
2 | ||
3 | import re | |
4 | ||
5 | from .common import InfoExtractor | |
96b96909 | 6 | from ..compat import compat_urlparse |
3bf57053 PH |
7 | from ..utils import ( |
8 | int_or_none, | |
9 | js_to_json, | |
10 | mimetype2ext, | |
1a13940c | 11 | ExtractorError, |
3bf57053 PH |
12 | ) |
13 | ||
b88ba053 | 14 | |
3bf57053 | 15 | class ImgurIE(InfoExtractor): |
dbee18b5 | 16 | _VALID_URL = r'https?://(?:i\.)?imgur\.com/(gallery/)?(?P<id>[a-zA-Z0-9]{6,})' |
3bf57053 PH |
17 | |
18 | _TESTS = [{ | |
19 | 'url': 'https://i.imgur.com/A61SaA1.gifv', | |
20 | 'info_dict': { | |
21 | 'id': 'A61SaA1', | |
22 | 'ext': 'mp4', | |
5e9a033e | 23 | 'title': 're:Imgur GIF$|MRW gifv is up and running without any bugs$', |
dbee18b5 | 24 | 'description': 'Imgur: The most awesome images on the Internet.', |
3bf57053 | 25 | }, |
1a13940c JB |
26 | }, { |
27 | 'url': 'https://imgur.com/A61SaA1', | |
28 | 'info_dict': { | |
29 | 'id': 'A61SaA1', | |
30 | 'ext': 'mp4', | |
5e9a033e | 31 | 'title': 're:Imgur GIF$|MRW gifv is up and running without any bugs$', |
dbee18b5 | 32 | 'description': 'Imgur: The most awesome images on the Internet.', |
1a13940c | 33 | }, |
dbee18b5 AK |
34 | }, { |
35 | 'url': 'https://imgur.com/gallery/YcAQlkx', | |
36 | 'info_dict': { | |
37 | 'id': 'YcAQlkx', | |
38 | 'ext': 'mp4', | |
39 | 'title': 'Classic Steve Carell gif...cracks me up everytime....damn the repost downvotes....', | |
40 | 'description': 'Imgur: The most awesome images on the Internet.' | |
41 | ||
42 | } | |
3bf57053 PH |
43 | }] |
44 | ||
45 | def _real_extract(self, url): | |
46 | video_id = self._match_id(url) | |
96b96909 S |
47 | webpage = self._download_webpage( |
48 | compat_urlparse.urljoin(url, video_id), video_id) | |
3bf57053 PH |
49 | |
50 | width = int_or_none(self._search_regex( | |
51 | r'<param name="width" value="([0-9]+)"', | |
52 | webpage, 'width', fatal=False)) | |
53 | height = int_or_none(self._search_regex( | |
54 | r'<param name="height" value="([0-9]+)"', | |
55 | webpage, 'height', fatal=False)) | |
56 | ||
b88ba053 | 57 | video_elements = self._search_regex( |
3bf57053 | 58 | r'(?s)<div class="video-elements">(.*?)</div>', |
b88ba053 | 59 | webpage, 'video elements', default=None) |
9e2d7dca JB |
60 | if not video_elements: |
61 | raise ExtractorError( | |
b88ba053 PH |
62 | 'No sources found for video %s. Maybe an image?' % video_id, |
63 | expected=True) | |
9e2d7dca | 64 | |
3bf57053 PH |
65 | formats = [] |
66 | for m in re.finditer(r'<source\s+src="(?P<src>[^"]+)"\s+type="(?P<type>[^"]+)"', video_elements): | |
67 | formats.append({ | |
68 | 'format_id': m.group('type').partition('/')[2], | |
69 | 'url': self._proto_relative_url(m.group('src')), | |
70 | 'ext': mimetype2ext(m.group('type')), | |
71 | 'acodec': 'none', | |
72 | 'width': width, | |
73 | 'height': height, | |
74 | 'http_headers': { | |
75 | 'User-Agent': 'youtube-dl (like wget)', | |
76 | }, | |
77 | }) | |
78 | ||
79 | gif_json = self._search_regex( | |
80 | r'(?s)var\s+videoItem\s*=\s*(\{.*?\})', | |
81 | webpage, 'GIF code', fatal=False) | |
82 | if gif_json: | |
83 | gifd = self._parse_json( | |
84 | gif_json, video_id, transform_source=js_to_json) | |
85 | formats.append({ | |
86 | 'format_id': 'gif', | |
87 | 'preference': -10, | |
88 | 'width': width, | |
89 | 'height': height, | |
90 | 'ext': 'gif', | |
91 | 'acodec': 'none', | |
92 | 'vcodec': 'gif', | |
93 | 'container': 'gif', | |
94 | 'url': self._proto_relative_url(gifd['gifUrl']), | |
95 | 'filesize': gifd.get('size'), | |
96 | 'http_headers': { | |
97 | 'User-Agent': 'youtube-dl (like wget)', | |
98 | }, | |
99 | }) | |
100 | ||
101 | self._sort_formats(formats) | |
102 | ||
103 | return { | |
104 | 'id': video_id, | |
105 | 'formats': formats, | |
106 | 'description': self._og_search_description(webpage), | |
107 | 'title': self._og_search_title(webpage), | |
108 | } | |
8875b3d5 S |
109 | |
110 | ||
111 | class ImgurAlbumIE(InfoExtractor): | |
dbee18b5 | 112 | _VALID_URL = r'https?://(?:i\.)?imgur\.com/(gallery/)?(?P<id>[a-zA-Z0-9]{5})(?![a-zA-Z0-9])' |
8875b3d5 S |
113 | |
114 | _TEST = { | |
115 | 'url': 'http://imgur.com/gallery/Q95ko', | |
116 | 'info_dict': { | |
117 | 'id': 'Q95ko', | |
118 | }, | |
119 | 'playlist_count': 25, | |
120 | } | |
121 | ||
122 | def _real_extract(self, url): | |
123 | album_id = self._match_id(url) | |
124 | ||
dbee18b5 AK |
125 | album_img_data = self._download_json( |
126 | 'http://imgur.com/gallery/%s/album_images/hit.json?all=true' % album_id, album_id)['data'] | |
8875b3d5 | 127 | |
dbee18b5 AK |
128 | if len(album_img_data) == 0: |
129 | return self.url_result('http://imgur.com/%s' % album_id) | |
130 | else: | |
131 | album_images = album_img_data['images'] | |
132 | entries = [ | |
133 | self.url_result('http://imgur.com/%s' % image['hash']) | |
134 | for image in album_images if image.get('hash')] | |
8875b3d5 S |
135 | |
136 | return self.playlist_result(entries, album_id) |