]>
Commit | Line | Data |
---|---|---|
3bf57053 PH |
1 | from __future__ import unicode_literals |
2 | ||
3 | import re | |
4 | ||
5 | from .common import InfoExtractor | |
6 | from ..utils import ( | |
7 | int_or_none, | |
8 | js_to_json, | |
9 | mimetype2ext, | |
10 | ) | |
11 | ||
12 | ||
13 | class ImgurIE(InfoExtractor): | |
14 | _VALID_URL = r'https?://i\.imgur\.com/(?P<id>[a-zA-Z0-9]+)\.(?:mp4|gifv)' | |
15 | ||
16 | _TESTS = [{ | |
17 | 'url': 'https://i.imgur.com/A61SaA1.gifv', | |
18 | 'info_dict': { | |
19 | 'id': 'A61SaA1', | |
20 | 'ext': 'mp4', | |
21 | 'title': 'MRW gifv is up and running without any bugs', | |
22 | 'description': 'The Internet\'s visual storytelling community. Explore, share, and discuss the best visual stories the Internet has to offer.', | |
23 | }, | |
24 | }] | |
25 | ||
26 | def _real_extract(self, url): | |
27 | video_id = self._match_id(url) | |
28 | webpage = self._download_webpage(url, video_id) | |
29 | ||
30 | width = int_or_none(self._search_regex( | |
31 | r'<param name="width" value="([0-9]+)"', | |
32 | webpage, 'width', fatal=False)) | |
33 | height = int_or_none(self._search_regex( | |
34 | r'<param name="height" value="([0-9]+)"', | |
35 | webpage, 'height', fatal=False)) | |
36 | ||
37 | formats = [] | |
38 | video_elements = self._search_regex( | |
39 | r'(?s)<div class="video-elements">(.*?)</div>', | |
40 | webpage, 'video elements') | |
41 | formats = [] | |
42 | for m in re.finditer(r'<source\s+src="(?P<src>[^"]+)"\s+type="(?P<type>[^"]+)"', video_elements): | |
43 | formats.append({ | |
44 | 'format_id': m.group('type').partition('/')[2], | |
45 | 'url': self._proto_relative_url(m.group('src')), | |
46 | 'ext': mimetype2ext(m.group('type')), | |
47 | 'acodec': 'none', | |
48 | 'width': width, | |
49 | 'height': height, | |
50 | 'http_headers': { | |
51 | 'User-Agent': 'youtube-dl (like wget)', | |
52 | }, | |
53 | }) | |
54 | ||
55 | gif_json = self._search_regex( | |
56 | r'(?s)var\s+videoItem\s*=\s*(\{.*?\})', | |
57 | webpage, 'GIF code', fatal=False) | |
58 | if gif_json: | |
59 | gifd = self._parse_json( | |
60 | gif_json, video_id, transform_source=js_to_json) | |
61 | formats.append({ | |
62 | 'format_id': 'gif', | |
63 | 'preference': -10, | |
64 | 'width': width, | |
65 | 'height': height, | |
66 | 'ext': 'gif', | |
67 | 'acodec': 'none', | |
68 | 'vcodec': 'gif', | |
69 | 'container': 'gif', | |
70 | 'url': self._proto_relative_url(gifd['gifUrl']), | |
71 | 'filesize': gifd.get('size'), | |
72 | 'http_headers': { | |
73 | 'User-Agent': 'youtube-dl (like wget)', | |
74 | }, | |
75 | }) | |
76 | ||
77 | self._sort_formats(formats) | |
78 | ||
79 | return { | |
80 | 'id': video_id, | |
81 | 'formats': formats, | |
82 | 'description': self._og_search_description(webpage), | |
83 | 'title': self._og_search_title(webpage), | |
84 | } |