]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/imgur.py
fe5d95e2c9cad488f342233e7ebfd52e42a86de3
[youtubedl] / youtube_dl / extractor / imgur.py
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 ExtractorError,
11 )
12
13
14 class ImgurIE(InfoExtractor):
15 _VALID_URL = r'https?://(?:i\.)?imgur\.com/(?P<id>[a-zA-Z0-9]+)(?:\.mp4|\.gifv)?'
16
17 _TESTS = [{
18 'url': 'https://i.imgur.com/A61SaA1.gifv',
19 'info_dict': {
20 'id': 'A61SaA1',
21 'ext': 'mp4',
22 'title': 're:Imgur GIF$|MRW gifv is up and running without any bugs$',
23 'description': 're:The origin of the Internet\'s most viral images$|The Internet\'s visual storytelling community\. Explore, share, and discuss the best visual stories the Internet has to offer\.$',
24 },
25 }, {
26 'url': 'https://imgur.com/A61SaA1',
27 'info_dict': {
28 'id': 'A61SaA1',
29 'ext': 'mp4',
30 'title': 're:Imgur GIF$|MRW gifv is up and running without any bugs$',
31 'description': 're:The origin of the Internet\'s most viral images$|The Internet\'s visual storytelling community\. Explore, share, and discuss the best visual stories the Internet has to offer\.$',
32 },
33 }]
34
35 def _real_extract(self, url):
36 video_id = self._match_id(url)
37 webpage = self._download_webpage(url, video_id)
38
39 width = int_or_none(self._search_regex(
40 r'<param name="width" value="([0-9]+)"',
41 webpage, 'width', fatal=False))
42 height = int_or_none(self._search_regex(
43 r'<param name="height" value="([0-9]+)"',
44 webpage, 'height', fatal=False))
45
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:
50 raise ExtractorError(
51 'No sources found for video %s. Maybe an image?' % video_id,
52 expected=True)
53
54 formats = []
55 for m in re.finditer(r'<source\s+src="(?P<src>[^"]+)"\s+type="(?P<type>[^"]+)"', video_elements):
56 formats.append({
57 'format_id': m.group('type').partition('/')[2],
58 'url': self._proto_relative_url(m.group('src')),
59 'ext': mimetype2ext(m.group('type')),
60 'acodec': 'none',
61 'width': width,
62 'height': height,
63 'http_headers': {
64 'User-Agent': 'youtube-dl (like wget)',
65 },
66 })
67
68 gif_json = self._search_regex(
69 r'(?s)var\s+videoItem\s*=\s*(\{.*?\})',
70 webpage, 'GIF code', fatal=False)
71 if gif_json:
72 gifd = self._parse_json(
73 gif_json, video_id, transform_source=js_to_json)
74 formats.append({
75 'format_id': 'gif',
76 'preference': -10,
77 'width': width,
78 'height': height,
79 'ext': 'gif',
80 'acodec': 'none',
81 'vcodec': 'gif',
82 'container': 'gif',
83 'url': self._proto_relative_url(gifd['gifUrl']),
84 'filesize': gifd.get('size'),
85 'http_headers': {
86 'User-Agent': 'youtube-dl (like wget)',
87 },
88 })
89
90 self._sort_formats(formats)
91
92 return {
93 'id': video_id,
94 'formats': formats,
95 'description': self._og_search_description(webpage),
96 'title': self._og_search_title(webpage),
97 }