]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/sockshare.py
debian/control: Add recommends on aria2 | wget | curl to use external downloaders.
[youtubedl] / youtube_dl / extractor / sockshare.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 import re
5
6 from ..compat import (
7 compat_urllib_parse,
8 compat_urllib_request,
9 )
10 from ..utils import (
11 determine_ext,
12 ExtractorError,
13 )
14
15 from .common import InfoExtractor
16
17
18 class SockshareIE(InfoExtractor):
19 _VALID_URL = r'https?://(?:www\.)?sockshare\.com/file/(?P<id>[0-9A-Za-z]+)'
20 _FILE_DELETED_REGEX = r'This file doesn\'t exist, or has been removed\.</div>'
21 _TEST = {
22 'url': 'http://www.sockshare.com/file/437BE28B89D799D7',
23 'md5': '9d0bf1cfb6dbeaa8d562f6c97506c5bd',
24 'info_dict': {
25 'id': '437BE28B89D799D7',
26 'title': 'big_buck_bunny_720p_surround.avi',
27 'ext': 'avi',
28 'thumbnail': 're:^http://.*\.jpg$',
29 }
30 }
31
32 def _real_extract(self, url):
33 video_id = self._match_id(url)
34 url = 'http://sockshare.com/file/%s' % video_id
35 webpage = self._download_webpage(url, video_id)
36
37 if re.search(self._FILE_DELETED_REGEX, webpage) is not None:
38 raise ExtractorError('Video %s does not exist' % video_id,
39 expected=True)
40
41 confirm_hash = self._html_search_regex(r'''(?x)<input\s+
42 type="hidden"\s+
43 value="([^"]*)"\s+
44 name="hash"
45 ''', webpage, 'hash')
46
47 fields = {
48 "hash": confirm_hash,
49 "confirm": "Continue as Free User"
50 }
51
52 post = compat_urllib_parse.urlencode(fields)
53 req = compat_urllib_request.Request(url, post)
54 # Apparently, this header is required for confirmation to work.
55 req.add_header('Host', 'www.sockshare.com')
56 req.add_header('Content-type', 'application/x-www-form-urlencoded')
57
58 webpage = self._download_webpage(
59 req, video_id, 'Downloading video page')
60
61 video_url = self._html_search_regex(
62 r'<a href="([^"]*)".+class="download_file_link"',
63 webpage, 'file url')
64 video_url = "http://www.sockshare.com" + video_url
65 title = self._html_search_regex((
66 r'<h1>(.+)<strong>',
67 r'var name = "([^"]+)";'),
68 webpage, 'title', default=None)
69 thumbnail = self._html_search_regex(
70 r'<img\s+src="([^"]*)".+?name="bg"',
71 webpage, 'thumbnail')
72
73 formats = [{
74 'format_id': 'sd',
75 'url': video_url,
76 'ext': determine_ext(title),
77 }]
78
79 return {
80 'id': video_id,
81 'title': title,
82 'thumbnail': thumbnail,
83 'formats': formats,
84 }