]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/sockshare.py
dc9f8055013170a87a447ee6370f5cae4546174d
[youtubedl] / youtube_dl / extractor / sockshare.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 from ..utils import (
5 ExtractorError,
6 compat_urllib_parse,
7 compat_urllib_request,
8 determine_ext,
9 )
10 import re
11
12 from .common import InfoExtractor
13
14
15 class SockshareIE(InfoExtractor):
16 _VALID_URL = r'https?://(?:www\.)?sockshare\.com/file/(?P<id>[0-9A-Za-z]+)'
17 _FILE_DELETED_REGEX = r'This file doesn\'t exist, or has been removed\.</div>'
18 _TEST = {
19 'url': 'http://www.sockshare.com/file/437BE28B89D799D7',
20 'md5': '9d0bf1cfb6dbeaa8d562f6c97506c5bd',
21 'info_dict': {
22 'id': '437BE28B89D799D7',
23 'title': 'big_buck_bunny_720p_surround.avi',
24 'ext': 'avi',
25 'thumbnail': 're:^http://.*\.jpg$',
26 }
27 }
28
29 def _real_extract(self, url):
30 mobj = re.match(self._VALID_URL, url)
31 video_id = mobj.group('id')
32
33 url = 'http://sockshare.com/file/%s' % video_id
34 webpage = self._download_webpage(url, video_id)
35
36 if re.search(self._FILE_DELETED_REGEX, webpage) is not None:
37 raise ExtractorError('Video %s does not exist' % video_id,
38 expected=True)
39
40 confirm_hash = self._html_search_regex(r'''(?x)<input\s+
41 type="hidden"\s+
42 value="([^"]*)"\s+
43 name="hash"
44 ''', webpage, 'hash')
45
46 fields = {
47 "hash": confirm_hash,
48 "confirm": "Continue as Free User"
49 }
50
51 post = compat_urllib_parse.urlencode(fields)
52 req = compat_urllib_request.Request(url, post)
53 # Apparently, this header is required for confirmation to work.
54 req.add_header('Host', 'www.sockshare.com')
55 req.add_header('Content-type', 'application/x-www-form-urlencoded')
56
57 webpage = self._download_webpage(
58 req, video_id, 'Downloading video page')
59
60 video_url = self._html_search_regex(
61 r'<a href="([^"]*)".+class="download_file_link"',
62 webpage, 'file url')
63 video_url = "http://www.sockshare.com" + video_url
64 title = self._html_search_regex(r'<h1>(.+)<strong>', webpage, 'title')
65 thumbnail = self._html_search_regex(
66 r'<img\s+src="([^"]*)".+?name="bg"',
67 webpage, 'thumbnail')
68
69 formats = [{
70 'format_id': 'sd',
71 'url': video_url,
72 'ext': determine_ext(title),
73 }]
74
75 return {
76 'id': video_id,
77 'title': title,
78 'thumbnail': thumbnail,
79 'formats': formats,
80 }