]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/shared.py
debian/copyright: Fix lintian's dep5-copyright-license-name-not-unique.
[youtubedl] / youtube_dl / extractor / shared.py
1 from __future__ import unicode_literals
2
3 import re
4 import base64
5
6 from .common import InfoExtractor
7 from ..compat import (
8 compat_urllib_parse,
9 compat_urllib_request,
10 )
11 from ..utils import (
12 ExtractorError,
13 int_or_none,
14 )
15
16
17 class SharedIE(InfoExtractor):
18 _VALID_URL = r'http://shared\.sx/(?P<id>[\da-z]{10})'
19
20 _TEST = {
21 'url': 'http://shared.sx/0060718775',
22 'md5': '106fefed92a8a2adb8c98e6a0652f49b',
23 'info_dict': {
24 'id': '0060718775',
25 'ext': 'mp4',
26 'title': 'Bmp4',
27 },
28 }
29
30 def _real_extract(self, url):
31 video_id = self._match_id(url)
32 webpage = self._download_webpage(url, video_id)
33
34 if '>File does not exist<' in webpage:
35 raise ExtractorError(
36 'Video %s does not exist' % video_id, expected=True)
37
38 download_form = dict(re.findall(
39 r'<input type="hidden" name="([^"]+)" value="([^"]*)"', webpage))
40 request = compat_urllib_request.Request(
41 url, compat_urllib_parse.urlencode(download_form))
42 request.add_header('Content-Type', 'application/x-www-form-urlencoded')
43
44 video_page = self._download_webpage(
45 request, video_id, 'Downloading video page')
46
47 video_url = self._html_search_regex(
48 r'data-url="([^"]+)"', video_page, 'video URL')
49 title = base64.b64decode(self._html_search_meta(
50 'full:title', webpage, 'title')).decode('utf-8')
51 filesize = int_or_none(self._html_search_meta(
52 'full:size', webpage, 'file size', fatal=False))
53 thumbnail = self._html_search_regex(
54 r'data-poster="([^"]+)"', video_page, 'thumbnail', default=None)
55
56 return {
57 'id': video_id,
58 'url': video_url,
59 'ext': 'mp4',
60 'filesize': filesize,
61 'title': title,
62 'thumbnail': thumbnail,
63 }