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