]> git.bitcoin.ninja Git - youtube-dl/blob - youtube_dl/extractor/ustudio.py
[pornhub:playlistbase] Use orderedSet
[youtube-dl] / youtube_dl / extractor / ustudio.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     unified_strdate,
9 )
10
11
12 class UstudioIE(InfoExtractor):
13     _VALID_URL = r'https?://(?:(?:www|v1)\.)?ustudio\.com/video/(?P<id>[^/]+)/(?P<display_id>[^/?#&]+)'
14     _TEST = {
15         'url': 'http://ustudio.com/video/Uxu2my9bgSph/san_francisco_golden_gate_bridge',
16         'md5': '58bbfca62125378742df01fc2abbdef6',
17         'info_dict': {
18             'id': 'Uxu2my9bgSph',
19             'display_id': 'san_francisco_golden_gate_bridge',
20             'ext': 'mp4',
21             'title': 'San Francisco: Golden Gate Bridge',
22             'description': 'md5:23925500697f2c6d4830e387ba51a9be',
23             'thumbnail': 're:^https?://.*\.jpg$',
24             'upload_date': '20111107',
25             'uploader': 'Tony Farley',
26         }
27     }
28
29     def _real_extract(self, url):
30         mobj = re.match(self._VALID_URL, url)
31         video_id = mobj.group('id')
32         display_id = mobj.group('display_id')
33
34         config = self._download_xml(
35             'http://v1.ustudio.com/embed/%s/ustudio/config.xml' % video_id,
36             display_id)
37
38         def extract(kind):
39             return [{
40                 'url': item.attrib['url'],
41                 'width': int_or_none(item.get('width')),
42                 'height': int_or_none(item.get('height')),
43             } for item in config.findall('./qualities/quality/%s' % kind) if item.get('url')]
44
45         formats = extract('video')
46         self._sort_formats(formats)
47
48         webpage = self._download_webpage(url, display_id)
49
50         title = self._og_search_title(webpage)
51         upload_date = unified_strdate(self._search_regex(
52             r'(?s)Uploaded by\s*.+?\s*on\s*<span>([^<]+)</span>',
53             webpage, 'upload date', fatal=False))
54         uploader = self._search_regex(
55             r'Uploaded by\s*<a[^>]*>([^<]+)<',
56             webpage, 'uploader', fatal=False)
57
58         return {
59             'id': video_id,
60             'display_id': display_id,
61             'title': title,
62             'description': self._og_search_description(webpage),
63             'thumbnails': extract('image'),
64             'upload_date': upload_date,
65             'uploader': uploader,
66             'formats': formats,
67         }