]> git.bitcoin.ninja Git - youtube-dl/blob - youtube_dl/extractor/xboxclips.py
Merge remote-tracking branch 'dstftw/escape-non-ascii-in-urls'
[youtube-dl] / youtube_dl / extractor / xboxclips.py
1 # encoding: utf-8
2 from __future__ import unicode_literals
3
4 import re
5
6 from .common import InfoExtractor
7 from ..utils import (
8     parse_iso8601,
9     float_or_none,
10     int_or_none,
11 )
12
13
14 class XboxClipsIE(InfoExtractor):
15     _VALID_URL = r'https?://(?:www\.)?xboxclips\.com/video\.php\?.*vid=(?P<id>[\w-]{36})'
16     _TEST = {
17         'url': 'https://xboxclips.com/video.php?uid=2533274823424419&gamertag=Iabdulelah&vid=074a69a9-5faf-46aa-b93b-9909c1720325',
18         'md5': 'fbe1ec805e920aeb8eced3c3e657df5d',
19         'info_dict': {
20             'id': '074a69a9-5faf-46aa-b93b-9909c1720325',
21             'ext': 'mp4',
22             'title': 'Iabdulelah playing Upload Studio',
23             'filesize_approx': 28101836.8,
24             'timestamp': 1407388500,
25             'upload_date': '20140807',
26             'duration': 56,
27         }
28     }
29
30     def _real_extract(self, url):
31         mobj = re.match(self._VALID_URL, url)
32         video_id = mobj.group('id')
33
34         webpage = self._download_webpage(url, video_id)
35
36         video_url = self._html_search_regex(
37             r'>Link: <a href="([^"]+)">', webpage, 'video URL')
38         title = self._html_search_regex(
39             r'<title>XboxClips \| ([^<]+)</title>', webpage, 'title')
40         timestamp = parse_iso8601(self._html_search_regex(
41             r'>Recorded: ([^<]+)<', webpage, 'upload date', fatal=False))
42         filesize = float_or_none(self._html_search_regex(
43             r'>Size: ([\d\.]+)MB<', webpage, 'file size', fatal=False), invscale=1024 * 1024)
44         duration = int_or_none(self._html_search_regex(
45             r'>Duration: (\d+) Seconds<', webpage, 'duration', fatal=False))
46         view_count = int_or_none(self._html_search_regex(
47             r'>Views: (\d+)<', webpage, 'view count', fatal=False))
48
49         return {
50             'id': video_id,
51             'url': video_url,
52             'title': title,
53             'timestamp': timestamp,
54             'filesize_approx': filesize,
55             'duration': duration,
56             'view_count': view_count,
57         }