youtube_dl/extractor/xboxclips.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..compat import (
   8     compat_parse_qs,
   9     compat_urllib_parse_urlparse,
  10 )
  11 from ..utils import (
  12     int_or_none,
  13     month_by_abbreviation,
  14     parse_filesize,
  15 )
  16
  17
  18 class XboxClipsIE(InfoExtractor):
  19     _VALID_URL = r'https?://(?:www\.)?(?:xboxclips\.com|gameclips\.io)/(?:video\.php\?.*vid=|[^/]+/)(?P<id>[\da-f]{8}-(?:[\da-f]{4}-){3}[\da-f]{12})'
  20     _TESTS = [{
  21         'url': 'http://xboxclips.com/video.php?uid=2533274823424419&gamertag=Iabdulelah&vid=074a69a9-5faf-46aa-b93b-9909c1720325',
  22         'md5': 'fbe1ec805e920aeb8eced3c3e657df5d',
  23         'info_dict': {
  24             'id': '074a69a9-5faf-46aa-b93b-9909c1720325',
  25             'ext': 'mp4',
  26             'title': 'iAbdulElah playing Titanfall',
  27             'filesize_approx': 26800000,
  28             'upload_date': '20140807',
  29             'duration': 56,
  30         }
  31     }, {
  32         'url': 'https://gameclips.io/iAbdulElah/074a69a9-5faf-46aa-b93b-9909c1720325',
  33         'only_matching': True,
  34     }]
  35
  36     def _real_extract(self, url):
  37         video_id = self._match_id(url)
  38
  39         if '/video.php' in url:
  40             qs = compat_parse_qs(compat_urllib_parse_urlparse(url).query)
  41             url = 'https://gameclips.io/%s/%s' % (qs['gamertag'][0], qs['vid'][0])
  42
  43         webpage = self._download_webpage(url, video_id)
  44         info = self._parse_html5_media_entries(url, webpage, video_id)[0]
  45
  46         title = self._html_search_meta(['og:title', 'twitter:title'], webpage)
  47         upload_date = None
  48         mobj = re.search(
  49             r'>Recorded: (\d{2})-(Jan|Feb|Mar|Apr|May|Ju[nl]|Aug|Sep|Oct|Nov|Dec)-(\d{4})',
  50             webpage)
  51         if mobj:
  52             upload_date = '%s%.2d%s' % (mobj.group(3), month_by_abbreviation(mobj.group(2)), mobj.group(1))
  53         filesize = parse_filesize(self._html_search_regex(
  54             r'>Size: ([^<]+)<', webpage, 'file size', fatal=False))
  55         duration = int_or_none(self._html_search_regex(
  56             r'>Duration: (\d+) Seconds<', webpage, 'duration', fatal=False))
  57         view_count = int_or_none(self._html_search_regex(
  58             r'>Views: (\d+)<', webpage, 'view count', fatal=False))
  59
  60         info.update({
  61             'id': video_id,
  62             'title': title,
  63             'upload_date': upload_date,
  64             'filesize_approx': filesize,
  65             'duration': duration,
  66             'view_count': view_count,
  67         })
  68         return info