yt_dlp/extractor/xboxclips.py

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