youtube-dl/youtube_dl/extractor/xboxclips.py

69 lines
2.4 KiB
Python
Raw Permalink Normal View History

2016-10-02 11:39:18 +00:00
# coding: utf-8
from __future__ import unicode_literals
import re
2014-08-08 06:48:02 +00:00
from .common import InfoExtractor
from ..compat import (
compat_parse_qs,
compat_urllib_parse_urlparse,
)
from ..utils import (
int_or_none,
month_by_abbreviation,
2014-12-31 17:59:16 +00:00
parse_filesize,
)
2014-08-08 06:48:02 +00:00
class XboxClipsIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?(?:xboxclips\.com|gameclips\.io)/(?:video\.php\?.*vid=|[^/]+/)(?P<id>[\da-f]{8}-(?:[\da-f]{4}-){3}[\da-f]{12})'
_TESTS = [{
'url': 'http://xboxclips.com/video.php?uid=2533274823424419&gamertag=Iabdulelah&vid=074a69a9-5faf-46aa-b93b-9909c1720325',
'md5': 'fbe1ec805e920aeb8eced3c3e657df5d',
'info_dict': {
'id': '074a69a9-5faf-46aa-b93b-9909c1720325',
'ext': 'mp4',
'title': 'iAbdulElah playing Titanfall',
2014-12-31 17:59:16 +00:00
'filesize_approx': 26800000,
'upload_date': '20140807',
'duration': 56,
}
}, {
'url': 'https://gameclips.io/iAbdulElah/074a69a9-5faf-46aa-b93b-9909c1720325',
'only_matching': True,
}]
2014-08-08 06:48:02 +00:00
def _real_extract(self, url):
2014-12-31 17:59:16 +00:00
video_id = self._match_id(url)
2014-08-08 06:48:02 +00:00
if '/video.php' in url:
qs = compat_parse_qs(compat_urllib_parse_urlparse(url).query)
url = 'https://gameclips.io/%s/%s' % (qs['gamertag'][0], qs['vid'][0])
2014-08-08 06:48:02 +00:00
webpage = self._download_webpage(url, video_id)
info = self._parse_html5_media_entries(url, webpage, video_id)[0]
2014-08-08 06:48:02 +00:00
title = self._html_search_meta(['og:title', 'twitter:title'], webpage)
upload_date = None
mobj = re.search(
r'>Recorded: (\d{2})-(Jan|Feb|Mar|Apr|May|Ju[nl]|Aug|Sep|Oct|Nov|Dec)-(\d{4})',
webpage)
if mobj:
upload_date = '%s%.2d%s' % (mobj.group(3), month_by_abbreviation(mobj.group(2)), mobj.group(1))
2014-12-31 17:59:16 +00:00
filesize = parse_filesize(self._html_search_regex(
r'>Size: ([^<]+)<', webpage, 'file size', fatal=False))
duration = int_or_none(self._html_search_regex(
r'>Duration: (\d+) Seconds<', webpage, 'duration', fatal=False))
view_count = int_or_none(self._html_search_regex(
r'>Views: (\d+)<', webpage, 'view count', fatal=False))
2014-08-08 06:48:02 +00:00
info.update({
'id': video_id,
'title': title,
2014-12-31 17:59:16 +00:00
'upload_date': upload_date,
'filesize_approx': filesize,
'duration': duration,
'view_count': view_count,
})
return info