from .common import InfoExtractor
from ..utils import (
int_or_none,
+ js_to_json,
orderedSet,
parse_duration,
sanitized_Request,
_VALID_URL = r'''(?x)
(?:
xtube:|
- https?://(?:www\.)?xtube\.com/(?:watch\.php\?.*\bv=|video-watch/(?P<display_id>[^/]+)-)
+ https?://(?:www\.)?xtube\.com/(?:watch\.php\?.*\bv=|video-watch/(?:embedded/)?(?P<display_id>[^/]+)-)
)
(?P<id>[^/?&#]+)
'''
'comment_count': int,
'age_limit': 18,
}
+ }, {
+ # FLV videos with duplicated formats
+ 'url': 'http://www.xtube.com/video-watch/A-Super-Run-Part-1-YT-9299752',
+ 'md5': 'a406963eb349dd43692ec54631efd88b',
+ 'info_dict': {
+ 'id': '9299752',
+ 'display_id': 'A-Super-Run-Part-1-YT',
+ 'ext': 'flv',
+ 'title': 'A Super Run - Part 1 (YT)',
+ 'description': 'md5:ca0d47afff4a9b2942e4b41aa970fd93',
+ 'uploader': 'tshirtguy59',
+ 'duration': 579,
+ 'view_count': int,
+ 'comment_count': int,
+ 'age_limit': 18,
+ },
}, {
# new URL schema
'url': 'http://www.xtube.com/video-watch/strange-erotica-625837',
}, {
'url': 'xtube:625837',
'only_matching': True,
+ }, {
+ 'url': 'xtube:kVTUy_G222_',
+ 'only_matching': True,
+ }, {
+ 'url': 'https://www.xtube.com/video-watch/embedded/milf-tara-and-teen-shared-and-cum-covered-extreme-bukkake-32203482?embedsize=big',
+ 'only_matching': True,
}]
def _real_extract(self, url):
if not display_id:
display_id = video_id
- url = 'http://www.xtube.com/watch.php?v=%s' % video_id
- req = sanitized_Request(url)
- req.add_header('Cookie', 'age_verified=1; cookiesAccepted=1')
- webpage = self._download_webpage(req, display_id)
+ if video_id.isdigit() and len(video_id) < 11:
+ url_pattern = 'http://www.xtube.com/video-watch/-%s'
+ else:
+ url_pattern = 'http://www.xtube.com/watch.php?v=%s'
+
+ webpage = self._download_webpage(
+ url_pattern % video_id, display_id, headers={
+ 'Cookie': 'age_verified=1; cookiesAccepted=1',
+ })
sources = self._parse_json(self._search_regex(
- r'(["\'])sources\1\s*:\s*(?P<sources>{.+?}),',
- webpage, 'sources', group='sources'), video_id)
+ r'(["\'])?sources\1?\s*:\s*(?P<sources>{.+?}),',
+ webpage, 'sources', group='sources'), video_id,
+ transform_source=js_to_json)
formats = []
for format_id, format_url in sources.items():
'format_id': format_id,
'height': int_or_none(format_id),
})
+ self._remove_duplicate_formats(formats)
self._sort_formats(formats)
title = self._search_regex(