mirror of
https://github.com/ytdl-org/youtube-dl.git
synced 2024-11-27 04:32:16 +00:00
1cc79574fc
· Import from compat what comes from compat. Yes, some names are available in utils too, but that's an implementation detail. · Use _match_id consistently whenever possible · Fix some outdated tests · Use consistent valid URL (always match the whole protocol, no ^ at start required) · Use modern test definitions
67 lines
2.2 KiB
Python
67 lines
2.2 KiB
Python
from __future__ import unicode_literals
|
|
|
|
import re
|
|
|
|
from .common import InfoExtractor
|
|
from ..compat import (
|
|
compat_urllib_parse_urlparse,
|
|
compat_urllib_request,
|
|
compat_urllib_parse,
|
|
)
|
|
from ..utils import (
|
|
str_to_int,
|
|
)
|
|
|
|
|
|
class ExtremeTubeIE(InfoExtractor):
|
|
_VALID_URL = r'https?://(?:www\.)?(?P<url>extremetube\.com/.*?video/.+?(?P<id>[0-9]+))(?:[/?&]|$)'
|
|
_TESTS = [{
|
|
'url': 'http://www.extremetube.com/video/music-video-14-british-euro-brit-european-cumshots-swallow-652431',
|
|
'md5': '1fb9228f5e3332ec8c057d6ac36f33e0',
|
|
'info_dict': {
|
|
'id': '652431',
|
|
'ext': 'mp4',
|
|
'title': 'Music Video 14 british euro brit european cumshots swallow',
|
|
'uploader': 'unknown',
|
|
'view_count': int,
|
|
'age_limit': 18,
|
|
}
|
|
}, {
|
|
'url': 'http://www.extremetube.com/gay/video/abcde-1234',
|
|
'only_matching': True,
|
|
}]
|
|
|
|
def _real_extract(self, url):
|
|
mobj = re.match(self._VALID_URL, url)
|
|
video_id = mobj.group('id')
|
|
url = 'http://www.' + mobj.group('url')
|
|
|
|
req = compat_urllib_request.Request(url)
|
|
req.add_header('Cookie', 'age_verified=1')
|
|
webpage = self._download_webpage(req, video_id)
|
|
|
|
video_title = self._html_search_regex(
|
|
r'<h1 [^>]*?title="([^"]+)"[^>]*>', webpage, 'title')
|
|
uploader = self._html_search_regex(
|
|
r'Uploaded by:\s*</strong>\s*(.+?)\s*</div>',
|
|
webpage, 'uploader', fatal=False)
|
|
view_count = str_to_int(self._html_search_regex(
|
|
r'Views:\s*</strong>\s*<span>([\d,\.]+)</span>',
|
|
webpage, 'view count', fatal=False))
|
|
|
|
video_url = compat_urllib_parse.unquote(self._html_search_regex(
|
|
r'video_url=(.+?)&', webpage, 'video_url'))
|
|
path = compat_urllib_parse_urlparse(video_url).path
|
|
format = path.split('/')[5].split('_')[:2]
|
|
format = "-".join(format)
|
|
|
|
return {
|
|
'id': video_id,
|
|
'title': video_title,
|
|
'uploader': uploader,
|
|
'view_count': view_count,
|
|
'url': video_url,
|
|
'format': format,
|
|
'format_id': format,
|
|
'age_limit': 18,
|
|
}
|