1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-11-24 03:01:53 +00:00
youtube-dl/youtube_dl/extractor/extremetube.py

66 lines
2.2 KiB
Python
Raw Normal View History

2014-04-19 17:42:51 +00:00
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
compat_urllib_parse_urlparse,
compat_urllib_request,
compat_urllib_parse,
2014-09-27 15:36:53 +00:00
str_to_int,
)
2014-04-19 17:42:51 +00:00
class ExtremeTubeIE(InfoExtractor):
_VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>extremetube\.com/.*?video/.+?(?P<videoid>[0-9]+))(?:[/?&]|$)'
_TESTS = [{
2014-04-19 17:42:51 +00:00
'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',
2014-09-27 15:36:53 +00:00
'view_count': int,
2014-04-19 17:42:51 +00:00
'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('videoid')
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)
2014-04-19 17:42:51 +00:00
video_title = self._html_search_regex(
r'<h1 [^>]*?title="([^"]+)"[^>]*>', webpage, 'title')
2014-04-19 17:42:51 +00:00
uploader = self._html_search_regex(
2014-09-27 15:36:53 +00:00
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))
2014-04-19 17:42:51 +00:00
video_url = compat_urllib_parse.unquote(self._html_search_regex(
r'video_url=(.+?)&amp;', 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,
2014-09-27 15:36:53 +00:00
'view_count': view_count,
'url': video_url,
'format': format,
'format_id': format,
'age_limit': 18,
}