mirror of
https://github.com/ytdl-org/youtube-dl.git
synced 2024-11-29 21:52:54 +00:00
62 lines
2.4 KiB
Python
62 lines
2.4 KiB
Python
|
import re
|
||
|
|
|
||
|
|
from .common import InfoExtractor
|
||
|
|
from ..utils import (
|
||
|
|
compat_urllib_parse,
|
||
|
|
|
||
|
|
ExtractorError,
|
||
|
|
)
|
||
|
|
|
||
|
|
|
||
|
|
class XHamsterIE(InfoExtractor):
|
||
|
|
"""Information Extractor for xHamster"""
|
||
|
|
_VALID_URL = r'(?:http://)?(?:www.)?xhamster\.com/movies/(?P<id>[0-9]+)/.*\.html'
|
||
|
|
|
||
|
|
def _real_extract(self,url):
|
||
|
|
mobj = re.match(self._VALID_URL, url)
|
||
|
|
|
||
|
|
video_id = mobj.group('id')
|
||
|
|
mrss_url = 'http://xhamster.com/movies/%s/.html' % video_id
|
||
|
|
webpage = self._download_webpage(mrss_url, video_id)
|
||
|
|
|
||
|
|
mobj = re.search(r'\'srv\': \'(?P<server>[^\']*)\',\s*\'file\': \'(?P<file>[^\']+)\',', webpage)
|
||
|
|
if mobj is None:
|
||
|
|
raise ExtractorError(u'Unable to extract media URL')
|
||
|
|
if len(mobj.group('server')) == 0:
|
||
|
|
video_url = compat_urllib_parse.unquote(mobj.group('file'))
|
||
|
|
else:
|
||
|
|
video_url = mobj.group('server')+'/key='+mobj.group('file')
|
||
|
|
video_extension = video_url.split('.')[-1]
|
||
|
|
|
||
|
|
video_title = self._html_search_regex(r'<title>(?P<title>.+?) - xHamster\.com</title>',
|
||
|
|
webpage, u'title')
|
||
|
|
|
||
|
|
# Can't see the description anywhere in the UI
|
||
|
|
# video_description = self._html_search_regex(r'<span>Description: </span>(?P<description>[^<]+)',
|
||
|
|
# webpage, u'description', fatal=False)
|
||
|
|
# if video_description: video_description = unescapeHTML(video_description)
|
||
|
|
|
||
|
|
mobj = re.search(r'hint=\'(?P<upload_date_Y>[0-9]{4})-(?P<upload_date_m>[0-9]{2})-(?P<upload_date_d>[0-9]{2}) [0-9]{2}:[0-9]{2}:[0-9]{2} [A-Z]{3,4}\'', webpage)
|
||
|
|
if mobj:
|
||
|
|
video_upload_date = mobj.group('upload_date_Y')+mobj.group('upload_date_m')+mobj.group('upload_date_d')
|
||
|
|
else:
|
||
|
|
video_upload_date = None
|
||
|
|
self._downloader.report_warning(u'Unable to extract upload date')
|
||
|
|
|
||
|
|
video_uploader_id = self._html_search_regex(r'<a href=\'/user/[^>]+>(?P<uploader_id>[^<]+)',
|
||
|
|
webpage, u'uploader id', default=u'anonymous')
|
||
|
|
|
||
|
|
video_thumbnail = self._search_regex(r'\'image\':\'(?P<thumbnail>[^\']+)\'',
|
||
|
|
webpage, u'thumbnail', fatal=False)
|
||
|
|
|
||
|
|
return [{
|
||
|
|
'id': video_id,
|
||
|
|
'url': video_url,
|
||
|
|
'ext': video_extension,
|
||
|
|
'title': video_title,
|
||
|
|
# 'description': video_description,
|
||
|
|
'upload_date': video_upload_date,
|
||
|
|
'uploader_id': video_uploader_id,
|
||
|
|
'thumbnail': video_thumbnail
|
||
|
|
}]
|