ytdl-nightly/youtube_dl/extractor/xhamster.py

85 lines
3.2 KiB
Python
Raw Normal View History

2013-06-23 22:32:44 +02:00
import re
from .common import InfoExtractor
from ..utils import (
compat_urllib_parse,
2013-08-23 16:40:20 +02:00
unescapeHTML,
2013-08-23 17:23:34 +02:00
determine_ext,
2013-06-23 22:32:44 +02:00
ExtractorError,
)
class XHamsterIE(InfoExtractor):
"""Information Extractor for xHamster"""
_VALID_URL = r'(?:http://)?(?:www\.)?xhamster\.com/movies/(?P<id>[0-9]+)/(?P<seo>.+?)\.html(?:\?.*)?'
_TESTS = [{
2013-06-27 20:46:46 +02:00
u'url': u'http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html',
u'file': u'1509445.flv',
u'md5': u'9f48e0e8d58e3076bb236ff412ab62fa',
u'info_dict': {
u"upload_date": u"20121014",
u"uploader_id": u"Ruseful2011",
u"title": u"FemaleAgent Shy beauty takes the bait"
}
},
{
u'url': u'http://xhamster.com/movies/2221348/britney_spears_sexy_booty.html?hd',
u'file': u'2221348.flv',
u'md5': u'e767b9475de189320f691f49c679c4c7',
u'info_dict': {
u"upload_date": u"20130914",
u"uploader_id": u"jojo747400",
u"title": u"Britney Spears Sexy Booty"
}
}]
2013-06-23 22:32:44 +02:00
def _real_extract(self,url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
seo = mobj.group('seo')
mrss_url = 'http://xhamster.com/movies/%s/%s.html?hd' % (video_id, seo)
2013-06-23 22:32:44 +02:00
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_title = self._html_search_regex(r'<title>(?P<title>.+?) - xHamster\.com</title>',
webpage, u'title')
2013-08-23 16:40:20 +02:00
# Only a few videos have an description
mobj = re.search('<span>Description: </span>(?P<description>[^<]+)', webpage)
if mobj:
video_description = unescapeHTML(mobj.group('description'))
else:
video_description = None
2013-06-23 22:32:44 +02:00
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,
2013-08-23 17:23:34 +02:00
'ext': determine_ext(video_url),
2013-06-23 22:32:44 +02:00
'title': video_title,
2013-08-23 16:40:20 +02:00
'description': video_description,
2013-06-23 22:32:44 +02:00
'upload_date': video_upload_date,
'uploader_id': video_uploader_id,
'thumbnail': video_thumbnail
}]