2014-01-23 02:52:59 +00:00
|
|
|
from __future__ import unicode_literals
|
|
|
|
|
2013-06-23 20:32:44 +00:00
|
|
|
import re
|
|
|
|
|
|
|
|
from .common import InfoExtractor
|
|
|
|
from ..utils import (
|
|
|
|
compat_urllib_parse,
|
2013-08-23 14:40:20 +00:00
|
|
|
unescapeHTML,
|
2013-06-23 20:32:44 +00:00
|
|
|
ExtractorError,
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
|
|
class XHamsterIE(InfoExtractor):
|
|
|
|
"""Information Extractor for xHamster"""
|
2013-09-17 04:24:20 +00:00
|
|
|
_VALID_URL = r'(?:http://)?(?:www\.)?xhamster\.com/movies/(?P<id>[0-9]+)/(?P<seo>.+?)\.html(?:\?.*)?'
|
|
|
|
_TESTS = [{
|
2014-01-23 02:52:59 +00:00
|
|
|
'url': 'http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html',
|
2014-01-23 03:04:35 +00:00
|
|
|
'file': '1509445.mp4',
|
|
|
|
'md5': '8281348b8d3c53d39fffb377d24eac4e',
|
2014-01-23 02:52:59 +00:00
|
|
|
'info_dict': {
|
2014-01-23 03:04:35 +00:00
|
|
|
"upload_date": "20121014",
|
|
|
|
"uploader_id": "Ruseful2011",
|
2014-01-23 02:52:59 +00:00
|
|
|
"title": "FemaleAgent Shy beauty takes the bait",
|
|
|
|
"age_limit": 18,
|
2013-06-27 18:46:46 +00:00
|
|
|
}
|
2013-09-17 04:24:20 +00:00
|
|
|
},
|
|
|
|
{
|
2014-01-23 02:52:59 +00:00
|
|
|
'url': 'http://xhamster.com/movies/2221348/britney_spears_sexy_booty.html?hd',
|
|
|
|
'file': '2221348.flv',
|
|
|
|
'md5': 'e767b9475de189320f691f49c679c4c7',
|
|
|
|
'info_dict': {
|
|
|
|
"upload_date": "20130914",
|
|
|
|
"uploader_id": "jojo747400",
|
|
|
|
"title": "Britney Spears Sexy Booty",
|
|
|
|
"age_limit": 18,
|
2013-09-17 04:24:20 +00:00
|
|
|
}
|
|
|
|
}]
|
2013-06-23 20:32:44 +00:00
|
|
|
|
|
|
|
def _real_extract(self,url):
|
2013-10-26 18:38:54 +00:00
|
|
|
def extract_video_url(webpage):
|
|
|
|
mobj = re.search(r'\'srv\': \'(?P<server>[^\']*)\',\s*\'file\': \'(?P<file>[^\']+)\',', webpage)
|
|
|
|
if mobj is None:
|
2014-01-23 03:04:35 +00:00
|
|
|
raise ExtractorError('Unable to extract media URL')
|
2013-10-26 18:38:54 +00:00
|
|
|
if len(mobj.group('server')) == 0:
|
|
|
|
return compat_urllib_parse.unquote(mobj.group('file'))
|
|
|
|
else:
|
|
|
|
return mobj.group('server')+'/key='+mobj.group('file')
|
|
|
|
|
2014-01-23 02:51:09 +00:00
|
|
|
def extract_mp4_video_url(webpage):
|
|
|
|
mp4 = re.search(r'<a href=\"(.+?)\" class=\"mp4Play\"',webpage)
|
|
|
|
if mp4 is None:
|
|
|
|
return None
|
|
|
|
else:
|
|
|
|
return mp4.group(1)
|
|
|
|
|
2013-10-26 18:38:54 +00:00
|
|
|
def is_hd(webpage):
|
2014-01-23 03:04:35 +00:00
|
|
|
return '<div class=\'icon iconHD\'' in webpage
|
2013-10-26 18:38:54 +00:00
|
|
|
|
2013-06-23 20:32:44 +00:00
|
|
|
mobj = re.match(self._VALID_URL, url)
|
|
|
|
|
|
|
|
video_id = mobj.group('id')
|
2013-09-17 04:24:20 +00:00
|
|
|
seo = mobj.group('seo')
|
2013-10-26 18:38:54 +00:00
|
|
|
mrss_url = 'http://xhamster.com/movies/%s/%s.html' % (video_id, seo)
|
2013-06-23 20:32:44 +00:00
|
|
|
webpage = self._download_webpage(mrss_url, video_id)
|
|
|
|
|
2014-01-23 03:04:35 +00:00
|
|
|
video_title = self._html_search_regex(
|
|
|
|
r'<title>(?P<title>.+?) - xHamster\.com</title>', webpage, 'title')
|
2013-06-23 20:32:44 +00:00
|
|
|
|
2013-08-23 14:40:20 +00:00
|
|
|
# Only a few videos have an description
|
2014-01-23 03:04:35 +00:00
|
|
|
mobj = re.search(r'<span>Description: </span>([^<]+)', webpage)
|
|
|
|
video_description = mobj.group(1) if mobj else None
|
2013-06-23 20:32:44 +00:00
|
|
|
|
|
|
|
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
|
2014-01-23 03:04:35 +00:00
|
|
|
self._downloader.report_warning('Unable to extract upload date')
|
2013-06-23 20:32:44 +00:00
|
|
|
|
2014-01-23 03:04:35 +00:00
|
|
|
video_uploader_id = self._html_search_regex(
|
|
|
|
r'<a href=\'/user/[^>]+>(?P<uploader_id>[^<]+)',
|
|
|
|
webpage, 'uploader id', default='anonymous')
|
2013-06-23 20:32:44 +00:00
|
|
|
|
2014-01-23 03:04:35 +00:00
|
|
|
video_thumbnail = self._search_regex(
|
|
|
|
r'\'image\':\'(?P<thumbnail>[^\']+)\'',
|
2014-01-23 02:52:59 +00:00
|
|
|
webpage, 'thumbnail', fatal=False)
|
2013-06-23 20:32:44 +00:00
|
|
|
|
2013-10-19 19:09:48 +00:00
|
|
|
age_limit = self._rta_search(webpage)
|
|
|
|
|
2013-10-26 18:38:54 +00:00
|
|
|
hd = is_hd(webpage)
|
2014-01-23 02:51:09 +00:00
|
|
|
video_url = extract_video_url(webpage)
|
2013-10-26 18:38:54 +00:00
|
|
|
formats = [{
|
|
|
|
'url': video_url,
|
|
|
|
'format_id': 'hd' if hd else 'sd',
|
2014-01-23 03:04:35 +00:00
|
|
|
'preference': 0,
|
2013-10-26 18:38:54 +00:00
|
|
|
}]
|
2014-01-23 02:51:09 +00:00
|
|
|
|
|
|
|
video_mp4_url = extract_mp4_video_url(webpage)
|
2014-01-23 03:04:35 +00:00
|
|
|
if video_mp4_url is not None:
|
2014-01-23 02:52:59 +00:00
|
|
|
formats.append({
|
|
|
|
'url': video_mp4_url,
|
|
|
|
'ext': 'mp4',
|
2014-01-23 03:04:35 +00:00
|
|
|
'format_id': 'mp4-hd' if hd else 'mp4-sd',
|
|
|
|
'preference': 1,
|
2014-01-23 02:52:59 +00:00
|
|
|
})
|
2014-01-23 02:51:09 +00:00
|
|
|
|
2013-10-26 18:38:54 +00:00
|
|
|
if not hd:
|
2014-01-23 03:04:35 +00:00
|
|
|
webpage = self._download_webpage(
|
|
|
|
mrss_url + '?hd', video_id, note='Downloading HD webpage')
|
2013-10-26 18:38:54 +00:00
|
|
|
if is_hd(webpage):
|
|
|
|
video_url = extract_video_url(webpage)
|
|
|
|
formats.append({
|
|
|
|
'url': video_url,
|
|
|
|
'format_id': 'hd',
|
2014-01-23 03:04:35 +00:00
|
|
|
'preference': 2,
|
2013-10-26 18:38:54 +00:00
|
|
|
})
|
|
|
|
|
2014-01-23 03:04:35 +00:00
|
|
|
self._sort_formats(formats)
|
|
|
|
|
2013-10-26 18:38:54 +00:00
|
|
|
return {
|
|
|
|
'id': video_id,
|
|
|
|
'title': video_title,
|
|
|
|
'formats': formats,
|
2013-08-23 14:40:20 +00:00
|
|
|
'description': video_description,
|
2013-06-23 20:32:44 +00:00
|
|
|
'upload_date': video_upload_date,
|
|
|
|
'uploader_id': video_uploader_id,
|
2013-10-19 19:09:48 +00:00
|
|
|
'thumbnail': video_thumbnail,
|
|
|
|
'age_limit': age_limit,
|
2013-10-26 18:38:54 +00:00
|
|
|
}
|