2014-03-20 16:19:54 -07:00
|
|
|
from __future__ import unicode_literals
|
|
|
|
|
|
|
|
|
2013-06-23 13:12:14 -07:00
|
|
|
import json
|
|
|
|
import re
|
|
|
|
import sys
|
|
|
|
|
|
|
|
from .common import InfoExtractor
|
|
|
|
from ..utils import (
|
|
|
|
compat_urllib_parse_urlparse,
|
|
|
|
compat_urllib_request,
|
|
|
|
|
|
|
|
ExtractorError,
|
|
|
|
unescapeHTML,
|
|
|
|
unified_strdate,
|
|
|
|
)
|
2013-08-09 09:37:33 -07:00
|
|
|
from ..aes import (
|
|
|
|
aes_decrypt_text
|
|
|
|
)
|
2013-06-23 13:12:14 -07:00
|
|
|
|
2013-12-26 09:37:12 -08:00
|
|
|
|
2013-06-23 13:12:14 -07:00
|
|
|
class YouPornIE(InfoExtractor):
|
2014-03-20 16:19:54 -07:00
|
|
|
_VALID_URL = r'^(?P<proto>https?://)(?:www\.)?(?P<url>youporn\.com/watch/(?P<videoid>[0-9]+)/(?P<title>[^/]+))'
|
2013-06-27 11:46:46 -07:00
|
|
|
_TEST = {
|
2014-03-20 16:19:54 -07:00
|
|
|
'url': 'http://www.youporn.com/watch/505835/sex-ed-is-it-safe-to-masturbate-daily/',
|
|
|
|
'info_dict': {
|
|
|
|
'id': '505835',
|
|
|
|
'ext': 'mp4',
|
|
|
|
'upload_date': '20101221',
|
|
|
|
'description': 'Love & Sex Answers: http://bit.ly/DanAndJenn -- Is It Unhealthy To Masturbate Daily?',
|
|
|
|
'uploader': 'Ask Dan And Jennifer',
|
|
|
|
'title': 'Sex Ed: Is It Safe To Masturbate Daily?',
|
|
|
|
'age_limit': 18,
|
2013-06-27 11:46:46 -07:00
|
|
|
}
|
|
|
|
}
|
2013-06-23 13:12:14 -07:00
|
|
|
|
|
|
|
def _real_extract(self, url):
|
|
|
|
mobj = re.match(self._VALID_URL, url)
|
|
|
|
video_id = mobj.group('videoid')
|
2014-03-20 16:19:54 -07:00
|
|
|
url = mobj.group('proto') + 'www.' + mobj.group('url')
|
2013-06-23 13:12:14 -07:00
|
|
|
|
|
|
|
req = compat_urllib_request.Request(url)
|
|
|
|
req.add_header('Cookie', 'age_verified=1')
|
|
|
|
webpage = self._download_webpage(req, video_id)
|
2013-10-05 21:06:30 -07:00
|
|
|
age_limit = self._rta_search(webpage)
|
2013-06-23 13:12:14 -07:00
|
|
|
|
|
|
|
# Get JSON parameters
|
2014-03-20 16:19:54 -07:00
|
|
|
json_params = self._search_regex(r'var currentVideo = new Video\((.*)\);', webpage, 'JSON parameters')
|
2013-06-23 13:12:14 -07:00
|
|
|
try:
|
|
|
|
params = json.loads(json_params)
|
|
|
|
except:
|
|
|
|
raise ExtractorError(u'Invalid JSON')
|
|
|
|
|
|
|
|
self.report_extraction(video_id)
|
|
|
|
try:
|
|
|
|
video_title = params['title']
|
|
|
|
upload_date = unified_strdate(params['release_date_f'])
|
|
|
|
video_description = params['description']
|
|
|
|
video_uploader = params['submitted_by']
|
|
|
|
thumbnail = params['thumbnails'][0]['image']
|
|
|
|
except KeyError:
|
|
|
|
raise ExtractorError('Missing JSON parameter: ' + sys.exc_info()[1])
|
|
|
|
|
2013-10-26 12:57:10 -07:00
|
|
|
# Get all of the links from the page
|
2013-06-23 13:12:14 -07:00
|
|
|
DOWNLOAD_LIST_RE = r'(?s)<ul class="downloadList">(?P<download_list>.*?)</ul>'
|
|
|
|
download_list_html = self._search_regex(DOWNLOAD_LIST_RE,
|
2014-03-20 16:19:54 -07:00
|
|
|
webpage, 'download list').strip()
|
2013-10-26 12:57:10 -07:00
|
|
|
LINK_RE = r'<a href="([^"]+)">'
|
2013-06-23 13:12:14 -07:00
|
|
|
links = re.findall(LINK_RE, download_list_html)
|
2013-10-26 12:57:10 -07:00
|
|
|
|
|
|
|
# Get all encrypted links
|
|
|
|
encrypted_links = re.findall(r'var encryptedQuality[0-9]{3}URL = \'([a-zA-Z0-9+/]+={0,2})\';', webpage)
|
|
|
|
for encrypted_link in encrypted_links:
|
|
|
|
link = aes_decrypt_text(encrypted_link, video_title, 32).decode('utf-8')
|
|
|
|
links.append(link)
|
2014-11-23 11:41:03 -08:00
|
|
|
|
2013-06-23 13:12:14 -07:00
|
|
|
formats = []
|
|
|
|
for link in links:
|
|
|
|
# A link looks like this:
|
|
|
|
# http://cdn1.download.youporn.phncdn.com/201210/31/8004515/480p_370k_8004515/YouPorn%20-%20Nubile%20Films%20The%20Pillow%20Fight.mp4?nvb=20121113051249&nva=20121114051249&ir=1200&sr=1200&hash=014b882080310e95fb6a0
|
|
|
|
# A path looks like this:
|
|
|
|
# /201210/31/8004515/480p_370k_8004515/YouPorn%20-%20Nubile%20Films%20The%20Pillow%20Fight.mp4
|
2013-11-03 05:03:17 -08:00
|
|
|
video_url = unescapeHTML(link)
|
|
|
|
path = compat_urllib_parse_urlparse(video_url).path
|
2013-12-26 09:37:12 -08:00
|
|
|
format_parts = path.split('/')[4].split('_')[:2]
|
2013-10-26 12:57:10 -07:00
|
|
|
|
2013-12-26 09:37:12 -08:00
|
|
|
dn = compat_urllib_parse_urlparse(video_url).netloc.partition('.')[0]
|
|
|
|
|
|
|
|
resolution = format_parts[0]
|
|
|
|
height = int(resolution[:-len('p')])
|
|
|
|
bitrate = int(format_parts[1][:-len('k')])
|
2014-03-20 16:19:54 -07:00
|
|
|
format = '-'.join(format_parts) + '-' + dn
|
2013-06-23 13:12:14 -07:00
|
|
|
|
|
|
|
formats.append({
|
|
|
|
'url': video_url,
|
|
|
|
'format': format,
|
2013-10-26 12:57:10 -07:00
|
|
|
'format_id': format,
|
2013-12-26 09:37:12 -08:00
|
|
|
'height': height,
|
|
|
|
'tbr': bitrate,
|
|
|
|
'resolution': resolution,
|
2013-06-23 13:12:14 -07:00
|
|
|
})
|
|
|
|
|
2013-12-26 09:37:12 -08:00
|
|
|
self._sort_formats(formats)
|
|
|
|
|
|
|
|
if not formats:
|
|
|
|
raise ExtractorError(u'ERROR: no known formats available for video')
|
2014-11-23 11:41:03 -08:00
|
|
|
|
2013-10-26 12:57:10 -07:00
|
|
|
return {
|
|
|
|
'id': video_id,
|
|
|
|
'uploader': video_uploader,
|
|
|
|
'upload_date': upload_date,
|
|
|
|
'title': video_title,
|
|
|
|
'thumbnail': thumbnail,
|
|
|
|
'description': video_description,
|
|
|
|
'age_limit': age_limit,
|
|
|
|
'formats': formats,
|
|
|
|
}
|