This commit is contained in:
rzhxeo 2013-10-27 01:04:22 +02:00
parent 49a25557b0
commit 125cfd78e8
2 changed files with 68 additions and 0 deletions

View File

@ -94,6 +94,7 @@ from .ooyala import OoyalaIE
from .orf import ORFIE from .orf import ORFIE
from .pbs import PBSIE from .pbs import PBSIE
from .photobucket import PhotobucketIE from .photobucket import PhotobucketIE
from .pornhub import PornHubIE
from .pornotube import PornotubeIE from .pornotube import PornotubeIE
from .rbmaradio import RBMARadioIE from .rbmaradio import RBMARadioIE
from .redtube import RedTubeIE from .redtube import RedTubeIE

View File

@ -0,0 +1,67 @@
import os
import re
from .common import InfoExtractor
from ..utils import (
compat_urllib_parse_urlparse,
compat_urllib_request,
compat_urllib_parse,
unescapeHTML,
)
from ..aes import (
aes_decrypt_text
)
class PornHubIE(InfoExtractor):
_VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>pornhub\.com/view_video\.php\?viewkey=(?P<videoid>[0-9]+))'
_TEST = {
u'url': u'http://www.pornhub.com/view_video.php?viewkey=648719015',
u'file': u'648719015.mp4',
u'md5': u'882f488fa1f0026f023f33576004a2ed',
u'info_dict': {
u"uploader": u"BABES-COM",
u"title": u"Seductive Indian beauty strips down and fingers her pink pussy",
}
}
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)
video_title = self._html_search_regex(r'<h1 [^>]+>([^<]+)', webpage, u'title')
video_uploader = self._html_search_regex(r'<b>From: </b>(?:\s|<[^>]*>)*(.+?)<', webpage, u'uploader', fatal=False)
thumbnail = self._html_search_regex(r'"image_url":"([^"]+)', webpage, u'thumbnail', fatal=False)
if thumbnail:
thumbnail = compat_urllib_parse.unquote(thumbnail)
video_urls = list(map(compat_urllib_parse.unquote , re.findall(r'"quality_[0-9]{3}p":"([^"]+)', webpage)))
if webpage.find('"encrypted":true') != -1:
password = self._html_search_regex(r'"video_title":"([^"]+)', webpage, u'password').replace('+', ' ')
video_urls = list(map(lambda s: aes_decrypt_text(s, password, 32).decode('utf-8'), video_urls))
formats = []
for video_url in video_urls:
path = compat_urllib_parse_urlparse( video_url ).path
extension = os.path.splitext( path )[1][1:]
format = path.split('/')[5].split('_')[:2]
format = "-".join( format )
formats.append({
'url': video_url,
'ext': extension,
'format': format,
'format_id': format,
})
formats.sort(key=lambda format: list(map(lambda s: s.zfill(6), format['format'].split('-'))))
return {
'id': video_id,
'uploader': video_uploader,
'title': video_title,
'thumbnail': thumbnail,
'formats': formats,
}