From 125cfd78e8579b1c6104d3ec2359417677863a8a Mon Sep 17 00:00:00 2001 From: rzhxeo Date: Sun, 27 Oct 2013 01:04:22 +0200 Subject: [PATCH] Add support for http://www.pornhub.com --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/pornhub.py | 67 ++++++++++++++++++++++++++++++++ 2 files changed, 68 insertions(+) create mode 100644 youtube_dl/extractor/pornhub.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index db69af361..2a5518665 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -94,6 +94,7 @@ from .ooyala import OoyalaIE from .orf import ORFIE from .pbs import PBSIE from .photobucket import PhotobucketIE +from .pornhub import PornHubIE from .pornotube import PornotubeIE from .rbmaradio import RBMARadioIE from .redtube import RedTubeIE diff --git a/youtube_dl/extractor/pornhub.py b/youtube_dl/extractor/pornhub.py new file mode 100644 index 000000000..3dbd2ab69 --- /dev/null +++ b/youtube_dl/extractor/pornhub.py @@ -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\.)?(?Ppornhub\.com/view_video\.php\?viewkey=(?P[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'

]+>([^<]+)', webpage, u'title') + video_uploader = self._html_search_regex(r'From: (?:\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, + }