X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fkeezmovies.py;h=126ca13df1b8c30e9d94b204beb54eab03644fea;hb=9f0ee2a3883ec6f6fdccba90085cb925aaa2f617;hp=7869244452ac4b8dab673ce82e29b6b737aa3bc2;hpb=2bc67c35acece68a75284b88fcb03d69f267a63c;p=youtube-dl diff --git a/youtube_dl/extractor/keezmovies.py b/youtube_dl/extractor/keezmovies.py index 786924445..126ca13df 100644 --- a/youtube_dl/extractor/keezmovies.py +++ b/youtube_dl/extractor/keezmovies.py @@ -1,34 +1,32 @@ -import os +from __future__ import unicode_literals + import re from .common import InfoExtractor from ..utils import ( - compat_urllib_parse_urlparse, - compat_urllib_request, - compat_urllib_parse, -) -from ..aes import ( - aes_decrypt_text + sanitized_Request, + url_basename, ) + class KeezMoviesIE(InfoExtractor): - _VALID_URL = r'^(?:https?://)?(?:www\.)?(?Pkeezmovies\.com/video/.+?(?P[0-9]+))(?:[/?&]|$)' + _VALID_URL = r'https?://(?:www\.)?keezmovies\.com/video/.+?(?P[0-9]+)(?:[/?&]|$)' _TEST = { - u'url': u'http://www.keezmovies.com/video/petite-asian-lady-mai-playing-in-bathtub-1214711', - u'file': u'1214711.mp4', - u'md5': u'6e297b7e789329923fcf83abb67c9289', - u'info_dict': { - u"title": u"Petite Asian Lady Mai Playing In Bathtub", - u"age_limit": 18, + 'url': 'http://www.keezmovies.com/video/petite-asian-lady-mai-playing-in-bathtub-1214711', + 'md5': '1c1e75d22ffa53320f45eeb07bc4cdc0', + 'info_dict': { + 'id': '1214711', + 'ext': 'mp4', + 'title': 'Petite Asian Lady Mai Playing In Bathtub', + 'age_limit': 18, + 'thumbnail': 're:^https?://.*\.jpg$', } } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('videoid') - url = 'http://www.' + mobj.group('url') + video_id = self._match_id(url) - req = compat_urllib_request.Request(url) + req = sanitized_Request(url) req.add_header('Cookie', 'age_verified=1') webpage = self._download_webpage(req, video_id) @@ -38,24 +36,31 @@ class KeezMoviesIE(InfoExtractor): embedded_url = mobj.group(1) return self.url_result(embedded_url) - video_title = self._html_search_regex(r'

]*>([^<]+)', webpage, u'title') - video_url = compat_urllib_parse.unquote(self._html_search_regex(r'video_url=(.+?)&', webpage, u'video_url')) - if webpage.find('encrypted=true')!=-1: - password = self._html_search_regex(r'video_title=(.+?)&', webpage, u'password') - video_url = aes_decrypt_text(video_url, password, 32).decode('utf-8') - path = compat_urllib_parse_urlparse( video_url ).path - extension = os.path.splitext( path )[1][1:] - format = path.split('/')[4].split('_')[:2] - format = "-".join( format ) + video_title = self._html_search_regex( + r'

]*>([^<]+)', webpage, 'title') + flashvars = self._parse_json(self._search_regex( + r'var\s+flashvars\s*=\s*([^;]+);', webpage, 'flashvars'), video_id) + + formats = [] + for height in (180, 240, 480): + if flashvars.get('quality_%dp' % height): + video_url = flashvars['quality_%dp' % height] + a_format = { + 'url': video_url, + 'height': height, + 'format_id': '%dp' % height, + } + filename_parts = url_basename(video_url).split('_') + if len(filename_parts) >= 2 and re.match(r'\d+[Kk]', filename_parts[1]): + a_format['tbr'] = int(filename_parts[1][:-1]) + formats.append(a_format) age_limit = self._rta_search(webpage) return { 'id': video_id, 'title': video_title, - 'url': video_url, - 'ext': extension, - 'format': format, - 'format_id': format, + 'formats': formats, 'age_limit': age_limit, + 'thumbnail': flashvars.get('image_url') }