X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fempflix.py;h=70f8efe27578c4d43b27378a4a2c80d495a7488c;hb=cc7fec5818254f4679896823c7de9d17f50201ca;hp=1c498d8c8fa0cc95a2963a19384201a42ec2fa4b;hpb=8f1ea7cbb6cb365e4ffd75bdc2d901afcbfdf72f;p=youtube-dl diff --git a/youtube_dl/extractor/empflix.py b/youtube_dl/extractor/empflix.py index 1c498d8c8..70f8efe27 100644 --- a/youtube_dl/extractor/empflix.py +++ b/youtube_dl/extractor/empflix.py @@ -1,58 +1,25 @@ from __future__ import unicode_literals -import re +from .tnaflix import TNAFlixIE -from .common import InfoExtractor -from ..utils import fix_xml_ampersands +class EMPFlixIE(TNAFlixIE): + _VALID_URL = r'^https?://www\.empflix\.com/videos/(?P[0-9a-zA-Z-]+)-(?P[0-9]+)\.html' + + _TITLE_REGEX = r'name="title" value="(?P[^"]*)"' + _DESCRIPTION_REGEX = r'name="description" value="([^"]*)"' + _CONFIG_REGEX = r'flashvars\.config\s*=\s*escape\("([^"]+)"' -class EmpflixIE(InfoExtractor): - _VALID_URL = r'^https?://www\.empflix\.com/videos/.*?-(?P<id>[0-9]+)\.html' _TEST = { 'url': 'http://www.empflix.com/videos/Amateur-Finger-Fuck-33051.html', 'md5': 'b1bc15b6412d33902d6e5952035fcabc', 'info_dict': { 'id': '33051', + 'display_id': 'Amateur-Finger-Fuck', 'ext': 'mp4', 'title': 'Amateur Finger Fuck', 'description': 'Amateur solo finger fucking.', + 'thumbnail': 're:https?://.*\.jpg$', 'age_limit': 18, } } - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - - webpage = self._download_webpage(url, video_id) - age_limit = self._rta_search(webpage) - - video_title = self._html_search_regex( - r'name="title" value="(?P<title>[^"]*)"', webpage, 'title') - video_description = self._html_search_regex( - r'name="description" value="([^"]*)"', webpage, 'description', fatal=False) - - cfg_url = self._html_search_regex( - r'flashvars\.config = escape\("([^"]+)"', - webpage, 'flashvars.config') - - cfg_xml = self._download_xml( - cfg_url, video_id, note='Downloading metadata', - transform_source=fix_xml_ampersands) - - formats = [ - { - 'url': item.find('videoLink').text, - 'format_id': item.find('res').text, - } for item in cfg_xml.findall('./quality/item') - ] - thumbnail = cfg_xml.find('./startThumb').text - - return { - 'id': video_id, - 'title': video_title, - 'description': video_description, - 'thumbnail': thumbnail, - 'formats': formats, - 'age_limit': age_limit, - }