from __future__ import unicode_literals import re from .common import InfoExtractor from ..compat import ( compat_urllib_parse, ) from ..utils import ( ExtractorError, ) class EscapistIE(InfoExtractor): _VALID_URL = r'^https?://?(www\.)?escapistmagazine\.com/videos/view/(?P[^/]+)/(?P[0-9]+)-' _TEST = { 'url': 'http://www.escapistmagazine.com/videos/view/the-escapist-presents/6618-Breaking-Down-Baldurs-Gate', 'md5': 'ab3a706c681efca53f0a35f1415cf0d1', 'info_dict': { 'id': '6618', 'ext': 'mp4', 'description': "Baldur's Gate: Original, Modded or Enhanced Edition? I'll break down what you can expect from the new Baldur's Gate: Enhanced Edition.", 'uploader': 'the-escapist-presents', 'title': "Breaking Down Baldur's Gate", } } def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) showName = mobj.group('showname') video_id = mobj.group('id') self.report_extraction(video_id) webpage = self._download_webpage(url, video_id) videoDesc = self._html_search_regex( r'