from __future__ import unicode_literals from .common import InfoExtractor from ..compat import ( compat_urllib_parse, ) from ..utils import ( ExtractorError, js_to_json, ) class EscapistIE(InfoExtractor): _VALID_URL = r'https?://?(www\.)?escapistmagazine\.com/videos/view/[^/?#]+/(?P[0-9]+)-[^/?#]*(?:$|[?#])' _TEST = { 'url': 'http://www.escapistmagazine.com/videos/view/the-escapist-presents/6618-Breaking-Down-Baldurs-Gate', 'md5': 'ab3a706c681efca53f0a35f1415cf0d1', 'info_dict': { 'id': '6618', 'ext': 'mp4', 'description': "Baldur's Gate: Original, Modded or Enhanced Edition? I'll break down what you can expect from the new Baldur's Gate: Enhanced Edition.", 'uploader_id': 'the-escapist-presents', 'uploader': 'The Escapist Presents', 'title': "Breaking Down Baldur's Gate", 'thumbnail': 're:^https?://.*\.jpg$', } } def _real_extract(self, url): video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) uploader_id = self._html_search_regex( r"\s*(.*?)", webpage, 'uploader', fatal=False) description = self._html_search_meta('description', webpage) raw_title = self._html_search_meta('title', webpage, fatal=True) title = raw_title.partition(' : ')[2] config_url = compat_urllib_parse.unquote(self._html_search_regex( r'