From 596ac6e31f6baaadf8280e2c54ca90a7cf2fbc2a Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Tue, 10 Feb 2015 15:45:36 +0100 Subject: [PATCH] [escapist] Modernize --- youtube_dl/extractor/escapist.py | 51 ++++++++++++++++---------------- 1 file changed, 25 insertions(+), 26 deletions(-) diff --git a/youtube_dl/extractor/escapist.py b/youtube_dl/extractor/escapist.py index e240cb859..98b698277 100644 --- a/youtube_dl/extractor/escapist.py +++ b/youtube_dl/extractor/escapist.py @@ -1,18 +1,17 @@ from __future__ import unicode_literals -import re - 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[^/]+)/(?P[0-9]+)-' + _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', @@ -20,31 +19,30 @@ class EscapistIE(InfoExtractor): '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', + 'uploader_id': 'the-escapist-presents', + '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) + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) - videoDesc = self._html_search_regex( - r'(.*?)", + webpage, 'uploader', fatal=False) + description = self._html_search_meta('description', webpage) - playerUrl = self._og_search_video_url(webpage, name='player URL') + raw_title = self._html_search_meta('title', webpage, fatal=True) + title = raw_title.partition(' : ')[2] - title = self._html_search_regex( - r'