From e2dc351d25d1b05b26cba654a22b0d10ed47dec9 Mon Sep 17 00:00:00 2001 From: pulpe Date: Mon, 27 Apr 2015 17:44:13 +0200 Subject: [PATCH] [escapist] Fix extractor (fixes #5090) --- youtube_dl/extractor/escapist.py | 156 +++++++++++++------------------ 1 file changed, 65 insertions(+), 91 deletions(-) diff --git a/youtube_dl/extractor/escapist.py b/youtube_dl/extractor/escapist.py index e47f3e27a..a01a05b06 100644 --- a/youtube_dl/extractor/escapist.py +++ b/youtube_dl/extractor/escapist.py @@ -1,128 +1,102 @@ from __future__ import unicode_literals +import json + from .common import InfoExtractor -from ..compat import ( - compat_urllib_parse, - compat_urllib_request, -) +from ..compat import compat_urllib_request + from ..utils import ( - ExtractorError, - js_to_json, - parse_duration, + determine_ext, + clean_html, + qualities, ) +def _decrypt_config(key, string): + a = '' + i = '' + r = '' + + while len(a) < (len(string) / 2): + a += key + + a = a[0:int(len(string) / 2)] + + t = 0 + while t < len(string): + i += chr(int(string[t] + string[t + 1], 16)) + t += 2 + + icko = [s for s in i] + + for t, c in enumerate(a): + r += chr(ord(c) ^ ord(icko[t])) + + return r + + class EscapistIE(InfoExtractor): _VALID_URL = r'https?://?(www\.)?escapistmagazine\.com/videos/view/[^/?#]+/(?P[0-9]+)-[^/?#]*(?:$|[?#])' - _USER_AGENT = 'Mozilla/5.0 (Windows NT 6.1; WOW64; Trident/7.0; rv:11.0) like Gecko' - _TEST = { + _TESTS = [{ 'url': 'http://www.escapistmagazine.com/videos/view/the-escapist-presents/6618-Breaking-Down-Baldurs-Gate', - 'md5': 'ab3a706c681efca53f0a35f1415cf0d1', + 'md5': 'c6793dbda81388f4264c1ba18684a74d', 'info_dict': { 'id': '6618', 'ext': 'mp4', 'description': "Baldur's Gate: Original, Modded or Enhanced Edition? I'll break down what you can expect from the new Baldur's Gate: Enhanced Edition.", - 'uploader_id': 'the-escapist-presents', - 'uploader': 'The Escapist Presents', 'title': "Breaking Down Baldur's Gate", 'thumbnail': 're:^https?://.*\.jpg$', 'duration': 264, } - } + }, { + 'url': 'http://www.escapistmagazine.com/videos/view/zero-punctuation/10044-Evolve-One-vs-Multiplayer', + 'md5': 'cf8842a8a46444d241f9a9980d7874f2', + 'info_dict': { + 'id': '10044', + 'ext': 'mp4', + 'description': 'This week, Zero Punctuation reviews Evolve.', + 'title': 'Evolve - One vs Multiplayer', + 'thumbnail': 're:^https?://.*\.jpg$', + 'duration': 304, + } + }] def _real_extract(self, url): video_id = self._match_id(url) - webpage_req = compat_urllib_request.Request(url) - webpage_req.add_header('User-Agent', self._USER_AGENT) - webpage = self._download_webpage(webpage_req, video_id) + 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) - duration = parse_duration(self._html_search_meta('duration', webpage)) + imsVideo = json.loads(self._search_regex(r'imsVideo\.play\(([^\)]+)\);', webpage, 'imsVideo')) + video_id = imsVideo['videoID'] + key = imsVideo['hash'] - 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'''(?x) - (?: -