From 05c8268c8192dcc4f61c869aba659c8e51d040bb Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Wed, 27 Jul 2016 23:39:02 +0700 Subject: [PATCH] [shared] Modernize and make more robust --- youtube_dl/extractor/shared.py | 18 ++++++++++-------- 1 file changed, 10 insertions(+), 8 deletions(-) diff --git a/youtube_dl/extractor/shared.py b/youtube_dl/extractor/shared.py index 6757e6ccf..d592dfeb8 100644 --- a/youtube_dl/extractor/shared.py +++ b/youtube_dl/extractor/shared.py @@ -6,7 +6,6 @@ from ..utils import ( ExtractorError, int_or_none, - sanitized_Request, urlencode_postdata, ) @@ -46,21 +45,24 @@ def _real_extract(self, url): download_form = self._hidden_inputs(webpage) - request = sanitized_Request( - urlh.geturl(), urlencode_postdata(download_form)) - request.add_header('Content-Type', 'application/x-www-form-urlencoded') - video_page = self._download_webpage( - request, video_id, 'Downloading video page') + urlh.geturl(), video_id, 'Downloading video page', + data=urlencode_postdata(download_form), + headers={ + 'Content-Type': 'application/x-www-form-urlencoded', + 'Referer': urlh.geturl(), + }) video_url = self._html_search_regex( - r'data-url="([^"]+)"', video_page, 'video URL') + r'data-url=(["\'])(?P(?:(?!\1).)+)\1', + video_page, 'video URL', group='url') title = base64.b64decode(self._html_search_meta( 'full:title', webpage, 'title').encode('utf-8')).decode('utf-8') filesize = int_or_none(self._html_search_meta( 'full:size', webpage, 'file size', fatal=False)) thumbnail = self._html_search_regex( - r'data-poster="([^"]+)"', video_page, 'thumbnail', default=None) + r'data-poster=(["\'])(?P(?:(?!\1).)+)\1', + video_page, 'thumbnail', default=None, group='url') return { 'id': video_id,