From 9d213fc199c1c9058c254b57932ef5d2506bad46 Mon Sep 17 00:00:00 2001 From: Bombadil Date: Thu, 30 Mar 2017 18:58:03 +0200 Subject: New gurumed.org, jeuxvideo.com, secouchermoinsbete.fr. Added numerama.com. (#281) * Update numerama.com.txt * Create gurumed.org.txt * Create jeuxvideo.com.txt * Create secouchermoinsbete.fr.txt --- numerama.com.txt | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) (limited to 'numerama.com.txt') diff --git a/numerama.com.txt b/numerama.com.txt index 684a654..f10a698 100644 --- a/numerama.com.txt +++ b/numerama.com.txt @@ -1,3 +1,11 @@ -strip://section[@class='related-article'] +# Need html5lib or replace_string to handle correctly badly included in-content-ad inclusion script. html5lib is a lot slower. +# parser: html5lib +replace_string(""): "</div>" +body: //article[@class='post-content'] +strip: //span[@class='summary-entry'] +strip: //footer -test_url: http://www.numerama.com/sciences/231009-les-radiochats-et-lepineuse-question-de-la-memoire-des-sites-nucleaires.html +test_url: http://www.numerama.com/sciences/243352-hubble-detecte-un-trou-noir-supermassif-propulse-hors-de-sa-galaxie.html +test_url: http://www.numerama.com/tech/242703-free-mobile-et-la-4g-en-illimite-ce-quil-faut-savoir.html +# Don't know why this one get everything in bold: +test_url: http://www.numerama.com/business/243686-comme-convenu-quand-lenfer-dune-startup-se-transforme-en-succes-dauto-edition.html -- cgit v1.3.1