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 --- gurumed.org.txt | 6 ++++++ jeuxvideo.com.txt | 10 ++++++++++ numerama.com.txt | 12 ++++++++++-- secouchermoinsbete.fr.txt | 9 +++++++++ 4 files changed, 35 insertions(+), 2 deletions(-) create mode 100644 gurumed.org.txt create mode 100644 jeuxvideo.com.txt create mode 100644 secouchermoinsbete.fr.txt diff --git a/gurumed.org.txt b/gurumed.org.txt new file mode 100644 index 0000000..9e775fd --- /dev/null +++ b/gurumed.org.txt @@ -0,0 +1,6 @@ +prune: no +body: //div[@class='entry'] +strip: //div[@class='addthis_toolbox'] +strip: //div[@class='yarpp-related'] + +test_url: http://www.gurumed.org/2015/06/22/nous-entrons-dsormais-dans-la-sixime-extinction-massive/ diff --git a/jeuxvideo.com.txt b/jeuxvideo.com.txt new file mode 100644 index 0000000..bd02e74 --- /dev/null +++ b/jeuxvideo.com.txt @@ -0,0 +1,10 @@ +prune: no +body: //div[@class='corps-news text-enrichi-default'] +body: //div[@class='corps-article text-enrichi-default'] +body: //div[@class='corps-video text-enrichi-default'] +strip: //div[@class='bloc-contact-auteur'] +strip: //div[@class='liens-avis-lecteur'] + +test_url: http://www.jeuxvideo.com/news/431383/lancement-cosmique-pour-devouring-stars.htm +test_url: http://www.jeuxvideo.com/test/431612/massive-chalice-du-tour-par-tour-medieval-independant.htm +test_url: http://www.jeuxvideo.com/videos/431381/devouring-stars-moisson-d-etoiles.htm 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 diff --git a/secouchermoinsbete.fr.txt b/secouchermoinsbete.fr.txt new file mode 100644 index 0000000..c66a1cd --- /dev/null +++ b/secouchermoinsbete.fr.txt @@ -0,0 +1,9 @@ +prune: no +body: //article[@class='anecdote'] +strip: //article[@class='anecdote']/aside/div[@class='column-wrapper'] +strip: //article[@class='anecdote']/aside/div[@id='related-sources-wrapper']/div[@id='related'] + + +test_url: http://secouchermoinsbete.fr/62836-audi-a-ete-cree-par-un-ancien-chef-de-chez-mercedes +test_url: http://secouchermoinsbete.fr/62795-sous-l-eau-a-plus-de-10-metres-votre-sang-est-vert +test_url: http://secouchermoinsbete.fr/62663-l-invention-qui-pourrait-nettoyer-les-oceans-en-quelques-annees -- cgit v1.3.1