From 3ba1548d2acc2261e2454afc5b176a22657dbdb7 Mon Sep 17 00:00:00 2001 From: Eloi Coutant Date: Wed, 23 Aug 2017 00:10:10 +0200 Subject: Updates for Le Monde websites (#327) * Update lemonde.fr.txt Proposition to remove of "Lire aussi" (Read too) blocks that impedes the reading of articles. * Create abonnes.lemonde.fr.txt Abonnes.lemonde.fr is the website for lemonde subscribers. File inspired from lemonde.fr.txt, plus stripping of highlighted quotes. Takes into account the Le Monde Festival subsite that uses the HTML5 section and aside tags. --- abonnes.lemonde.fr.txt | 33 +++++++++++++++++++++++++++++++++ lemonde.fr.txt | 2 ++ 2 files changed, 35 insertions(+) create mode 100644 abonnes.lemonde.fr.txt diff --git a/abonnes.lemonde.fr.txt b/abonnes.lemonde.fr.txt new file mode 100644 index 0000000..4c23307 --- /dev/null +++ b/abonnes.lemonde.fr.txt @@ -0,0 +1,33 @@ +title: //h1 + +# We can have multiple authors +author: //span[@id='publisher'] +author: //a[@class='auteur'] + +# Last edition date (if any) +date: //time[@itemprop='dateModified']/@datetime +# Publication date +date: //time[@itemprop='datePublished']/@datetime + + +body: //div[@id='articleBody']|//section[@class='contenu']//div[@class='texte'] + +# Remove highlighted quotes +strip_id_or_class: accroche +strip_id_or_class: encart + +# Remove "Lire aussi" blocks +strip: //p[@class='lire'] + +# Remove footers for Le Monde Festival +strip: //aside[@class='fenetre'] + +# Remove the insane "conjugaison.lemonde.fr" links: +find_string: