From 690d66ce0b85d9a1e5a3c2bd0c0d42b846ad399d Mon Sep 17 00:00:00 2001 From: Davide Masserut Date: Mon, 19 Dec 2022 14:03:16 +0100 Subject: [PATCH] Update scraping rules for ilpost.it --- reader/rewrite/rules.go | 1 + reader/scraper/rules.go | 2 +- 2 files changed, 2 insertions(+), 1 deletion(-) diff --git a/reader/rewrite/rules.go b/reader/rewrite/rules.go index 50014844..375e3952 100644 --- a/reader/rewrite/rules.go +++ b/reader/rewrite/rules.go @@ -16,6 +16,7 @@ var predefinedRules = map[string]string{ "exocomics.com": "add_image_title", "framatube.org": "nl2br,convert_text_link", "happletea.com": "add_image_title", + "ilpost.it": `remove(".art_tag, #audioPlayerArticle, .author-container, .caption, .ilpostShare, .lastRecents, #mc_embed_signup, p:has(.leggi-anche)")`, "imogenquest.net": "add_image_title", "lukesurl.com": "add_image_title", "medium.com": "fix_medium_images", diff --git a/reader/scraper/rules.go b/reader/scraper/rules.go index f3d424a2..710d70a8 100644 --- a/reader/scraper/rules.go +++ b/reader/scraper/rules.go @@ -19,7 +19,7 @@ var predefinedRules = map[string]string{ "heise.de": "header .article-content__lead, header .article-image, div.article-layout__content.article-content", "igen.fr": "section.corps", "ikiwiki.iki.fi": ".page.group", - "ilpost.it": "#singleBody > :not(#audioPlayerArticle, .ilpostShare, p:has(.leggi-anche))", + "ilpost.it": ".entry-content", "ing.dk": "section.body", "lapresse.ca": ".amorce, .entry", "lemonde.fr": "article",