From 4fdef7b837ca8dc4c3840062eee5829e08242bd7 Mon Sep 17 00:00:00 2001
From: David Izquierdo <david@izquierdofernandez.com>
Date: Tue, 11 Jul 2023 05:26:50 +0200
Subject: [PATCH] Add scrape and rewrite rules for webtoons
Although the only source I have for the rewrite rule is, in fact, https://github.com/miniflux/v2/pull/892, it does work when combined with add_dynamic_image and scraping the right element. I have not investigated further.
Works around https://github.com/miniflux/v2/issues/775 and https://github.com/miniflux/v2/issues/1871 (as in, gives us working webtoons feeds but referer spoofing would still be a nice tool to have).
Fixes https://github.com/miniflux/v2/issues/256.
---
reader/rewrite/rules.go | 1 +
reader/scraper/rules.go | 1 +
2 files changed, 2 insertions(+)
diff --git a/reader/rewrite/rules.go b/reader/rewrite/rules.go
index c2262644..8d98dc5b 100644
--- a/reader/rewrite/rules.go
+++ b/reader/rewrite/rules.go
@@ -32,6 +32,7 @@ var predefinedRules = map[string]string{
"thedoghousediaries.com": "add_image_title",
"theverge.com": `add_dynamic_image, remove("div.duet--recirculation--related-list")`,
"treelobsters.com": "add_image_title",
+ "webtoons.com": `add_dynamic_image,replace("webtoon"|"swebtoon")`,
"www.qwantz.com": "add_image_title,add_mailto_subject",
"www.recalbox.com": "parse_markdown",
"xkcd.com": "add_image_title",
diff --git a/reader/scraper/rules.go b/reader/scraper/rules.go
index 8e0fef74..6dcda370 100644
--- a/reader/scraper/rules.go
+++ b/reader/scraper/rules.go
@@ -50,6 +50,7 @@ var predefinedRules = map[string]string{
"universfreebox.com": "#corps_corps",
"version2.dk": "section.body",
"wdwnt.com": "div.entry-content",
+ "webtoons.com": ".viewer_img",
"wired.com": "main figure, article",
"zeit.de": ".summary, .article-body",
"zdnet.com": "div.storyBody",
--
GitLab