From c72ea4c6ca60e4974a05b8fff0827532bec481a6 Mon Sep 17 00:00:00 2001
From: Slatian <baschdel@disroot.org>
Date: Sat, 19 Nov 2022 01:11:31 +0100
Subject: [PATCH] Improved heuristics for enlish language text to skip over
 most fluff paragraphs to get better samples of sites

---
 data/heuristics.txt | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/data/heuristics.txt b/data/heuristics.txt
index 99d2993..d6f1c38 100644
--- a/data/heuristics.txt
+++ b/data/heuristics.txt
@@ -8,3 +8,16 @@ last edit
 (c)
 all rights reserved
 licensed under
+subscribe
+|
+generated by
+powered by
+this post was
+click here for
+click here to
+published on:
+published:
+posted:
+note:
+share this article
+estimated read time