From e920a622cae28bbebca3bbc519f39dc2025040a4 Mon Sep 17 00:00:00 2001
From: Martin Stadler <martin@siarp.de>
Date: Sun, 8 Dec 2019 16:39:56 +0100
Subject: [PATCH] add cleanup steps to README

---
 README.md | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/README.md b/README.md
index 8c9739c..e281aad 100644
--- a/README.md
+++ b/README.md
@@ -74,3 +74,12 @@ mv martin.xml misc modules rss.xml sites themes tilman.xml ../../httrack-clean/s
 cd ../../working-dir/siarp.de
 find . -name "*.html" -type f -print0 |   xargs -0 perl -i -pe "s/\/index\././g"
 ```
+
+### More cleanup
+
+```
+find . -name "*.html" -type f -print0 | xargs -0 perl -i -pe 's/<link rel="(canonical|shortlink)" href=".+?" \/>\n//g'
+```
+```
+find . -name "*.html" -type f -print0 | xargs -0 perl -i -pe 's/<\!\-\- Added by HTTrack \-\-><meta http\-equiv="content-type" content="text\/html;charset=utf\-8" \/><\!\-\- \/Added by HTTrack \-\->\n//g'
+```