add cleanup steps to README

This commit is contained in:
Martin Stadler
2019-12-08 16:39:56 +01:00
parent ab29955ef8
commit e920a622ca
+9
View File
@@ -74,3 +74,12 @@ mv martin.xml misc modules rss.xml sites themes tilman.xml ../../httrack-clean/s
cd ../../working-dir/siarp.de cd ../../working-dir/siarp.de
find . -name "*.html" -type f -print0 | xargs -0 perl -i -pe "s/\/index\././g" 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'
```