From d1e2966ab8d3fd38edfa3e50fae8e26601ef1902 Mon Sep 17 00:00:00 2001
From: dvs1
Date: Mon, 20 Jan 2025 14:50:57 +1000
Subject: Clean up the cleaning up

---
 SuckItPm | 30 ++++++++++++++++--------------
 1 file changed, 16 insertions(+), 14 deletions(-)

(limited to 'SuckItPm')

diff --git a/SuckItPm b/SuckItPm
index 156ee9f..a63eb08 100755
--- a/SuckItPm
+++ b/SuckItPm
@@ -10,20 +10,20 @@ filter="
  -not -name ".pageindex" -a \
 "
 
-pushd /opt/merged
+pushd /opt/mergedWork
 
 find /opt/pmwiki/wiki.d  ${filter} \
 -name "*.*" -type f,l -printf "%P\n" | while read line
 do
     base=`echo "${line}" | cut -d '.' -f 1`
     file=`echo "${line}" | cut -d '.' -f 2`
+#    page="?n=${line}"
     mkdir -p PmWiki/$base
     mkdir -p combined/$base
     echo "Converting ${URL}/?n=${base}.${file}?action=print -> PmWiki/${base}/${file}.md"
 #    pandoc -f html -t markdown --self-contained ${URL}/?n=${base}.${file} >PmWiki/${base}/${file}.md
     # TODO - try curl, to see what is actually downloaded, and maybe not download unchanged pages.  curl to .HTM
     # Doesn't help with redownloads, coz natch a dynamic site isn't cached.  But I can at least comment out the curl command during testing to save time.
-#    curl --no-progress-meter ${URL}/?n=${base}.${file} -o PmWiki/${base}/${file}.HTM
 #    curl --no-progress-meter ${URL}/?n=${base}.${file}?action=markdown -o PmWiki/${base}/${file}.MD
     curl --no-progress-meter ${URL}/?n=${base}.${file}?action=print -o PmWiki/${base}/${file}.HTM
     cp PmWiki/${base}/${file}.HTM PmWiki/${base}/${file}.HTM_ORIGINAL
@@ -44,7 +44,6 @@ do
 	-e "s/class='vspace'//g" \
 	-e "s/class='wikilink'//g" \
 	-e "s/style='.*;'//g"
-#	-e "s/class='.*'//g" \
 #	-e "s/style='background-color: #.*;'//g" \
 #	-e "s/style='font-size: .*;'//g"
 
@@ -57,23 +56,26 @@ do
 	-e 's/\$/\$dlr\$/g' \
 	-e 's/\{#.*\}//g' \
 	-e '/^:::/d' \
-	-e '/\[Site$/d' \
-	-e '/^Page last modified on /d' \
-	-e '/^\[\]/d' \
-	-e "s/\`<a id='trailstart'>\`\{=html\}\`<\/a>\`\{=html\}//g" \
-	-e "s/^\`<img /<img /g" \
-	-e "s/^\`\`\`\{=html\}//g" \
-	-e "s/^\`\`\`//g" \
-	-e "s/\`\{=html\}//g"
+#	-e '/\[Site$/d' \
+#	-e '/^Page last modified on /d' \
+#	-e '/^\[\]/d' \
+#	-e "s/\`<a id='trailstart'>\`\{=html\}\`<\/a>\`\{=html\}//g" \
+#	-e "s/^\`<img /<img /g" \
+#	-e "s/^\`\`\`\{=html\}//g" \
+#	-e "s/^\`\`\`//g" \
+#	-e "s/\`\{=html\}//g"
 
-    echo -e "****\n[Original page](${URL}/${base}/${file}) where maybe you can edit it." >> PmWiki/${base}/${file}.md
+    # Don't need this, the parts we are grabbing already include that link at the bottom.
+#    echo -e "****\n[Original page](${URL}/${base}/${page}) where maybe you can edit it." >> PmWiki/${base}/${file}.md
 
 #    pandoc -t html -f commonmark_x --self-contained		PmWiki/${base}/${file}.md > PmWiki/${base}/${file}.htm
 #    cmark-gfm -t html -e footnotes -e table -e strikethrough	PmWiki/${base}/${file}.md > PmWiki/${base}/${file}.body
 #    ln -frs PmWiki/${base}/${file}.body combined/${base}/${file}.body
     ln -frs PmWiki/${base}/${file}.md combined/${base}/${file}.md
-done
 
-notYetAnotherWiki.lua
+    if [ -f xx01 ]; then
+	rm xx01
+    fi
+done
 
 popd
-- 
cgit v1.1