From f34badc723a821d732ace78f098aabea0f395f07 Mon Sep 17 00:00:00 2001
From: dvs1
Date: Thu, 2 Jan 2025 10:02:27 +1000
Subject: Add the Suckit* scripts.

---
 SuckItFos | 52 ++++++++++++++++++++++++++++++++++++++++++++++++++++
 SuckItPm  | 57 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 109 insertions(+)
 create mode 100755 SuckItFos
 create mode 100755 SuckItPm

diff --git a/SuckItFos b/SuckItFos
new file mode 100755
index 0000000..4f824be
--- /dev/null
+++ b/SuckItFos
@@ -0,0 +1,52 @@
+#!/bin/bash
+
+URL="https://devuan.daffodil.linuxoz.net"
+
+filter="
+ -name _default -prune -o \
+ -name _empty -prune -o \
+ -name System -prune -o \
+ -name Trash -prune -o \
+ -name TWiki -prune -o \
+"
+
+find ../Foswiki/data  ${filter} \
+-name "*.txt" -type f,l -printf "%P\n" | while read line
+do
+    base=`echo "${line}" | cut -d '/' -f 1`
+    file=`echo "${line}" | cut -d '/' -f 2- | rev | cut -b 5- | rev`
+    mkdir -p Foswiki/$base
+    echo "Converting ${URL}/${base}/${file} -> Foswiki/${base}/${file}.md"
+#    pandoc -f html -t markdown --self-contained ${URL}/${base}/${file} >Foswiki/${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 --silent --no-progress-meter ${URL}/${base}/${file} -o Foswiki/${base}/${file}.HTM
+    pandoc -f html -t commonmark_x --self-contained Foswiki//${base}/${file}.HTM >Foswiki/${base}/${file}.md
+    cp Foswiki/${base}/${file}.md Foswiki/${base}/${file}.md_ORIGINAL
+
+#    csplit -ks Foswiki/${base}/${file}.md '%::: foswikiTopic%' '/::: foswikiContentFooter/'
+#    if [ -f xx00 ]; then
+#	rm Foswiki/${base}/${file}.md
+#	mv xx00 Foswiki/${base}/${file}.md
+#    fi
+
+    # Attempt to clean things up, badly.
+    sed -i -E Foswiki/${base}/${file}.md \
+	-e 's/\$/\$dlr\$/g' \
+	-e 's/\{#.*\}//g' \
+	-e 's/\{\.foswiki.*\}//g' \
+	-e 's/\{\.foswiki.*//g' \
+	-e 's/\{\.foswikiNewLink rel=“nofollow”\}//g' \
+	-e 's/\{\.foswikiNewLink$//g' \
+	-e 's/^\.foswiki.*\}//g' \
+	-e 's/\{\.pattern.*\}//g' \
+	-e 's/\{\.pattern.*//g' \
+	-e 's/\{rel="nofollow"\}//g' \
+	-e 's/^rel="nofollow"\}//g' \
+	-e 's/rel=“nofollow”\}$//g' \
+	-e '/^:::/d'
+
+    echo "<hr/><p><a href=\"${URL}/${base}/${file}\">Original page</a> where you can edit it.</p>" >> Foswiki/${base}/${file}.md
+done
+
+notYetAnotherWiki.lua
diff --git a/SuckItPm b/SuckItPm
new file mode 100755
index 0000000..6232cdc
--- /dev/null
+++ b/SuckItPm
@@ -0,0 +1,57 @@
+#!/bin/bash
+
+URL="https://wiki.devuan.org"
+
+filter="
+ -not -name "*~" -a \
+ -not -name ".flock" -a \
+ -not -name ".htaccess" -a \
+ -not -name ".lastmod" -a \
+ -not -name ".pageindex" -a \
+"
+
+find ../pmwiki/wiki.d  ${filter} \
+-name "*.*" -type f,l -printf "%P\n" | while read line
+do
+    base=`echo "${line}" | cut -d '.' -f 1`
+    file=`echo "${line}" | cut -d '.' -f 2`
+    mkdir -p PmWiki/$base
+    echo "Converting ${URL}/?n=${base}.${file} -> PmWiki/${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}/${file}.HTM
+    pandoc -f html -t commonmark_x --self-contained PmWiki//${base}/${file}.HTM >PmWiki/${base}/${file}.md
+    cp PmWiki/${base}/${file}.md PmWiki/${base}/${file}.md_ORIGINAL
+
+#    csplit -ks PmWiki/${base}/${file}.md '/trailstart/' '/trailend/'
+    csplit -ks PmWiki/${base}/${file}.md '%::: {#wikitext}%' 
+    if [ -f xx00 ]; then
+	rm PmWiki/${base}/${file}.md
+	mv xx00 PmWiki/${base}/${file}.md
+    fi
+
+    # Attempt to clean things up, badly.
+    sed -i -E PmWiki/${base}/${file}.md \
+	-e 's/\$/\$dlr\$/g' \
+	-e 's/\{#.*\}//g' \
+	-e '/\{\.wikilink\}/d' \
+	-e '/\[Site$/d' \
+	-e '/^:::/d' \
+	-e '/^Page last modified on /d' \
+	-e '/^\[\]/d' \
+	-e 's/\{rel=".*\}//g' \
+	-e 's/\{rel="nofollow"$//g' \
+	-e 's/^rel="nofollow"\}//g' \
+	-e 's/^target="_blank"\}//g' \
+	-e 's/\{\.createlinktext.*\}//g' \
+	-e 's/\{\.createlinktext$//g' \
+	-e 's/\{\.createlink.*\}//g' \
+	-e 's/\{\.createlink$//g' \
+	-e 's/\{\.urllink.*\}//g' \
+	-e 's/\{\.urllink$//g'
+
+echo "<hr/><p><a href=\"${URL}/?n=${base}.${file}\">Original page</a> where you can edit it.</p>" >> PmWiki/${base}/${file}.md
+done
+
+notYetAnotherWiki.lua
-- 
cgit v1.1