ref: eef67b503efb2ec9fbec704270207e720b15ce18
parent: e632ea03e5154e539cd4c252c40e365412b10472
author: sl <sl@x1yg3>
date: Sun Jul 6 18:15:18 EDT 2025
add epub2html
--- a/INDEX
+++ b/INDEX
@@ -17,6 +17,7 @@
crip - Repack .cbr as .cbz. Try to fix the file names.
df - du -h /root | tail -1
dsrc - delete posts on a given barf website
+epub2html - convert epub to html
flac2alac - Convert FLAC to ALAC using ffmpeg.
flac2mp3 - Convert FLAC to MP3 using lame.
flacsplit - Split single FLAC into multiple files based on .cue sheet using shntool.
--- /dev/null
+++ b/epub2html
@@ -1,0 +1,60 @@
+#!/bin/rc
+# epub2html - convert epub to html
+# usage: epub2html file.epub
+# bugs: only one epub at a time
+
+# set some defaults
+rfork e
+cwd=`{pwd}+fn usage{+ echo Usage: epub2html file.epub >[1=2]
+ exit usage
+}
+if(! ~ $#* 1) usage
+file=$1
+if(! ~ $file /*) file=`{cleanname $cwd/$1}+if(! test -f $file && ! ~ $1 *.[Ee][Pp][Uu][Bb]) usage
+name=`{basename $1 | sed 's/\.[Ee][Pp][Uu][Bb]//'}+dir=$name^_files
+
+# determine directory name of toc file
+fn ops{+ ops=`{ls -p $1 | grep -i '^o.*ps'}+ if(~ $#ops 0) echo $1
+ if not{+ toc=`{ls -p $1/$ops | grep -i 'toc.ncx'}+ if(~ $#toc 0) echo $1
+ if not echo $1/$ops
+ }
+}
+
+# extract epub and chapter information
+mkdir -p $dir && cd $dir
+unzip -af $file >/dev/null >[2=1]
+ops=`{ops $cwd/$dir} && cd $ops+cat [Tt][Oo][Cc].[Nn][Cc][Xx] | sed -n '/<navPoint/,/<\/navPoint/p' |
+ sed -n 's/.*<text>(.*)<\/text>.*/\1/p' > chaps
+cat [Tt][Oo][Cc].[Nn][Cc][Xx] | sed -n '/<navPoint/,/<\/navPoint/p' |
+ sed -n 's/.*src="(.*)".*/\1/p' | sed 's/%20/ /g' > links
+
+# generate html index
+cat <<eof > $cwd/$name.html
+<!DOCTYPE html>
+<html>
+ <head>
+ <meta charset="utf-8">
+ <title>Contents</title>
+ </head>
+ <body>
+ <h1>Contents:</h1>
+eof
+for(i in `{seq `{cat links | wc -l}}){+ link=`{sed -n $i^p links}+ chap=`{sed -n $i^p chaps}+ echo ' <a href="'$ops^/^$"link'">'$"chap'</a><br>' \
+ >> $cwd/$name.html
+}
+cat <<eof >> $cwd/$name.html
+ </body>
+</html>
+eof
--
⑨