Differences

This shows you the differences between two versions of the page.

--- ingesting:pdfw [2012/11/26 18:30]
giancarlo
+++ ingesting:pdfw [2012/11/26 18:33]
giancarlo
@@ Line 81: / Line 81: @@
 </WRAP>
+<WRAP prewrap center>
+<code bash pdfatiff.sh>
+#!/bin/bash
+bdir=$1
+SAVEIFS=$IFS
+IFS=$(echo -en "\n\b")
+for bookdir in $(find "$bdir/"openbess* -maxdepth 0 -type d );
+do
+   echo "$bookdir"
+   n=0
+   SAVEIFS=$IFS
+   IFS=$(echo -en "\n\b")
+   for nfile in $(find "$bookdir/"*.pdf -type f);
+   do
+      let "n += 1"
+      filepdf="$nfile"
+   done
+   if [ $n -gt 1 ] || [ $n -lt 1 ]
+   then
+      echo "ERROR file PDF non unico"
+      exit
+   fi
+   mkdir "$bookdir""/pdfs"
+   cp "$filepdf" "$bookdir""/pdfs"
+   cd "$bookdir""/pdfs"
+   pdftk "$filepdf" burst output pg-%04d.pdf
+   n=0
+   SAVEIFS=$IFS
+   IFS=$(echo -en "\n\b")
+   for nfile in $(find pg-*.pdf -type f);
+   do
+      let "n += 1"
+      sn=$(printf "%04d" $n)
+      filepdf="$nfile"
+      echo "$filepdf"" -> ""$sn.tif"
+      pdftk "$filepdf" output "temp.pdf"
+      # For PDF from image
+      #	convert -density 150 "temp.pdf" "$sn.tif"
+      # For PDF from Word
+      convert -background white -flatten -density 600 -resize 1200 -border 0.5% -bordercolor LightGray "temp.pdf" "../""$sn.tif"
+      rm "temp.pdf"
+   done
+   cd ~/clineFC
+   rm -R "$bookdir""/pdfs"
+done
+exit
+</code>
+</WRAP>
+The script creates a single tif file for every pdf page (i.e. 0001.tif, 0002.tif, ...) in every book directory.
+//
+//
+Book in now ready for ingesting.