aaded script

strip_pdf.py

+#!/usr/bin/python3
+
+import re, sys, os
+import subprocess
+
+def is_tool(name):
+    from shutil import which
+    return which(name) is not None
+
+
+if not is_tool('qpdf') or not is_tool('fix-qdf'):
+    print ('This tool depends on the \"qpdf\" and \"fix-qdf\" tools. Please install first!')
+    sys.exit(1)
+
+if (len (sys.argv) != 2):
+    print ('Please pass name of pdf file to remove page groups from.')
+    sys.exit(1)
+    
+print (sys.argv)
+filename = sys.argv[1]
+filename_name, filename_extension = os.path.splitext(filename)
+if filename_extension != ".pdf":
+    print ("Can only handle pdf input files.")
+    sys.exit(1)
+outfilename = filename_name + '.strip.pdf'
+outfile = open(outfilename, 'xb')
+
+qpdf = subprocess.Popen(['qpdf', '--qdf', filename, '-'], stdin=subprocess.PIPE, stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True)
+fixpdf = subprocess.Popen('fix-qdf', stdin=subprocess.PIPE, stdout=outfile, stderr=subprocess.PIPE)
+
+output, err = qpdf.communicate()
+
+
+page_group = None
+for line in output:
+    print (type(line), line)
+    if page_group is None:
+        if line.rstrip() == b"  /Group <<":
+            page_group = [line]
+        else:
+            fixpdf.stdin.write(line)
+    else:
+        page_group.append(line)
+        if line.rstrip() == b"  >>":
+            break
+else:
+    if page_group:
+        fixpdf.stdin.write(b"".join(page_group))
+        page_group = None
+
+for line in output:
+    fixpdf.stdin.write(line)
+fixpdf.stdin.flush()
+
+fixout,fixerr = fixpdf.communicate()
+
+print (fixout, fixerr)
+
+if page_group:
+    stderr.write(b"".join(page_group))
+else:
+    stderr.write(b"note: did not find page group\n")