Add argument parser and documentation

scripts/pdf_unlock.py

@@ -1,3 +1,38 @@
+"""Remove security features from pdfs.
+
+This script removes security features of pdfs inside a specified folder,
+including restrictions on:
+
+- copying text and images
+- printing the document
+
+usage: pdf_unlock.py [-h] [-r] [-o] folder
+
+positional arguments:
+  folder           name of input folder
+
+
+optional arguments:
+  -h, --help       show this help message and exit
+  -r, --recursive  search for files recursively
+  -o, --overwrite  overwrite original files
+
+Examples:
+
+Search for pdfs inside 'pdf_folder', then create new unlocked versions
+of the pdfs with the the suffix '-unlocked.pdf'.
+> python pdf_unlock.py pdf_folder
+
+Search for pdfs inside 'pdf_folder', then unlock the pdfs and overwrite
+the original versions.
+> python pdf_unlock.py pdf_folder -o
+
+Search recursively for pdfs inside 'pdf_folder' and all subfolders,
+then unlock the pdfs and overwrite the original versions.
+> python pdf_unlock.py pdf_folder -o -r
+
+"""
+
 __author__ = "D. Howe"
 __version__ = "0.1.0"
 __email__ = "d.howe@wrl.unsw.edu.au"
@@ -7,45 +42,41 @@ import sys
 import glob
 import argparse
 import subprocess
+import shutil
 
 
-def pdf_unlock():
-    # Get pdfs in same folder
-    fnames = [
-        os.path.join(name) for name in os.listdir('.') if name.endswith('.pdf')
-    ]
-
-    # Use pdf names from user (if provided)
-    if len(sys.argv[1:]) > 0:
-        fnames = sys.argv[1:]
-
-    for fname in fnames:
+def pdf_unlock(pdf_file, overwrite=False):
+    # Create suffix for unlocked pdfs
+    suffix = '-unlocked'
 
-        # Strip file extension
-        base_name = os.path.splitext(fname)[0]
+    # Strip file extension
+    input_name = os.path.splitext(pdf_file)[0]
+    output_name = input_name + suffix
 
-        # save as temporary file
-        cmd_str = ('gs '
-                   '-dNOPAUSE '
-                   '-dQUIET '
-                   '-dBATCH '
-                   '-sDEVICE=pdfwrite '
-                   '-sOutputFile="{output_pdf}" '
-                   '"{input_pdf}"').format(output_pdf, input_pdf)
+    # Skip file if it has already been processed
+    if input_name.endswith(suffix):
+        return
 
-        print('Processing ' + base_name + '.pdf ...')
+    # save as temporary file
+    cmd_str = ('gs '
+               '-dSAFER '
+               '-dNOPAUSE '
+               '-dQUIET '
+               '-dBATCH '
+               '-sPDFPassword= '
+               '-sDEVICE=pdfwrite '
+               '-sOutputFile="{}.pdf" '
+               '"{}.pdf"').format(output_name, input_name)
 
-        with subprocess.Popen(
-                cmd_str,
-                stdout=subprocess.PIPE,
-                bufsize=1,
-                universal_newlines=True) as p:
-            for line in p.stdout:
-                print(line, end='')
+    with subprocess.Popen(
+            cmd_str, stdout=subprocess.PIPE, bufsize=1,
+            universal_newlines=True) as p:
+        for line in p.stdout:
+            print(line, end='')
 
-        # Overwrite original file
-        os.remove(base_name + '.pdf')
-        os.rename(base_name + '_temp.pdf', base_name + '.pdf')
+    # Overwrite original file
+    if overwrite:
+        shutil.move(output_name + '.pdf', input_name + '.pdf')
 
 
 def main():
@@ -56,9 +87,23 @@ def main():
         '--recursive',
         help='search for files recursively',
         action='store_true')
+    parser.add_argument(
+        '-o',
+        '--overwrite',
+        help='overwrite original files',
+        action='store_true')
     args = parser.parse_args()
 
-    print(args.recursive)
+    # Get pdf files
+    if args.recursive:
+        glob_str = args.folder + '/**/*.pdf'
+    else:
+        glob_str = args.folder + '/*.pdf'
+
+    pdf_files = glob.glob(glob_str, recursive=args.recursive)
+
+    for pdf_file in pdf_files:
+        pdf_unlock(pdf_file, overwrite=args.overwrite)
 
 
 if __name__ == '__main__':