edit PDF DecodeParms dict

pdf_edit_via_pikepdf.py

import pikepdf

def edit_decodeparms(pdf_path, output_path):
    with pikepdf.open(pdf_path) as pdf:
        for page_num, page in enumerate(pdf.pages, start=1):
            resources = page.get('/Resources', {})
            xobjects = resources.get('/XObject', {})
            for xobj_name, xobj_ref in xobjects.items():
                xobj = xobj_ref  # Use the object directly
                filters = xobj.get('/Filter', [])
                if not isinstance(filters, list):
                    filters = [filters]
                if '/DCTDecode' in filters:
                    decode_parms = xobj.get('/DecodeParms', {})
                    if decode_parms:
                        keys = list(decode_parms.keys())
                        invalid_keys = [k for k in keys if k != '/ColorTransform']
                        if invalid_keys:
                            print(f"Page {page_num}, XObject {xobj_name}: Removing invalid keys {invalid_keys} from DecodeParms")
                            for key in invalid_keys:
                                del decode_parms[key]  # Remove the invalid key
        # Save the modified PDF to a new file
        pdf.save(output_path)
        print(f"Modified PDF saved to {output_path}")

# Replace with your actual file paths
edit_decodeparms('/path/to/original/HH012060_1146.pdf', '/path/to/new/HH012060_1146_modified.pdf')