Add scripts

extract_form_fields.py

@@ -0,0 +1,103 @@
+#!/usr/bin/env python3
+"""
+extract form field data from PDFs recursively
+"""
+from pypdf import PdfReader
+from pathlib import Path
+
+def extract_form_fields(pdf_path):
+    try:
+        reader = PdfReader(pdf_path)
+
+        if reader.is_encrypted:
+            return {'file': str(pdf_path), 'error': 'File is encrypted'}
+
+        fields = reader.get_fields()
+
+        if fields:
+            form_data = []
+
+            for field_name, field_info in fields.items():
+                if not field_info: 
+                    continue
+
+                field_entry = {
+                    'name': field_name,
+                    'value': field_info.get('/V', ''),
+                    'default_value': field_info.get('/DV', ''),
+                    'type': field_info.get('/FT', ''),
+                    'flags': field_info.get('/Ff', 0),
+                    'read_only': bool(field_info.get('/Ff', 0) & 1),
+                    'required': bool(field_info.get('/Ff', 0) & 2),
+                }
+
+                # alternate field name if present
+                if '/T' in field_info:
+                    field_entry['name'] = field_info['/T']
+
+                # tooltip/description
+                if '/TU' in field_info:
+                    field_entry['tooltip'] = field_info['/TU']
+
+                form_data.append(field_entry)
+
+            return {
+                'file': str(pdf_path),
+                'field_count': len(form_data),
+                'fields': form_data
+            }
+
+        return None
+
+    except Exception as e:
+        return {
+            'file': str(pdf_path),
+            'error': str(e)
+        }
+
+def main():
+    pdf_files = Path('.').rglob('*.pdf')
+    found_count = 0
+
+    print(f"{'SCANNING FOR FORM FIELDS':=^60}")
+
+    for pdf_file in pdf_files:
+        result = extract_form_fields(pdf_file)
+
+        if result:
+            if 'error' in result:
+                # print(f"\nFile: {result['file']}")
+                # print(f"  [!] Error: {result['error']}")
+                continue
+
+            found_count += 1
+            print(f"\nFile: {result['file']}")
+            print(f"  Total Fields: {result['field_count']}")
+            print("-" * 60)
+
+            for field in result['fields']:
+                # clean up type string (e.g. '/Tx' -> 'Tx')
+                f_type = str(field['type']).replace('/', '') if field['type'] else 'UNK'
+
+                val = field['value']
+                display_val = f"'{val}'" if val else "<empty>"
+
+                status = []
+                if field['required']: status.append("REQ")
+                if field['read_only']: status.append("RO")
+                status_str = f"[{', '.join(status)}]" if status else ""
+
+                print(f"  [{f_type:<3}] {field['name']}")
+                print(f"        Value: {display_val}")
+
+                if status_str:
+                    print(f"        Flags: {status_str}")
+                if field.get('tooltip'):
+                    print(f"        Tip:   {field['tooltip']}")
+
+            print("-" * 60)
+
+    print(f"\nExtraction complete. Found {found_count} PDFs with form fields.")
+
+if __name__ == '__main__':
+    main()