Smart PDF Rename

😫 The Pain Point

You downloaded 100 invoices all named “download.pdf” or “doc123.pdf”. You need them named like “Invoice_2024-01-15_CompanyName.pdf” for organized filing.

🚀 Agentic Solution

A Content-Based Renamer that reads the PDF and names it intelligently.

Key Features:

• Pattern Matching: Extract invoice numbers, dates, titles using regex.
• Template Naming: Define your naming format.
• Preview Mode: See proposed names before applying.

⚔️ Phase 1: Commander (Quick Fix)

For quick renaming.

Prompt:

“I have a folder invoices with PDFs. Write a Python script using pdfplumber to:

1. Extract: Read first page of each PDF.
2. Find Patterns:
   • Invoice number: regex INV-\\d+ or Invoice #\\d+
   • Date: regex for common date formats
3. Rename: To format {Invoice_Number}_{Date}.pdf
4. Dry Run: Default to preview; --apply to actually rename.

Print proposed renames. Skip files where pattern not found.”

Result: Organized file names based on content.

🏗️ Phase 2: Architect (Permanent Tool)

For Accountants/File Managers.

Engineering Prompt:

**Role:** Python Tool Developer
**Task:** Create a "Smart PDF Renamer".

**Requirements:**
1.  **GUI:**
    *   Select folder.
    *   Pattern builder: Extract invoice #, date, customer name.
    *   Naming template input with variables.
    *   Preview table (old name → new name).
    *   "Apply" button.
    *   Progress bar.

2.  **Logic:**
    *   Read first 2 pages for content.
    *   Regex pattern matching.
    *   Handle duplicate names (add suffix).
    *   Sanitize filenames.

3.  **Deliverables:**
    *   `pdf_rename.py`
    *   `run.bat`, `run.sh`
    *   `requirements.txt`

🧠 Prompt Decoding

• Dry Run: Essential for file renaming tools. Never rename without preview.

🛠️ Instructions

1. Copy Prompt → Run with preview.
2. Review names → Apply.