html2pdf_gui.py

#!/usr/bin/env python3
"""
HTML to PDF Converter - GUI Version
A simple graphical interface for converting HTML files to PDF using WeasyPrint.
"""

import tkinter as tk
from tkinter import filedialog, scrolledtext, ttk
from pathlib import Path
import threading
from weasyprint import HTML


class HTML2PDFConverter:
    def __init__(self, root):
        self.root = root
        self.root.title("HTML to PDF Converter")
        self.root.geometry("700x600")
        self.root.resizable(True, True)
        
        self.input_dir = tk.StringVar()
        self.output_dir = tk.StringVar(value="output")
        self.is_converting = False
        
        self.setup_ui()
    
    def setup_ui(self):
        main_frame = ttk.Frame(self.root, padding="10")
        main_frame.grid(row=0, column=0, sticky=(tk.W, tk.E, tk.N, tk.S))
        self.root.columnconfigure(0, weight=1)
        self.root.rowconfigure(0, weight=1)
        main_frame.columnconfigure(1, weight=1)
        
        ttk.Label(main_frame, text="HTML to PDF Converter", 
                 font=('Arial', 16, 'bold')).grid(row=0, column=0, columnspan=3, pady=(0, 20))
        
        ttk.Label(main_frame, text="Input Directory:").grid(row=1, column=0, sticky=tk.W, pady=5)
        ttk.Entry(main_frame, textvariable=self.input_dir, width=50).grid(row=1, column=1, sticky=(tk.W, tk.E), pady=5, padx=5)
        ttk.Button(main_frame, text="Browse...", command=self.browse_input).grid(row=1, column=2, pady=5)
        
        ttk.Label(main_frame, text="Output Directory:").grid(row=2, column=0, sticky=tk.W, pady=5)
        ttk.Entry(main_frame, textvariable=self.output_dir, width=50).grid(row=2, column=1, sticky=(tk.W, tk.E), pady=5, padx=5)
        ttk.Button(main_frame, text="Browse...", command=self.browse_output).grid(row=2, column=2, pady=5)
        
        self.convert_btn = ttk.Button(main_frame, text="Convert to PDF", command=self.start_conversion)
        self.convert_btn.grid(row=3, column=0, columnspan=3, pady=20)
        
        ttk.Label(main_frame, text="Status:", font=('Arial', 10, 'bold')).grid(row=4, column=0, sticky=tk.W, pady=(10, 5))
        
        self.status_text = scrolledtext.ScrolledText(main_frame, height=20, width=80, wrap=tk.WORD)
        self.status_text.grid(row=5, column=0, columnspan=3, sticky=(tk.W, tk.E, tk.N, tk.S), pady=5)
        main_frame.rowconfigure(5, weight=1)
        
        self.status_text.tag_configure("success", foreground="green")
        self.status_text.tag_configure("error", foreground="red")
        self.status_text.tag_configure("info", foreground="blue")
        self.status_text.tag_configure("summary", foreground="purple", font=('Arial', 10, 'bold'))
        
        self.log_message("Welcome! Select an input directory containing HTML files to get started.", "info")
    
    def browse_input(self):
        directory = filedialog.askdirectory(title="Select Input Directory")
        if directory:
            self.input_dir.set(directory)
            self.log_message(f"Input directory selected: {directory}", "info")
    
    def browse_output(self):
        directory = filedialog.askdirectory(title="Select Output Directory")
        if directory:
            self.output_dir.set(directory)
            self.log_message(f"Output directory selected: {directory}", "info")
    
    def log_message(self, message, tag=""):
        self.status_text.insert(tk.END, message + "\n", tag)
        self.status_text.see(tk.END)
        self.root.update_idletasks()
    
    def log_message_safe(self, message, tag=""):
        self.root.after(0, lambda: self.log_message(message, tag))
    
    def update_button_safe(self, state, text):
        self.root.after(0, lambda: self.convert_btn.config(state=state, text=text))
    
    def convert_html_to_pdf(self, html_file, output_dir):
        try:
            pdf_filename = html_file.stem + '.pdf'
            pdf_path = output_dir / pdf_filename
            
            self.log_message_safe(f"Converting: {html_file.name} → {pdf_filename}")
            
            HTML(filename=str(html_file)).write_pdf(str(pdf_path))
            
            self.log_message_safe(f"  ✓ Success: {pdf_path}", "success")
            return True
            
        except Exception as e:
            self.log_message_safe(f"  ✗ Error converting {html_file.name}: {str(e)}", "error")
            return False
    
    def run_conversion(self):
        input_path = Path(self.input_dir.get())
        output_path = Path(self.output_dir.get())
        
        if not input_path.exists():
            self.log_message_safe(f"Error: Input directory '{self.input_dir.get()}' does not exist.", "error")
            self.is_converting = False
            self.update_button_safe(tk.NORMAL, "Convert to PDF")
            return
        
        if not input_path.is_dir():
            self.log_message_safe(f"Error: '{self.input_dir.get()}' is not a directory.", "error")
            self.is_converting = False
            self.update_button_safe(tk.NORMAL, "Convert to PDF")
            return
        
        output_path.mkdir(parents=True, exist_ok=True)
        
        html_files = list(input_path.glob('*.html')) + list(input_path.glob('*.htm'))
        
        if not html_files:
            self.log_message_safe(f"No HTML files found in '{self.input_dir.get()}'", "error")
            self.is_converting = False
            self.update_button_safe(tk.NORMAL, "Convert to PDF")
            return
        
        self.log_message_safe(f"\n{'='*60}", "info")
        self.log_message_safe(f"Found {len(html_files)} HTML file(s) in '{self.input_dir.get()}'", "info")
        self.log_message_safe(f"Output directory: '{self.output_dir.get()}'", "info")
        self.log_message_safe(f"{'='*60}\n", "info")
        
        successful = 0
        failed = 0
        
        for html_file in sorted(html_files):
            if self.convert_html_to_pdf(html_file, output_path):
                successful += 1
            else:
                failed += 1
        
        self.log_message_safe(f"\n{'='*60}", "summary")
        self.log_message_safe(f"Conversion Complete!", "summary")
        self.log_message_safe(f"  Successful: {successful}", "summary")
        self.log_message_safe(f"  Failed: {failed}", "summary")
        self.log_message_safe(f"  Total: {len(html_files)}", "summary")
        self.log_message_safe(f"{'='*60}\n", "summary")
        
        self.is_converting = False
        self.update_button_safe(tk.NORMAL, "Convert to PDF")
    
    def start_conversion(self):
        if self.is_converting:
            return
        
        if not self.input_dir.get():
            self.log_message("Please select an input directory first.", "error")
            return
        
        self.is_converting = True
        self.convert_btn.config(state=tk.DISABLED, text="Converting...")
        
        thread = threading.Thread(target=self.run_conversion, daemon=True)
        thread.start()


def main():
    root = tk.Tk()
    app = HTML2PDFConverter(root)
    root.mainloop()


if __name__ == '__main__':
    main()