gui_parser.py

import tkinter as tk
from tkinter import ttk, scrolledtext, messagebox
import requests
import re

class ModernRegexGui:
    def __init__(self, root):
        self.root = root
        self.root.title("Web Link Inspector")
        self.root.geometry("800x600")
        self.root.configure(bg="#f0f0f0")

        # Define Styles
        style = ttk.Style()
        style.configure("TButton", font=("Segoe UI", 10))
        style.configure("Header.TLabel", font=("Segoe UI", 14, "bold"), background="#f0f0f0")

        # Main Layout Container
        main_frame = ttk.Frame(root, padding="20")
        main_frame.pack(fill=tk.BOTH, expand=True)

        # Header
        ttk.Label(main_frame, text="URL Link Extractor", style="Header.TLabel").pack(pady=(0, 15))

        # Input Area
        input_frame = ttk.Frame(main_frame)
        input_frame.pack(fill=tk.X, pady=5)
        
        self.url_entry = ttk.Entry(input_frame, font=("Segoe UI", 11))
        self.url_entry.insert(0, "https://www.wikipedia.org")
        self.url_entry.pack(side=tk.LEFT, fill=tk.X, expand=True, padx=(0, 10))

        self.btn_fetch = ttk.Button(input_frame, text="Fetch Links", command=self.run_parser)
        self.btn_fetch.pack(side=tk.LEFT)

        # Results Area
        self.result_area = scrolledtext.ScrolledText(
            main_frame, 
            font=("Consolas", 10), 
            bg="#ffffff", 
            fg="#333333",
            padx=10, 
            pady=10
        )
        self.result_area.pack(fill=tk.BOTH, expand=True, pady=15)

        # Status Bar
        self.status_var = tk.StringVar(value="Ready")
        status_bar = ttk.Label(root, textvariable=self.status_var, relief=tk.SUNKEN, anchor=tk.W)
        status_bar.pack(side=tk.BOTTOM, fill=tk.X)

    def run_parser(self):
        url = self.url_entry.get()
        self.result_area.delete(1.0, tk.END)
        self.status_var.set(f"Connecting to {url}...")
        self.root.update_idletasks()
        
        try:
            headers = {'User-Agent': 'Mozilla/5.0'}
            response = requests.get(url, headers=headers, timeout=10)
            
            # FIX ENCODING HERE
            response.encoding = response.apparent_encoding 
            
            response.raise_for_status()
            
            # Regex for links
            link_pattern = re.compile(r'<a\s+(?:[^>]*?\s+)?href="([^"]*)"[^>]*>(.*?)</a>', re.IGNORECASE)
            links = link_pattern.findall(response.text)

            for href, text in links:
                # Clean up nested tags and fix whitespace
                clean_text = re.sub(r'<[^>]+>', '', text).strip()
                if not clean_text: clean_text = "[No Text]"
                
                self.result_area.insert(tk.END, f"● {clean_text:<40} \n  URL: {href}\n\n")

            self.status_var.set(f"Done! Found {len(links)} links.")

        except Exception as e:
            self.status_var.set("Error occurred.")
            messagebox.showerror("Connection Error", str(e))

if __name__ == "__main__":
    root = tk.Tk()
    app = ModernRegexGui(root)
    root.mainloop()