advanced_clone_gui.py

import os
import re
import requests
from urllib.parse import urljoin, urlparse
from bs4 import BeautifulSoup
import tkinter as tk
from tkinter import ttk, filedialog, messagebox, scrolledtext
import threading

class WebClonerGUI:
    def __init__(self, root):
        self.root = root
        self.root.title("Advanced Web Cloner")
        self.root.geometry("800x600")

        # Variabel GUI
        self.target_url = tk.StringVar()
        self.output_dir = tk.StringVar(value="cloned_site")
        self.max_depth = tk.IntVar(value=2)
        self.is_running = False

        # Setup GUI
        self.setup_gui()

    def setup_gui(self):
        # Frame input
        input_frame = ttk.Frame(self.root, padding="10")
        input_frame.grid(row=0, column=0, sticky="ew")
        self.root.columnconfigure(0, weight=1)
        self.root.rowconfigure(1, weight=1)

        ttk.Label(input_frame, text="URL Target:").grid(row=0, column=0, sticky="w", pady=2)
        ttk.Entry(input_frame, textvariable=self.target_url, width=60).grid(row=0, column=1, padx=5, pady=2)
        ttk.Button(input_frame, text="Pilih Folder", command=self.select_output_dir).grid(row=0, column=2, padx=5)

        ttk.Label(input_frame, text="Output Folder:").grid(row=1, column=0, sticky="w", pady=2)
        ttk.Entry(input_frame, textvariable=self.output_dir, width=60).grid(row=1, column=1, padx=5, pady=2)

        ttk.Label(input_frame, text="Max Kedalaman (rekursif):").grid(row=2, column=0, sticky="w", pady=2)
        ttk.Spinbox(input_frame, from_=1, to=5, textvariable=self.max_depth, width=5).grid(row=2, column=1, sticky="w", padx=5, pady=2)

        # Tombol
        btn_frame = ttk.Frame(self.root, padding="10")
        btn_frame.grid(row=1, column=0, sticky="nsew")
        self.start_btn = ttk.Button(btn_frame, text="Mulai Clone", command=self.start_clone)
        self.start_btn.grid(row=0, column=0, padx=5)

        # Log area
        self.log_text = scrolledtext.ScrolledText(btn_frame, wrap=tk.WORD, state='disabled')
        self.log_text.grid(row=1, column=0, pady=10, sticky="nsew")
        btn_frame.columnconfigure(0, weight=1)
        btn_frame.rowconfigure(1, weight=1)

    def select_output_dir(self):
        folder = filedialog.askdirectory()
        if folder:
            self.output_dir.set(folder)

    def log(self, msg):
        self.log_text.config(state='normal')
        self.log_text.insert(tk.END, msg + "\n")
        self.log_text.see(tk.END)
        self.log_text.config(state='disabled')
        self.root.update_idletasks()

    def is_valid(self, url):
        parsed = urlparse(url)
        return bool(parsed.netloc) and bool(parsed.scheme)

    def get_all_links(self, soup, base_url):
        links = set()
        for a_tag in soup.find_all("a", href=True):
            href = a_tag["href"]
            full_url = urljoin(base_url, href)
            if self.is_valid(full_url) and urlparse(full_url).netloc == urlparse(base_url).netloc:
                links.add(full_url)
        return links

    def get_all_resources(self, soup, base_url):
        resources = set()

        # CSS
        for link in soup.find_all("link", rel="stylesheet"):
            href = link.get("href")
            if href:
                full_url = urljoin(base_url, href)
                if self.is_valid(full_url):
                    resources.add(full_url)

        # JS
        for script in soup.find_all("script", src=True):
            src = script["src"]
            full_url = urljoin(base_url, src)
            if self.is_valid(full_url):
                resources.add(full_url)

        # Images
        for img in soup.find_all("img", src=True):
            src = img["src"]
            full_url = urljoin(base_url, src)
            if self.is_valid(full_url):
                resources.add(full_url)

        return resources

    def download_file(self, url, folder):
        try:
            response = requests.get(url, timeout=10)
            response.raise_for_status()

            # Buat path lokal
            parsed = urlparse(url)
            rel_path = parsed.path.lstrip("/")
            if not rel_path or rel_path.endswith("/"):
                rel_path = os.path.join(rel_path, "index.html")

            full_path = os.path.join(folder, rel_path)
            os.makedirs(os.path.dirname(full_path), exist_ok=True)

            with open(full_path, "wb") as f:
                f.write(response.content)
            self.log(f"Downloaded: {url}")
        except Exception as e:
            self.log(f"Failed to download {url}: {e}")

    def clone_page(self, url, folder, visited, depth, max_depth):
        if depth > max_depth or url in visited:
            return
        visited.add(url)

        try:
            response = requests.get(url, timeout=10)
            response.raise_for_status()
            soup = BeautifulSoup(response.text, "html.parser")

            # Simpan HTML
            parsed = urlparse(url)
            rel_path = parsed.path.lstrip("/")
            if not rel_path or rel_path.endswith("/"):
                rel_path = os.path.join(rel_path, "index.html")
            full_path = os.path.join(folder, rel_path)
            os.makedirs(os.path.dirname(full_path), exist_ok=True)

            with open(full_path, "w", encoding="utf-8") as f:
                f.write(str(soup))

            self.log(f"Saved: {url}")

            # Ambil resource
            resources = self.get_all_resources(soup, url)
            for res_url in resources:
                self.download_file(res_url, folder)

            # Ambil link untuk rekursif
            if depth < max_depth:
                links = self.get_all_links(soup, url)
                for link in links:
                    self.clone_page(link, folder, visited, depth + 1, max_depth)

        except Exception as e:
            self.log(f"Error cloning {url}: {e}")

    def start_clone(self):
        if self.is_running:
            return
        self.is_running = True
        self.start_btn.config(state='disabled')
        threading.Thread(target=self.run_clone, daemon=True).start()

    def run_clone(self):
        try:
            url = self.target_url.get().strip()
            folder = self.output_dir.get()
            max_depth = self.max_depth.get()

            if not url:
                messagebox.showerror("Error", "URL tidak boleh kosong!")
                return

            self.log("Mulai cloning...")
            visited = set()
            self.clone_page(url, folder, visited, 1, max_depth)
            self.log("Cloning selesai!")
        except Exception as e:
            self.log(f"Error: {e}")
        finally:
            self.is_running = False
            self.start_btn.config(state='normal')

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