#!/usr/bin/env python3 # -*- coding: utf-8 -*- import re import requests import json import time from urllib.parse import parse_qs, urlparse from config import USER_AGENT def check_url_patterns(url): """ Memeriksa apakah URL adalah URL Terabox yang valid. Args: url (str): URL yang akan diperiksa Returns: bool: True jika URL adalah URL Terabox yang valid, False jika tidak """ patterns = [ r"ww\.mirrobox\.com", r"www\.nephobox\.com", r"freeterabox\.com", r"www\.freeterabox\.com", r"1024tera\.com", r"4funbox\.co", r"www\.4funbox\.com", r"mirrobox\.com", r"nephobox\.com", r"terabox\.app", r"terabox\.com", r"www\.terabox\.ap", r"www\.terabox\.com", r"www\.1024tera\.co", r"www\.momerybox\.com", r"teraboxapp\.com", r"momerybox\.com", r"tibibox\.com", r"www\.tibibox\.com", r"www\.teraboxapp\.com", ] for pattern in patterns: if re.search(pattern, url): return True return False def get_formatted_size(size_in_bytes): """ Mengubah ukuran dalam bytes menjadi format yang mudah dibaca. Args: size_in_bytes (int): Ukuran dalam bytes Returns: str: Ukuran dalam format yang mudah dibaca (KB, MB, GB) """ if size_in_bytes < 1024: return f"{size_in_bytes} B" elif size_in_bytes < 1024 * 1024: return f"{size_in_bytes / 1024:.2f} KB" elif size_in_bytes < 1024 * 1024 * 1024: return f"{size_in_bytes / (1024 * 1024):.2f} MB" else: return f"{size_in_bytes / (1024 * 1024 * 1024):.2f} GB" def extract_terabox_url(text): """ Mengekstrak URL Terabox dari teks. Args: text (str): Teks yang berisi URL Terabox Returns: str or None: URL Terabox jika ditemukan, None jika tidak """ pattern = r"(https?://\S+)" urls = re.findall(pattern, text) for url in urls: if check_url_patterns(url): return url return None def get_terabox_download_link(url): """ Mendapatkan link download langsung dari URL Terabox. Args: url (str): URL Terabox Returns: dict: Informasi file termasuk link download, nama file, ukuran, dll. Atau None jika gagal """ try: print(f"Processing URL: {url}") # Metode 1: Menggunakan API ytshorts.savetube.me headers = { "User-Agent": USER_AGENT, "Accept": "application/json, text/plain, */*", "Content-Type": "application/json", "Origin": "https://ytshorts.savetube.me", "Referer": "https://ytshorts.savetube.me/", } api_url = "https://ytshorts.savetube.me/api/v1/terabox-downloader" response = requests.post( api_url, headers=headers, json={"url": url}, timeout=30 ) print(f"API Response Status: {response.status_code}") if response.status_code == 200: try: data = response.json() print(f"API Response Data: {json.dumps(data, indent=2)}") responses = data.get("response", []) if responses: resolutions = responses[0].get("resolutions", {}) if resolutions: download_link = resolutions.get("Fast Download", "") video_link = resolutions.get("HD Video", "") if download_link or video_link: # Dapatkan informasi file dari header file_name = None file_size = None direct_link = None if video_link: try: response = requests.head(video_link, timeout=10) content_length = response.headers.get("Content-Length", 0) content_disposition = response.headers.get("content-disposition") if content_disposition: file_name_match = re.findall('filename="(.+)"', content_disposition) if file_name_match: file_name = file_name_match[0] if content_length: file_size = int(content_length) except Exception as e: print(f"Error getting video link info: {str(e)}") if download_link: try: response = requests.head(download_link, timeout=10, allow_redirects=True) direct_link = response.url except Exception as e: print(f"Error getting direct link: {str(e)}") direct_link = download_link # Jika tidak ada nama file, ekstrak dari URL if not file_name: path = urlparse(url).path if path: file_name = path.split('/')[-1] if not file_name: file_name = "terabox_file" # Buat data hasil return { "file_name": file_name, "link": video_link or direct_link, "direct_link": direct_link or download_link, "thumb": None, "size": get_formatted_size(file_size) if file_size else "Unknown", "size_bytes": file_size, } except Exception as e: print(f"Error parsing API response: {str(e)}") # Metode 2: Menggunakan API gofile.io sebagai alternatif # Ini adalah simulasi untuk tujuan demonstrasi # Dalam implementasi nyata, kita perlu mengupload file ke gofile.io terlebih dahulu # Fallback: Menggunakan metode scraping sederhana try: # Ubah domain ke 1024terabox.com untuk konsistensi netloc = urlparse(url).netloc url = url.replace(netloc, "1024terabox.com") headers = { "User-Agent": USER_AGENT, "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,*/*;q=0.8", "Accept-Language": "en-US,en;q=0.5", } response = requests.get(url, headers=headers, timeout=10) print(f"Scraping Response Status: {response.status_code}") if response.status_code == 200: # Coba ekstrak nama file dari halaman file_name_match = re.search(r'(.*?) - Terabox', response.text) file_name = file_name_match.group(1) if file_name_match else "terabox_file" # Coba ekstrak thumbnail dari halaman thumbnail_match = re.search(r'og:image" content="([^"]+)"', response.text) thumbnail = thumbnail_match.group(1) if thumbnail_match else None # Karena kita tidak bisa mendapatkan link download langsung dengan scraping sederhana, # kita hanya mengembalikan informasi file yang berhasil diekstrak return { "file_name": file_name, "link": url, # Gunakan URL asli sebagai link "direct_link": url, # Tidak ada link download langsung "thumb": thumbnail, "size": "Unknown", "size_bytes": None, "requires_premium": True, # Tandai bahwa file ini memerlukan akses premium } except Exception as e: print(f"Error scraping page: {str(e)}") # Jika semua metode gagal, kembalikan informasi dasar return { "file_name": "terabox_file", "link": url, "direct_link": url, "thumb": None, "size": "Unknown", "size_bytes": None, "requires_premium": True, "message": "Tidak dapat mengekstrak link download langsung. File ini mungkin memerlukan akses premium atau URL tidak valid." } except Exception as e: print(f"Error getting Terabox download link: {str(e)}") return None