#!/usr/bin/env python3 # -*- coding: utf-8 -*- import re import requests import json import time import logging from urllib.parse import parse_qs, urlparse from config import USER_AGENT # Konfigurasi logging logger = logging.getLogger(__name__) 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: logger.info(f"Processing URL: {url}") # Metode 1: Menggunakan API terabox-dl-api.vercel.app (API baru yang lebih reliable) headers = { "User-Agent": USER_AGENT, "Accept": "application/json, text/plain, */*", "Content-Type": "application/json", } api_url = "https://terabox-dl-api.vercel.app/api/getDownloadLink" response = requests.post( api_url, headers=headers, json={"url": url}, timeout=30 ) logger.info(f"API Response Status: {response.status_code}") if response.status_code == 200: try: data = response.json() logger.info(f"API Response Data: {json.dumps(data, indent=2)}") if data.get("status") == "success": file_info = data.get("data", {}) file_name = file_info.get("filename", "terabox_file") file_size = file_info.get("size") direct_link = file_info.get("downloadLink") # Konversi ukuran file jika tersedia size_bytes = None if file_size: # Coba ekstrak ukuran dalam bytes size_match = re.search(r'([\d.]+)\s*([KMGT]?B)', file_size) if size_match: size_num = float(size_match.group(1)) size_unit = size_match.group(2) if size_unit == "KB": size_bytes = int(size_num * 1024) elif size_unit == "MB": size_bytes = int(size_num * 1024 * 1024) elif size_unit == "GB": size_bytes = int(size_num * 1024 * 1024 * 1024) elif size_unit == "TB": size_bytes = int(size_num * 1024 * 1024 * 1024 * 1024) else: # Bytes size_bytes = int(size_num) return { "file_name": file_name, "link": direct_link, "direct_link": direct_link, "thumb": file_info.get("thumbnail"), "size": file_size or "Unknown", "size_bytes": size_bytes, } except Exception as e: logger.error(f"Error parsing API response: {str(e)}") # Metode 2: Menggunakan API alternatif teraboxdownloader.com try: api_url = "https://teraboxdownloader.com/api/task/create" headers = { "User-Agent": USER_AGENT, "Content-Type": "application/x-www-form-urlencoded", "Accept": "application/json, text/plain, */*", "Origin": "https://teraboxdownloader.com", "Referer": "https://teraboxdownloader.com/", } data = { "url": url } response = requests.post(api_url, headers=headers, data=data, timeout=30) logger.info(f"Alternative API Response Status: {response.status_code}") if response.status_code == 200: try: result = response.json() logger.info(f"Alternative API Response: {json.dumps(result, indent=2)}") if result.get("status") == "success": task_id = result.get("data", {}).get("task_id") if task_id: # Dapatkan hasil task time.sleep(2) # Tunggu sebentar agar task diproses result_url = f"https://teraboxdownloader.com/api/task/{task_id}" result_response = requests.get(result_url, headers=headers, timeout=30) if result_response.status_code == 200: result_data = result_response.json() logger.info(f"Task Result: {json.dumps(result_data, indent=2)}") if result_data.get("status") == "success": file_data = result_data.get("data", {}) file_name = file_data.get("file_name", "terabox_file") file_size = file_data.get("file_size", "Unknown") direct_link = file_data.get("direct_download_link") # Konversi ukuran file jika tersedia size_bytes = None if isinstance(file_size, (int, float)): size_bytes = int(file_size) elif isinstance(file_size, str): size_match = re.search(r'([\d.]+)\s*([KMGT]?B)', file_size) if size_match: size_num = float(size_match.group(1)) size_unit = size_match.group(2) if size_unit == "KB": size_bytes = int(size_num * 1024) elif size_unit == "MB": size_bytes = int(size_num * 1024 * 1024) elif size_unit == "GB": size_bytes = int(size_num * 1024 * 1024 * 1024) elif size_unit == "TB": size_bytes = int(size_num * 1024 * 1024 * 1024 * 1024) else: # Bytes size_bytes = int(size_num) return { "file_name": file_name, "link": direct_link, "direct_link": direct_link, "thumb": file_data.get("thumbnail"), "size": file_size, "size_bytes": size_bytes, } except Exception as e: logger.error(f"Error processing alternative API response: {str(e)}") except Exception as e: logger.error(f"Error with alternative API: {str(e)}") # Metode 3: Menggunakan scraping sederhana sebagai fallback 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) logger.info(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: logger.error(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: logger.error(f"Error getting Terabox download link: {str(e)}") return None