Refactor authentication and session management

- Removed old llm_login and session scripts, replacing them with a new structure for handling SSO login and session management.
- Introduced a new prompt system for collecting SSO redirect URLs, ensuring compliance with security protocols.
- Implemented a robust backend notification system for tracking scan initiation.
- Enhanced browser profile configuration and resource management for improved session handling.
- Added utility functions for environment variable checks and logging.
- Updated the overall architecture to improve maintainability and readability.

lib/utils/__init__.py

@@ -0,0 +1,40 @@
+from lib.utils.config import (
+    BACKEND_URL,
+    GOOGLE_API_KEY,
+    GOOGLE_MODEL,
+    GOOGLE_PLANNER_MODEL,
+)
+
+
+def show_info():
+    print("🔧 환경 설정:")
+    print(browser_use_version())
+    print(f"🔗 Backend URL: {BACKEND_URL}")
+    print(
+        f"🔑 Google API Key: {'*' * (len(GOOGLE_API_KEY) - 4) + GOOGLE_API_KEY[-4:] if GOOGLE_API_KEY else None}"
+    )
+    print(f"🌐 Google Model: {GOOGLE_MODEL}")
+    print(f"🌐 Google Planner Model: {GOOGLE_PLANNER_MODEL}")
+
+
+def browser_use_version():
+    try:
+        # run uv pip show browser-use
+        import subprocess
+
+        result = subprocess.run(
+            ["uv", "pip", "show", "browser-use"],
+            capture_output=True,
+            text=True,
+            check=True,
+        )
+
+        print("📦 Browser Use 패키지 정보:")
+        return result.stdout.strip()
+    except ImportError:
+        return None
+
+
+def env_cheker():
+    if GOOGLE_API_KEY is None:
+        raise ValueError("GOOGLE_API_KEY 환경변수가 설정되지 않았습니다.")

lib/utils/backend_client.py

@@ -0,0 +1,21 @@
+import requests
+from config import BACKEND_URL
+
+def notify_backend(target_url):
+    # Backend에 스캔 시작을 알림
+    try:
+        response = requests.post(
+            f"{BACKEND_URL}/start", params={"url": target_url}, timeout=5
+        )
+        if response.status_code == 200:
+            print(f"✅ Backend notified: {response.text}")
+        else:
+            print(f"⚠️ Backend notification failed: {response.status_code}")
+    except requests.exceptions.ConnectionError:
+        print(
+            f"⚠️ Backend server not available at {BACKEND_URL}. Continuing without notification."
+        )
+    except requests.exceptions.Timeout:
+        print(f"⚠️ Backend notification timed out. Continuing without notification.")
+    except Exception as e:
+        print(f"⚠️ Failed to notify backend: {e}")

lib/utils/browser_use/__init__.py

@@ -0,0 +1,29 @@
+from func import *
+import clean_resources as clean_resources_func
+
+# Initialize configuration
+proxy_url = setup_proxy()
+storage_state_path = setup_storage_state()
+
+# Create browser profile
+profile = BrowserProfile(
+    # Security settings
+    disable_security=True,
+    stealth=True,
+    
+    # Display settings
+    headless=False,
+    device_scale_factor=1,
+    window_size={"width": 1600, "height": 900},
+    viewport={"width": 1600, "height": 900},
+    
+    # Data persistence
+    user_data_dir=None,
+    storage_state=storage_state_path,
+    
+    # Network settings
+    proxy={"server": proxy_url} if proxy_url else None,
+    
+    # Additional arguments
+    args=get_browser_args(),
+)

lib/utils/browser_use/clean_resources.py

@@ -0,0 +1,25 @@
+from pathlib import Path
+
+async def clean_resources(agent=None, session=None):
+    """리소스를 정리하는 함수"""
+    storage_state_temp_path = Path("./data/storage_state_temp.json").resolve()
+    if storage_state_temp_path.exists():
+        try:
+            # remove file
+            print(f"🗑️ 임시 스토리지 상태 파일 삭제 중: {storage_state_temp_path}")
+            # unlink removes the file
+            storage_state_temp_path.unlink()
+            print("🗑️ 임시 스토리지 상태 파일 삭제 완료.")
+        except Exception as e:
+            print(f"⚠️ 임시 스토리지 상태 파일 삭제 실패: {e}")
+
+    if agent:
+        try:
+            await agent.close()
+        except Exception as e:
+            print(f"⚠️ 에이전트 리소스 정리 실패: {e}")
+    if session:
+        try:
+            await session.close()
+        except Exception as e:
+            print(f"⚠️ 세션 리소스 정리 실패: {e}")

lib/utils/browser_use/func.py

@@ -0,0 +1,69 @@
+import os
+from pathlib import Path
+from dotenv import load_dotenv
+from browser_use import BrowserProfile
+
+# Load environment variables
+load_dotenv(override=True)
+
+def setup_proxy():
+    """Configure proxy settings from environment variables."""
+    proxy_host = os.getenv("PROXY_HOST")
+    proxy_port = os.getenv("PROXY_PORT")
+
+    if proxy_host and proxy_port:
+        proxy_url = f"http://{proxy_host}:{proxy_port}"
+        print(f"🔗 Using proxy: {proxy_host}:{proxy_port}")
+        return proxy_url
+    else:
+        print("🔗 No proxy configured, using direct connection.")
+        return None
+
+
+def setup_storage_state():
+    """Setup browser storage state for session persistence."""
+    storage_state_path = Path("./data/storage_state.json").resolve()
+    storage_state_temp_path = Path("./data/storage_state_temp.json").resolve()
+
+    if storage_state_path.exists():
+        if storage_state_temp_path.exists():
+            storage_state_temp_path.unlink()
+
+        storage_state_temp_path.write_text(
+            storage_state_path.read_text(encoding="utf-8"), encoding="utf-8"
+        )
+        print(f"🔄 Using existing storage state: {storage_state_temp_path}")
+        return str(storage_state_temp_path)
+
+    return None
+
+
+def get_browser_args():
+    """Get browser arguments for enhanced compatibility and security."""
+    return [
+        # Security and isolation
+        "--disable-web-security",
+        "--disable-site-isolation-trials",
+        "--disable-features=IsolateOrigins,site-per-process",
+        "--ignore-certificate-errors",
+        "--ignore-ssl-errors",
+        "--allow-running-insecure-content",
+        # Performance and rendering
+        "--disable-features=VizDisplayCompositor",
+        "--disable-dev-shm-usage",
+        # Popup and automation
+        "--disable-popup-blocking",
+        "--disable-blink-features=AutomationControlled",
+        # Browser behavior
+        "--no-first-run",
+        "--no-service-autorun",
+        "--no-default-browser-check",
+        "--password-store=basic",
+        "--use-mock-keychain",
+        # Extensions
+        "--disable-extensions-file-access-check",
+        "--disable-extensions-http-throttling",
+        "--disable-component-extensions-with-background-pages",
+        # Language
+        f"--lang={os.getenv('LANG', 'en_US')}",
+    ]

lib/utils/browser_use/model.py

@@ -0,0 +1,11 @@
+from typing import List
+from pydantic import BaseModel
+
+# 출력 모델
+class OAuth(BaseModel):
+    provider: str
+    oauth_uri: str
+
+
+class OAuthList(BaseModel):
+    oauth_providers: List[OAuth]

lib/utils/config.py

@@ -0,0 +1,8 @@
+import os
+from dotenv import load_dotenv
+load_dotenv(verbose=True, override=True)
+
+BACKEND_URL = os.getenv("BACKEND_URL", "http://localhost:11081")
+GOOGLE_API_KEY = os.getenv("GOOGLE_API_KEY")
+GOOGLE_MODEL = os.getenv("GOOGLE_MODEL", "gemini-2.5-flash-preview-05-20")
+GOOGLE_PLANNER_MODEL = os.getenv("GOOGLE_PLANNER_MODEL", "gemini-2.5-pro-preview-06-05")

lib/utils/is_html.py

@@ -0,0 +1,36 @@
+import requests
+
+def is_html_url(url: str, timeout: float = 10.0) -> bool:
+    """
+    주어진 URL에 HEAD 요청을 보내고, 응답 헤더의 Content-Type이 HTML인지 확인합니다.
+    - url: 검사할 URL 문자열
+    - timeout: 요청 타임아웃(초 단위)
+    
+    반환값:
+    - Content-Type이 'text/html' 로 시작하면 True, 그렇지 않으면 False
+    """
+    
+    try:
+        with requests.get(url, timeout=timeout, stream=True) as response:
+            # 응답 코드가 200번대가 아니면 False로 간주
+            if not response.ok:
+                return False
+
+            content_type = response.headers.get('Content-Type', '')
+            # Content-Type에 'text/html'이 포함되어 있으면 HTML로 간주
+            return content_type.lower().startswith('text/html')
+    except requests.RequestException:
+        return False
+
+if __name__ == '__main__':
+    test_urls = [
+        'https://www.example.com',
+        'https://api.github.com',        # JSON API라서 HTML이 아닐 확률이 높음
+        'https://raw.githubusercontent.com'  # 텍스트 파일 등 다양한 타입
+    ]
+
+    for url in test_urls:
+        if is_html_url(url):
+            print(f"[HTML] {url}")
+        else:
+            print(f"[Not HTML] {url}")

lib/utils/logger.py

@@ -0,0 +1,29 @@
+from pathlib import Path
+from datetime import datetime
+
+# 미리 정해진 파일 경로
+FILE_PATH = Path("data/log.txt")
+
+def logger(msg: str) -> None:
+    try:
+        """
+        msg 문자열을 파일 끝에 추가합니다.
+        - 파일이 없으면 새로 생성
+        - 디렉터리가 없으면 생성
+        """
+        # 상위 디렉터리 생성 (이미 있으면 무시)
+        FILE_PATH.parent.mkdir(parents=True, exist_ok=True)
+        
+        # 현재 시각 구해서 포맷팅
+        now = datetime.now()
+        timestamp = now.strftime("%Y-%m-%d %H:%M:%S")
+
+        # 메시지에 개행이 없으면 자동으로 붙이기
+        newline = "" if msg.endswith("\n") else "\n"
+        line = f"[{timestamp}] {msg}{newline}"
+
+        # 'a' 모드: 파일이 없으면 생성, 있으면 이어쓰기
+        with FILE_PATH.open(mode="a", encoding="utf-8") as f:
+            f.write(line)
+    except:
+        print(msg)

lib/utils/read_txt.py

@@ -0,0 +1,36 @@
+def read_lines_between(filepath: str, start_line: int, end_line: int) -> list[str]:
+    """
+    파일에서 start_line번 째 줄부터 end_line번 째 줄까지 읽어와 
+    각 줄을 요소로 갖는 리스트를 반환하는 함수.
+
+    Parameters:
+    ----------
+    filepath : str
+        읽을 텍스트 파일의 경로
+    start_line : int
+        읽기 시작할 행 번호 (1부터 시작)
+    end_line : int
+        읽을 마지막 행 번호 (start_line <= end_line)
+
+    Returns:
+    -------
+    list[str]
+        각 줄을 문자열로 저장한 리스트. 
+        파일에 해당 범위의 줄이 없으면 가능한 만큼만 반환.
+    """
+
+    if start_line < 1 or end_line < start_line:
+        raise ValueError("start_line은 1 이상이어야 하며, end_line은 start_line 이상이어야 합니다.")
+
+    selected_lines: list[str] = []
+    with open(filepath, 'r', encoding='utf-8') as f:
+        for idx, line in enumerate(f, start=1):
+            if idx < start_line:
+                # 아직 읽기 시작 전
+                continue
+            if idx > end_line:
+                # 읽을 범위를 벗어났으므로 중단
+                break
+            # 줄 끝의 개행 문자를 제거하고 리스트에 추가
+            selected_lines.append(line.rstrip('\n'))
+    return selected_lines