mirror of
https://github.com/j93es/browser-use-oauth.git
synced 2026-06-04 02:41:53 +09:00
92 lines
3.4 KiB
Python
92 lines
3.4 KiB
Python
import json
|
|
from pydantic import BaseModel
|
|
from browser_use import (
|
|
Agent,
|
|
Controller,
|
|
)
|
|
from lib.agents.run_agent import run_agent
|
|
from lib.utils.logger import logger
|
|
from lib.browser_use_utils.create_google_ai import create_google_ai
|
|
from lib.config import GOOGLE_MODEL, GOOGLE_PLANNER_MODEL
|
|
|
|
NOT_FOUND_LOGIN_PAGE = 0
|
|
FOUND_LOGIN_PAGE = 1
|
|
|
|
class FindLoginPageResponse(BaseModel):
|
|
status: int = NOT_FOUND_LOGIN_PAGE # 0 if not found, 1 if found
|
|
msg: str | None = None
|
|
url: str | None = None
|
|
|
|
async def find_login_page(target_url, session) -> tuple[bool, str | None]:
|
|
initial_actions = [{"open_tab": {"url": target_url}}]
|
|
task = """
|
|
You are an expert in finding login pages.
|
|
|
|
Your task is to navigate to the login page of the given URL. Follow the steps below strictly and return results only in the specified format.
|
|
|
|
※ You are NOT allowed to navigate to URLs that are not directly discoverable within the initial domain. Do NOT use search engines or guess external login URLs.
|
|
|
|
0. INITIAL BLOCK CHECK
|
|
- If the browser is blocked when trying to access the page — due to firewall, CAPTCHA, regional restrictions, or other access denials — immediately terminate the process and return the following JSON:
|
|
```json
|
|
{
|
|
"status": 0,
|
|
"msg": "Blocked",
|
|
"url": ""
|
|
}
|
|
```
|
|
- Do NOT proceed to further steps in this case.
|
|
|
|
1. LOGIN PAGE NAVIGATION
|
|
- Navigate only to a **client-side (non-enterprise)** login page within the provided domain.
|
|
- Do NOT rely on external tools, search engines, or links not directly found on the site.
|
|
- If a consent popup (e.g. for privacy/cookies) appears, you MUST dismiss or close it before proceeding.
|
|
- Since step 0 confirmed access, assume the page now loads properly.
|
|
|
|
2. RETURN FORMAT
|
|
- Once the login page is reached, return a JSON object matching the following schema:
|
|
```json
|
|
{
|
|
"status": 1, // 1 if login page is found, 0 otherwise
|
|
"msg": "Login page found", // Optional message
|
|
"url": "https://example.com/login" // Full URL of the login page if found
|
|
}
|
|
```
|
|
- If the login page cannot be found, return:
|
|
```json
|
|
{
|
|
"status": 0,
|
|
"msg": "Login page not found",
|
|
"url": ""
|
|
}
|
|
```
|
|
- Return ONLY the JSON object. Do NOT include any explanation, logging, or extra output.
|
|
"""
|
|
|
|
|
|
controller = Controller(output_model=FindLoginPageResponse, exclude_actions=['search_google'])
|
|
agent = Agent(
|
|
browser_session=session,
|
|
initial_actions=initial_actions,
|
|
task=task,
|
|
llm=create_google_ai(GOOGLE_MODEL),
|
|
controller=controller,
|
|
)
|
|
|
|
is_failed, final_result = await run_agent(agent)
|
|
if is_failed:
|
|
logger(f"⚠️ 스캔 실패: {target_url} | {final_result}")
|
|
print(f"⚠️ 스캔 실패: {target_url} | {final_result}")
|
|
return False, None;
|
|
|
|
data = json.loads(final_result)
|
|
try:
|
|
resp = FindLoginPageResponse(**data)
|
|
if resp.status == FOUND_LOGIN_PAGE and len(resp.url) > 0:
|
|
return True, resp.url
|
|
else:
|
|
return False, resp.msg
|
|
except Exception as e:
|
|
logger(f"⚠️ 결과 파싱 실패: {target_url} | {e}\n원본 결과: {data.msg}")
|
|
print(f"⚠️ 결과 파싱 실패: {target_url} | {e}\n원본 결과: {data.msg}")
|
|
return False, data.msg
|