クラウドフレア トゥルネスティールを解決する方法 ラングラフ エージェントで

python -m venv .venv
source .venv/bin/activate
pip install git+https://github.com/capsolver-ai/capsolver-core.git
pip install "capsolver-agent[langchain] @ git+https://github.com/capsolver-ai/capsolver-agent.git"
pip install langchain-openai langgraph playwright
playwright install chromium

from typing import Literal, TypedDict

class AgentState(TypedDict, total=False):
    request_id: str
    purpose: str
    page_id: str
    current_url: str
    step: str
    challenge_detected: bool
    challenge_attempts: int
    challenge_status: Literal[
        "not-needed", "pending", "resolved", "review", "denied"
    ]
    error_code: str | None
    final_assertion_passed: bool

from urllib.parse import urlparse

ALLOWED_HOSTS = {"staging.example.com", "research.example.com"}
ALLOWED_PURPOSES = {"qa-validation", "public-data-research"}

def authorize_challenge(state: AgentState) -> AgentState:
    host = urlparse(state["current_url"]).hostname
    attempts = state.get("challenge_attempts", 0)

    if host not in ALLOWED_HOSTS:
        return {**state, "challenge_status": "denied", "error_code": "domain"}
    if state.get("purpose") not in ALLOWED_PURPOSES:
        return {**state, "challenge_status": "denied", "error_code": "purpose"}
    if attempts >= 2:
        return {**state, "challenge_status": "review", "error_code": "retry-limit"}
    return {**state, "challenge_status": "pending"}

class BrowserRegistry:
    def __init__(self):
        self._pages = {}

    def register(self, page_id: str, page) -> None:
        self._pages[page_id] = page

    def get(self, page_id: str):
        if page_id not in self._pages:
            raise KeyError("browser page is not registered")
        return self._pages[page_id]

    async def remove(self, page_id: str) -> None:
        page = self._pages.pop(page_id, None)
        if page is not None:
            await page.close()

import os
from capsolver_core import create_capsolver

async def solve_turnstile_node(
    state: AgentState,
    registry: BrowserRegistry,
) -> AgentState:
    page = registry.get(state["page_id"])
    attempts = state.get("challenge_attempts", 0) + 1

    async with create_capsolver(
        api_key=os.environ["CAPSOLVER_API_KEY"],
        default_timeout=120,
        polling_interval=5,
    ) as cap:
        detected = await cap.detect(page)
        if not detected:
            return {
                **state,
                "challenge_attempts": attempts,
                "challenge_status": "not-needed",
                "error_code": None,
            }

        results = await cap.solve_on_page(page)

    failures = [item for item in results if item.error or not item.filled]
    if failures:
        return {
            **state,
            "challenge_attempts": attempts,
            "challenge_status": "review" if attempts >= 2 else "pending",
            "error_code": "fill-back-failed",
        }

    return {
        **state,
        "challenge_attempts": attempts,
        "challenge_status": "resolved",
        "error_code": None,
    }

async def verify_page_node(
    state: AgentState,
    registry: BrowserRegistry,
) -> AgentState:
    page = registry.get(state["page_id"])
    try:
        await page.get_by_test_id("authorized-content").wait_for(timeout=15_000)
        return {
            **state,
            "final_assertion_passed": True,
            "step": "continue",
            "error_code": None,
        }
    except Exception:
        return {
            **state,
            "final_assertion_passed": False,
            "challenge_status": "review",
            "error_code": "page-assertion-failed",
        }

from langgraph.graph import END, StateGraph

def route_after_authorization(state: AgentState) -> str:
    if state["challenge_status"] == "pending":
        return "solve"
    if state["challenge_status"] in {"denied", "review"}:
        return "human_review"
    return "verify"

def route_after_solve(state: AgentState) -> str:
    if state["challenge_status"] == "resolved":
        return "verify"
    if state["challenge_status"] == "pending":
        return "authorize"
    return "human_review"

def build_graph(authorize, solve, verify, human_review):
    graph = StateGraph(AgentState)
    graph.add_node("authorize", authorize)
    graph.add_node("solve", solve)
    graph.add_node("verify", verify)
    graph.add_node("human_review", human_review)
    graph.set_entry_point("authorize")
    graph.add_conditional_edges(
        "authorize",
        route_after_authorization,
        {"solve": "solve", "verify": "verify", "human_review": "human_review"},
    )
    graph.add_conditional_edges(
        "solve",
        route_after_solve,
        {"authorize": "authorize", "verify": "verify", "human_review": "human_review"},
    )
    graph.add_edge("verify", END)
    graph.add_edge("human_review", END)
    return graph.compile()

async def solved_stub(state: AgentState) -> AgentState:
    return {
        **state,
        "challenge_attempts": state.get("challenge_attempts", 0) + 1,
        "challenge_status": "resolved",
        "error_code": None,
    }

async def failed_stub(state: AgentState) -> AgentState:
    return {
        **state,
        "challenge_attempts": state.get("challenge_attempts", 0) + 1,
        "challenge_status": "review",
        "error_code": "fixture-failure",
    }