Chẩn đoán Thách thức Cloudflare: Nhận dạng và Xác minh Phiên

from dataclasses import dataclass

@dataclass(frozen=True)
class HttpObservation:
    url: str
    status_code: int
    title: str
    html: str
    headers: dict[str, str]


def classify_observation(obs: HttpObservation) -> str:
    title = obs.title.lower()
    html = obs.html.lower()

    if obs.status_code == 429:
        return "RATE_LIMIT"

    if obs.status_code >= 500:
        return "ORIGIN_OR_NETWORK_ERROR"

    if "challenges.cloudflare.com/turnstile" in html:
        return "TURNSTILE_WIDGET"

    challenge_markers = (
        "just a moment" in title
        or "challenge-platform" in html
        or "cf-chl-" in html
    )
    if challenge_markers:
        return "CLOUDFLARE_CHALLENGE"

    if 'type="password"' in html or obs.status_code == 401:
        return "AUTH_REQUIRED"

    if obs.status_code == 200 and 'data-page="expected"' in html:
        return "EXPECTED_PAGE"

    if obs.status_code == 403:
        return "HARD_BLOCK"

    return "UNKNOWN_PAGE"

from dataclasses import dataclass

@dataclass(frozen=True)
class SessionIdentity:
    session_id: str
    proxy_profile: str
    chrome_user_agent: str
    tls_profile: str
    cookie_jar_id: str
    target_host: str

from dataclasses import dataclass
from urllib.parse import urlparse

@dataclass(frozen=True)
class TargetPolicy:
    target_id: str
    hostname: str
    allowed_path_prefixes: tuple[str, ...]
    purpose: str
    proxy_profile: str
    max_attempts: int = 1

TARGETS = {
    "docs_demo": TargetPolicy(
        target_id="docs_demo",
        hostname="approved.example.com",
        allowed_path_prefixes=("/public/", "/test/"),
        purpose="kiểm tra tích hợp được cấp phép",
        proxy_profile="approved_static_us",
    )
}


def resolve_target(target_id: str, url: str) -> TargetPolicy:
    policy = TARGETS.get(target_id)
    if policy is None:
        raise PermissionError("Mục tiêu không xác định")
    parsed = urlparse(url)
    if parsed.scheme != "https":
        raise PermissionError("HTTPS là bắt buộc")
    if parsed.hostname != policy.hostname:
        raise PermissionError("Tên miền nằm ngoài phạm vi được phê duyệt")
    if not any(parsed.path.startswith(p) for p in policy.allowed_path_prefixes):
        raise PermissionError("Đường dẫn nằm ngoài phạm vi được phê duyệt")
    return policy

import os
import capsolver

capsolver.api_key = os.environ["CAPSOLVER_API_KEY"]

PROXY_VAULT = {
    "approved_static_us": os.environ["APPROVED_STATIC_PROXY"],
}


def build_task(
    policy: TargetPolicy,
    identity: SessionIdentity,
    target_url: str,
    fresh_html: str | None,
) -> dict:
    if identity.proxy_profile != policy.proxy_profile:
        raise ValueError("Proxy phiên không khớp với chính sách mục tiêu")
    if identity.target_host != policy.hostname:
        raise ValueError("Tên miền phiên không khớp với chính sách mục tiêu")

    task = {
        "type": "AntiCloudflareTask",
        "websiteURL": target_url,
        "proxy": PROXY_VAULT[identity.proxy_profile],
        "userAgent": identity.chrome_user_agent,
    }
    if fresh_html:
        task["html"] = fresh_html
    return task

from datetime import datetime, timezone

@dataclass(frozen=True)
class ChallengeDocument:
    session_id: str
    target_url: str
    body: str
    status_code: int
    captured_at: str

async def capture_challenge_document(client, identity, target_url):
    response = await client.get(
        target_url,
        session_id=identity.session_id,
        proxy_profile=identity.proxy_profile,
        user_agent=identity.chrome_user_agent,
        tls_profile=identity.tls_profile,
        cookie_jar_id=identity.cookie_jar_id,
    )
    observation = HttpObservation(
        url=str(response.url),
        status_code=response.status_code,
        title=extract_title(response.text),
        html=response.text,
        headers=dict(response.headers),
    )
    if classify_observation(observation) != "CLOUDFLARE_CHALLENGE":
        raise ValueError("Phản hồi không phải là trang xác minh được nhận diện")
    return ChallengeDocument(
        session_id=identity.session_id,
        target_url=target_url,
        body=response.text,
        status_code=response.status_code,
        captured_at=datetime.now(timezone.utc).isoformat(),
    )

def solve_approved_challenge(
    target_id: str,
    target_url: str,
    identity: SessionIdentity,
    document: ChallengeDocument,
) -> dict:
    policy = resolve_target(target_id, target_url)
    if document.session_id != identity.session_id:
        raise ValueError("Tài liệu và phiên không khớp")
    if document.target_url != target_url:
        raise ValueError("Tài liệu và URL đích không khớp")
    task = build_task(
        policy=policy,
        identity=identity,
        target_url=target_url,
        fresh_html=document.body,
    )
    solution = capsolver.solve(task)
    cookies = solution.get("cookies") or {}
    clearance = cookies.get("cf_clearance") or solution.get("token")
    returned_user_agent = solution.get("userAgent") or identity.chrome_user_agent
    if not clearance:
        raise RuntimeError("Kết quả nhiệm vụ không chứa dữ liệu làm sạch")
    return {
        "cookies": cookies,
        "user_agent": returned_user_agent,
    }

async def apply_clearance(client, identity: SessionIdentity, result: dict):
    for name, value in result["cookies"].items():
        await client.set_cookie(
            cookie_jar_id=identity.cookie_jar_id,
            domain=identity.target_host,
            name=name,
            value=value,
            secure=True,
        )
    await client.set_user_agent(
        session_id=identity.session_id,
        user_agent=result["user_agent"],
    )

@dataclass(frozen=True)
class VerificationRule:
    expected_status: int
    required_selectors: tuple[str, ...]
    forbidden_markers: tuple[str, ...]
    expected_path_prefix: str

async def verify_target_page(
    client,
    identity: SessionIdentity,
    target_url: str,
    rule: VerificationRule,
) -> dict:
    response = await client.get(
        target_url,
        session_id=identity.session_id,
        proxy_profile=identity.proxy_profile,
        user_agent=identity.chrome_user_agent,
        tls_profile=identity.tls_profile,
        cookie_jar_id=identity.cookie_jar_id,
    )
    parsed = urlparse(str(response.url))
    body = response.text.lower()
    status_ok = response.status_code == rule.expected_status
    path_ok = parsed.path.startswith(rule.expected_path_prefix)
    markers_ok = not any(marker.lower() in body for marker in rule.forbidden_markers)
    selectors_ok = all(selector_in_html(response.text, selector) for selector in rule.required_selectors)
    return {
        "verified": status_ok and path_ok and markers_ok and selectors_ok,
        "status_ok": status_ok,
        "path_ok": path_ok,
        "markers_ok": markers_ok,
        "selectors_ok": selectors_ok,
    }

from enum import Enum

class FlowState(str, Enum):
    OBSERVED = "OBSERVED"
    CLASSIFIED = "CLASSIFIED"
    TASK_CREATED = "TASK_CREATED"
    RESULT_READY = "RESULT_READY"
    PAGE_VERIFIED = "PAGE_VERIFIED"
    STOPPED = "STOPPED"

ALLOWED = {
    FlowState.OBSERVED: {FlowState.CLASSIFIED, FlowState.STOPPED},
    FlowState.CLASSIFIED: {FlowState.TASK_CREATED, FlowState.STOPPED},
    FlowState.TASK_CREATED: {FlowState.RESULT_READY, FlowState.STOPPED},
    FlowState.RESULT_READY: {FlowState.PAGE_VERIFIED, FlowState.STOPPED},
    FlowState.PAGE_VERIFIED: {FlowState.STOPPED},
}

def transition(current: FlowState, next_state: FlowState) -> FlowState:
    if next_state not in ALLOWED[current]:
        raise ValueError(f"Chuyển tiếp không hợp lệ: {current} -> {next_state}")
    return next_state

ERROR_ACTIONS = {
    "ERROR_INVALID_TASK_DATA": "FIX_INPUT",
    "ERROR_RATE_LIMIT": "WAIT",
    "ERROR_TASK_TIMEOUT": "REVIEW",
    "ERROR_TASK_NOT_SUPPORTED": "RECLASSIFY",
    "ERROR_CAPTCHA_UNSOLVABLE": "REVIEW",
    "ERROR_PROXY_BANNED": "REVIEW_NETWORK",
    "ERROR_KEY_DENIED_ACCESS": "FIX_ACCOUNT",
    "ERROR_ZERO_BALANCE": "FIX_ACCOUNT",
    "ERROR_SERVICE_UNAVALIABLE": "BACKOFF",
}


def normalize_error(error_code: str | None) -> dict:
    code = error_code or "UNKNOWN_ERROR"
    return {
        "category": code,
        "action": ERROR_ACTIONS.get(code, "OPERATOR_REVIEW"),
        "retry_allowed": ERROR_ACTIONS.get(code) in {"WAIT", "BACKOFF"},
    }

SAFE_EVENT_FIELDS = {
    "event",
    "target_id",
    "state",
    "error_category",
    "attempt_count",
    "duration_ms",
    "verified",
    "observed_at",
}


def redact_event(event: dict) -> dict:
    return {
        key: event[key]
        for key in SAFE_EVENT_FIELDS
        if key in event
    }

from datetime import datetime, timezone
from time import monotonic


def diagnostic_event(
    target_id: str,
    state: str,
    attempt_count: int,
    verified: bool,
    started_at: float,
    error_category: str | None = None,
) -> dict:
    return redact_event({
        "event": "cloudflare_challenge_diagnostic",
        "target_id": target_id,
        "state": state,
        "attempt_count": attempt_count,
        "duration_ms": int((monotonic() - started_at) * 1000),
        "verified": verified,
        "error_category": error_category,
        "observed_at": datetime.now(timezone.utc).isoformat(),
    })

import pytest

@pytest.mark.parametrize(
    "status,title,html,expected",
    [
        (429, "Bị giới hạn tốc độ", "", "RATE_LIMIT"),
        (403, "Vui lòng chờ...", "cf-chl-test", "CLOUDFLARE_CHALLENGE"),
        (200, "Đăng nhập", '<input type="password">', "AUTH_REQUIRED"),
        (500, "Lỗi máy chủ", "", "ORIGIN_OR_NETWORK_ERROR"),
    ],
)
def test_classifier(status, title, html, expected):
    observation = HttpObservation(
        url="https://approved.example.com/test/",
        status_code=status,
        title=title,
        html=html,
        headers={},
    )
    assert classify_observation(observation) == expected

def test_task_rejects_proxy_profile_mismatch():
    policy = TARGETS["docs_demo"]
    identity = SessionIdentity(
        session_id="session-1",
        proxy_profile="wrong_profile",
        chrome_user_agent="Mozilla/5.0 ... Chrome/141.0.0.0 ...",
        tls_profile="chrome141",
        cookie_jar_id="jar-1",
        target_host="approved.example.com",
    )

    with pytest.raises(ValueError):
        build_task(
            policy=policy,
            identity=identity,
            target_url="https://approved.example.com/test/",
            fresh_html="<html>Vui lòng chờ...</html>",
        )