506 lines
21 KiB
Python
506 lines
21 KiB
Python
"""站点交互：加购 / 校验购物车 / 进入下单确认页 / 金额守卫 / 提交 / 付款 / 监控
|
|
|
|
实测进度（详见 project://jp-rakuten/checkout-flow-probe-findings）：
|
|
- add_to_cart、verify_cart 已实测可用（Playwright + storage_state 走 SP 通道）
|
|
- enter_checkout 及之后**未实现**：Rakuten 对 checkout 这类敏感操作要求
|
|
session upgrade（重输密码），即使当前 SSO 已登录。这是自动 checkout 的硬墙，
|
|
比 3DS 还前置。本层留接口缝，未实测前调用直接抛「未实现」，不要写猜测的提交逻辑。
|
|
|
|
**httpx 不能用于带账号的写操作**：Rakuten 对账号操作有 TLS/HTTP2 指纹校验，
|
|
同一份 cookie Playwright 能用、httpx 不能。所以本模块全程使用 Playwright
|
|
的 BrowserContext + APIRequestContext（共享 cookie，绕过 CORS）。
|
|
"""
|
|
from __future__ import annotations
|
|
|
|
import json
|
|
import logging
|
|
import re
|
|
from dataclasses import dataclass
|
|
from typing import TYPE_CHECKING
|
|
|
|
from app.shared.errors import (
|
|
CartOperationError,
|
|
InvalidRequestError,
|
|
NotLoggedInError,
|
|
)
|
|
from app.trading.core import auth_site
|
|
from app.trading.worker.models import LeaseTask
|
|
|
|
if TYPE_CHECKING:
|
|
from app.shared.config import Settings
|
|
from app.trading.services.auth_session import AuthSession
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
# 普通购买的事件标识，站点前端构造加购表单时固定带上（同 scraping/parsers/item.py）
|
|
_NORMAL_PURCHASE_EVENT = "ES01_003_001"
|
|
|
|
# 库存类型 → 加购表单里的 inventory_flag（与 scraping/parsers/item.py 一致）
|
|
_INVENTORY_FLAG = {"multiple": "2"}
|
|
_DEFAULT_INVENTORY_FLAG = "1"
|
|
|
|
# 加购端点路径片段（探针实测：basketDomain 逐商品不同，但路径固定）
|
|
_BASKET_PATH = "/rms/mall/bss/cartadd/set"
|
|
|
|
# 购物车页（SP）与 cart 数量 JSONP API（探针实测）
|
|
_CART_PAGE = auth_site.RAKUTEN_CART_URL
|
|
_CART_COUNT_API = "https://cart-api.step.rakuten.co.jp/rms/mall/cart/count/all/jsonp/"
|
|
|
|
# 购物车页未登录标记（旧 marker；新 SPA 上不可靠，这里只作辅助判据）
|
|
_LEGACY_LOGGED_OUT_MARKER = auth_site.RAKUTEN_LOGGED_OUT_MARKER
|
|
|
|
_NOT_IMPLEMENTED_MSG = (
|
|
"站点交互未实现：见 docs/order-gateway.md §10 与 "
|
|
"project://jp-rakuten/checkout-flow-probe-findings。"
|
|
"session upgrade 是 checkout 阶段的硬墙，未实测前不写猜测的提交逻辑。"
|
|
)
|
|
|
|
|
|
@dataclass(slots=True)
|
|
class CheckoutSummary:
|
|
"""下单确认页解析结果（待实测确认字段位置）
|
|
|
|
payable_yen 用于金额守卫；其他字段在实测确认后补全。
|
|
"""
|
|
|
|
payable_yen: int
|
|
site_order_id: str | None = None
|
|
pay_deadline: str | None = None
|
|
|
|
|
|
class SiteInteractor:
|
|
"""Rakuten 站点交互器：持有 Playwright 浏览器 context，复用账号 cookie
|
|
|
|
生命周期：
|
|
- start() 在 worker 启动时调用一次：启动 Playwright + 创建带 cookie 的 context
|
|
- add_to_cart / verify_cart 在每个任务里调用
|
|
- close() 在 worker 关闭时调用
|
|
|
|
浏览器 context 复用同一份登录态，所有任务串行（worker 主循环本就串行），
|
|
不需要为每个任务开新 context——开销大且 cookie 状态会乱。
|
|
"""
|
|
|
|
# 每任务保留的临时状态：task_id → {"item_id": str, "shop_bid": str}
|
|
# 用于 add_to_cart 把抓出来的 item_id / shop_bid 喂给 verify_cart
|
|
_per_task_state: dict[str, dict[str, str]]
|
|
|
|
def __init__(self, *, auth_session: "AuthSession", settings: "Settings"):
|
|
self._auth_session = auth_session
|
|
self._settings = settings
|
|
self._playwright = None
|
|
self._browser = None
|
|
self._context = None # playwright BrowserContext
|
|
self._per_task_state = {}
|
|
# 上次 build context 时读到的 storage_state 文件 mtime。
|
|
# 用于在任务间检测 AuthSession 重登后产生的新 storage_state，触发 context 重建。
|
|
self._state_mtime: float | None = None
|
|
|
|
# ---- 生命周期 ----
|
|
|
|
async def start(self) -> None:
|
|
"""启动 Playwright 与带 cookie 的浏览器 context
|
|
|
|
登录态文件不存在时同样启动（context 没 cookie），后续 add_to_cart 会
|
|
在 require_logged_in 里报错。这样保持启动路径一致。
|
|
"""
|
|
from playwright.async_api import async_playwright
|
|
|
|
state_path = self._settings.auth_state_path / auth_site.profile("rakuten").state_filename
|
|
storage_state = str(state_path) if state_path.exists() else None
|
|
if storage_state is None:
|
|
logger.warning(
|
|
"登录态文件不存在：site_interactor 以无 cookie 状态启动，"
|
|
"加购请求会被站点拒认"
|
|
)
|
|
else:
|
|
self._state_mtime = state_path.stat().st_mtime
|
|
|
|
self._playwright = await async_playwright().start()
|
|
self._browser = await self._playwright.chromium.launch(
|
|
headless=True,
|
|
channel=self._settings.browser_channel or None,
|
|
args=["--no-first-run", "--disable-blink-features=AutomationControlled"],
|
|
)
|
|
self._context = await self._browser.new_context(
|
|
storage_state=storage_state,
|
|
user_agent=auth_site.RAKUTEN_USER_AGENT,
|
|
locale="ja-JP",
|
|
timezone_id="Asia/Tokyo",
|
|
viewport={"width": 390, "height": 844},
|
|
is_mobile=True,
|
|
has_touch=True,
|
|
)
|
|
logger.info("SiteInteractor 已就绪：storage_state=%s", storage_state or "(none)")
|
|
|
|
async def _refresh_context_if_stale(self) -> None:
|
|
"""检查 storage_state 文件 mtime，变化则重建 context
|
|
|
|
AuthSession.try_relogin 成功后会重写 storage_state 文件。本 context 启动时
|
|
用快照式 storage_state 创建，cookie 不会自动同步——必须关掉旧 context、
|
|
用新文件重建。在 add_to_cart / verify_cart 开头各调一次，开销可接受
|
|
（只在 mtime 变了才重建）。
|
|
"""
|
|
state_path = self._settings.auth_state_path / auth_site.profile("rakuten").state_filename
|
|
if not state_path.exists():
|
|
return
|
|
mtime = state_path.stat().st_mtime
|
|
if mtime == self._state_mtime:
|
|
return
|
|
|
|
logger.info(
|
|
"storage_state 文件变化（mtime %s → %s），重建 context",
|
|
self._state_mtime, mtime,
|
|
)
|
|
if self._context is not None:
|
|
try:
|
|
await self._context.close()
|
|
except Exception:
|
|
logger.debug("关闭旧 context 失败", exc_info=True)
|
|
self._context = await self._browser.new_context(
|
|
storage_state=str(state_path),
|
|
user_agent=auth_site.RAKUTEN_USER_AGENT,
|
|
locale="ja-JP",
|
|
timezone_id="Asia/Tokyo",
|
|
viewport={"width": 390, "height": 844},
|
|
is_mobile=True,
|
|
has_touch=True,
|
|
)
|
|
self._state_mtime = mtime
|
|
|
|
async def close(self) -> None:
|
|
"""关闭 context、browser、playwright，吞掉单个 close 异常"""
|
|
for resource, name in (
|
|
(self._context, "context"),
|
|
(self._browser, "browser"),
|
|
(self._playwright, "playwright"),
|
|
):
|
|
if resource is None:
|
|
continue
|
|
try:
|
|
closer = resource.close() if name != "playwright" else resource.stop()
|
|
await closer
|
|
except Exception:
|
|
logger.debug("关闭 %s 失败", name, exc_info=True)
|
|
self._context = None
|
|
self._browser = None
|
|
self._playwright = None
|
|
|
|
# ---- 已实现：add_to_cart / verify_cart ----
|
|
|
|
async def add_to_cart(self, task: LeaseTask) -> None:
|
|
"""加购：打开商品页 → 抽 __INITIAL_STATE__.purchase → POST basketDomain
|
|
|
|
调用方需在 task.intent 提供：
|
|
- item_url: 商品详情页 URL（必填）
|
|
- quantity: 数量，默认 1
|
|
- variant_id: 多规格商品的 variant_id；不传则从 sku.variants[] 自动选第一个非售罄
|
|
- choice: 必填选项的取值列表；不传则每个必填选项用第一个候选值（站点不严格校验）
|
|
|
|
Raises:
|
|
InvalidRequestError: intent.item_url 缺失
|
|
NotLoggedInError: 登录态失效
|
|
CartOperationError: 商品页打不开、state 解析失败、商品不可购买、加购返回错误页
|
|
"""
|
|
intent = task.intent or {}
|
|
item_url = intent.get("item_url")
|
|
if not item_url:
|
|
raise InvalidRequestError("intent.item_url 必填")
|
|
quantity = int(intent.get("quantity") or 1)
|
|
if quantity <= 0:
|
|
raise InvalidRequestError(f"intent.quantity 必须为正整数，收到 {quantity}")
|
|
|
|
await self._auth_session.require_logged_in("rakuten")
|
|
|
|
# 任务开始前刷新 context：AuthSession 可能刚自动重登过，storage_state 变了
|
|
await self._refresh_context_if_stale()
|
|
|
|
page = await self._context.new_page()
|
|
try:
|
|
try:
|
|
await page.goto(item_url, wait_until="domcontentloaded", timeout=30_000)
|
|
await page.wait_for_function(
|
|
"() => window.__INITIAL_STATE__ && window.__INITIAL_STATE__.purchase",
|
|
timeout=10_000,
|
|
)
|
|
except Exception as exc:
|
|
raise CartOperationError(
|
|
f"打开商品页失败或反爬被触发：{type(exc).__name__}: {exc}"
|
|
) from exc
|
|
|
|
html = await page.content()
|
|
state = _parse_initial_state(html)
|
|
if not state:
|
|
raise CartOperationError("无法从商品页抽 __INITIAL_STATE__（可能 PC 模板或反爬）")
|
|
|
|
fields = _extract_purchase_fields(state, intent_override=intent)
|
|
self._per_task_state[task.task_id] = {
|
|
"item_id": fields["form_fields"].get("item_id", ""),
|
|
"shop_bid": fields["form_fields"].get("shop_bid", ""),
|
|
"basket_domain": fields["basket_domain"],
|
|
}
|
|
|
|
if fields["purchase_condition"] != "enabled":
|
|
raise CartOperationError(
|
|
f"商品不可购买：purchaseCondition={fields['purchase_condition']}"
|
|
)
|
|
if not fields["basket_domain"]:
|
|
raise CartOperationError("basketDomain 为空（商品可能下架）")
|
|
# 多规格商品要求选了 variant_id
|
|
if fields["inventory_flag"] == _INVENTORY_FLAG["multiple"] and not fields["form_fields"].get("variant_id"):
|
|
raise CartOperationError(
|
|
"多规格商品未选 variant，且 sku.variants 全部售罄或为空"
|
|
)
|
|
# 必填选项要求填了 choice
|
|
if fields["has_required_options"] and not fields["form_fields"].get(fields["options_field"]):
|
|
raise CartOperationError(
|
|
"商品有必填选项但未提供 choice，且选项无候选值"
|
|
)
|
|
|
|
payload = dict(fields["form_fields"])
|
|
payload[fields["quantity_field"]] = str(quantity)
|
|
|
|
logger.info(
|
|
"加购请求：task_id=%s basket=%s payload=%s",
|
|
task.task_id, fields["basket_domain"], payload,
|
|
)
|
|
|
|
resp = await self._context.request.post(
|
|
fields["basket_domain"],
|
|
form=payload,
|
|
max_redirects=5,
|
|
headers={
|
|
"Referer": item_url,
|
|
"Origin": "https://item.rakuten.co.jp",
|
|
},
|
|
)
|
|
final_url = str(resp.url)
|
|
if "/error" in final_url:
|
|
body = await resp.text()
|
|
msg = _extract_error_message(body) or f"错误页 {final_url}"
|
|
raise CartOperationError(f"加购失败：{msg}")
|
|
|
|
# 成功标志：URL 跳到 cart 且带 added_item 参数（探针实测的落地）
|
|
if "cart" not in final_url:
|
|
body = await resp.text()
|
|
raise CartOperationError(
|
|
f"加购响应异常：final_url={final_url} body_head={body[:200]!r}"
|
|
)
|
|
|
|
logger.info(
|
|
"加购成功：task_id=%s item_id=%s final=%s",
|
|
task.task_id, fields["form_fields"].get("item_id"), final_url,
|
|
)
|
|
finally:
|
|
await page.close()
|
|
|
|
async def verify_cart(self, task: LeaseTask) -> None:
|
|
"""校验购物车里有没有刚加的商品
|
|
|
|
策略（探针实测最稳的两步）：
|
|
1. 打 cart count JSONP API：status=100 且 count>=1 才算「购物车非空」
|
|
2. 打开 cart 页等 SPA 渲染，在 HTML 里找 item_id
|
|
|
|
登录态失效抛 NotLoggedInError；找不到 item 抛 CartOperationError。
|
|
"""
|
|
await self._auth_session.require_logged_in("rakuten")
|
|
|
|
# 同 add_to_cart：刷新 context 以反映可能的自动重登结果
|
|
await self._refresh_context_if_stale()
|
|
|
|
per_task = self._per_task_state.get(task.task_id, {})
|
|
item_id = (task.intent or {}).get("item_id") or per_task.get("item_id")
|
|
if not item_id:
|
|
raise CartOperationError(
|
|
"无法确定 item_id：intent 未提供且 add_to_cart 未记录"
|
|
)
|
|
|
|
# 1. cart count API
|
|
resp = await self._context.request.get(
|
|
_CART_COUNT_API + "?sid=1010",
|
|
headers={"Referer": _CART_PAGE},
|
|
)
|
|
count_body = await resp.text()
|
|
status_match = re.search(r'"status"\s*:\s*"(\d+)"', count_body)
|
|
if not status_match:
|
|
raise CartOperationError(
|
|
f"cart count 响应无法解析：{count_body[:200]!r}"
|
|
)
|
|
if status_match.group(1) != "100":
|
|
raise CartOperationError(
|
|
f"cart count API 异常：status={status_match.group(1)} body={count_body[:200]!r}"
|
|
)
|
|
count_match = re.search(r'"count"\s*:\s*"(\d+)"', count_body)
|
|
count = int(count_match.group(1)) if count_match and count_match.group(1) else 0
|
|
if count == 0:
|
|
raise CartOperationError("购物车为空，加购可能未生效")
|
|
logger.info("cart count=%s task_id=%s", count, task.task_id)
|
|
|
|
# 2. 渲染 cart 页确认 item_id 在里面
|
|
page = await self._context.new_page()
|
|
try:
|
|
await page.goto(_CART_PAGE, wait_until="domcontentloaded", timeout=30_000)
|
|
# 等 SPA 把 shopUrlList / cartItem 渲染出来
|
|
try:
|
|
await page.wait_for_function(
|
|
"""() => {
|
|
const s = window.__INITIAL_STATE__;
|
|
return s && s.cart && Array.isArray(s.cart.shopUrlList) && s.cart.shopUrlList.length > 0;
|
|
}""",
|
|
timeout=15_000,
|
|
)
|
|
except Exception:
|
|
logger.warning(
|
|
"cart SPA 15s 内未渲染出 shopUrlList，继续按静态 HTML 校验：task_id=%s",
|
|
task.task_id,
|
|
)
|
|
|
|
html = await page.content()
|
|
# 旧 marker 出现一定是登录失效；新 SPA 不渲染 marker，所以这判据是单边的
|
|
if _LEGACY_LOGGED_OUT_MARKER in html:
|
|
raise NotLoggedInError(
|
|
site="rakuten",
|
|
detail="购物车页出现旧版未登录 marker",
|
|
)
|
|
if str(item_id) not in html:
|
|
raise CartOperationError(
|
|
f"购物车页未找到 item_id={item_id}（加购可能被服务端静默丢弃）"
|
|
)
|
|
logger.info(
|
|
"cart 校验通过：task_id=%s item_id=%s in cart HTML",
|
|
task.task_id, item_id,
|
|
)
|
|
finally:
|
|
await page.close()
|
|
|
|
# ---- 未实现：保留 NotImplementedError ----
|
|
|
|
async def enter_checkout(self, task: LeaseTask) -> str:
|
|
"""进入下单确认页。**未实现**：session upgrade 是硬墙"""
|
|
raise NotImplementedError(_NOT_IMPLEMENTED_MSG)
|
|
|
|
async def parse_checkout(self, html: str) -> CheckoutSummary:
|
|
"""从下单确认页解析应付金额、付款期限、订单号。**未实现**"""
|
|
raise NotImplementedError(_NOT_IMPLEMENTED_MSG)
|
|
|
|
async def submit_order(self, task: LeaseTask) -> str:
|
|
"""提交下单。**未实现**"""
|
|
raise NotImplementedError(_NOT_IMPLEMENTED_MSG)
|
|
|
|
async def pay(self, task: LeaseTask, site_order_id: str) -> None:
|
|
"""付款。**未实现**"""
|
|
raise NotImplementedError(_NOT_IMPLEMENTED_MSG)
|
|
|
|
async def monitor(self, task: LeaseTask, site_order_id: str) -> None:
|
|
"""付款后监控。**未实现**"""
|
|
raise NotImplementedError(_NOT_IMPLEMENTED_MSG)
|
|
|
|
|
|
# ---- 模块级辅助函数（纯函数，便于单测）----
|
|
|
|
|
|
def _parse_initial_state(html: str) -> dict | None:
|
|
"""从商品页 HTML 抽 window.__INITIAL_STATE__ 并解析为 dict"""
|
|
m = re.search(
|
|
r"window\.__INITIAL_STATE__\s*=\s*(.+?);\s*window\.",
|
|
html,
|
|
re.DOTALL,
|
|
)
|
|
if not m:
|
|
return None
|
|
try:
|
|
return json.loads(m.group(1))
|
|
except json.JSONDecodeError:
|
|
return None
|
|
|
|
|
|
def _extract_purchase_fields(state: dict, *, intent_override: dict | None) -> dict:
|
|
"""从 __INITIAL_STATE__ 抽加购所需字段（与 scraping/parsers/item.py 同源逻辑）
|
|
|
|
intent_override 允许调用方提供 variant_id / choice 覆盖自动选择。
|
|
"""
|
|
intent_override = intent_override or {}
|
|
purchase = state.get("purchase") or {}
|
|
sell_type = (purchase.get("sellType") or {}).get("normalPurchase") or {}
|
|
raw_sku = purchase.get("sku") or {}
|
|
item = state.get("item") or {}
|
|
shop = (state.get("shop") or {}).get("information") or {}
|
|
information = purchase.get("information") or {}
|
|
|
|
basket_domain = (sell_type.get("basketDomain") or "").replace("\\u002F", "/")
|
|
inventory_type = raw_sku.get("inventoryType")
|
|
inventory_flag = _INVENTORY_FLAG.get(inventory_type, _DEFAULT_INVENTORY_FLAG)
|
|
shop_id = shop.get("shopId")
|
|
item_id = item.get("itemId")
|
|
|
|
form_fields: dict[str, str] = {
|
|
"shop_bid": str(shop_id) if shop_id else "",
|
|
"item_id": str(item_id) if item_id else "",
|
|
"inventory_flag": inventory_flag,
|
|
"__event": _NORMAL_PURCHASE_EVENT,
|
|
}
|
|
|
|
# variant_id 选择：调用方覆盖 > 多规格自动选第一个非售罄 > 单规格用 item.variantId
|
|
chosen_variant = None
|
|
if intent_override.get("variant_id"):
|
|
form_fields["variant_id"] = str(intent_override["variant_id"])
|
|
elif inventory_flag == _INVENTORY_FLAG["multiple"]:
|
|
for v in raw_sku.get("variants") or []:
|
|
if not v.get("isSoldOut"):
|
|
chosen_variant = v
|
|
break
|
|
if chosen_variant is None and (raw_sku.get("variants") or []):
|
|
chosen_variant = raw_sku["variants"][0]
|
|
if chosen_variant:
|
|
form_fields["variant_id"] = str(
|
|
chosen_variant.get("variantId") or chosen_variant.get("id") or ""
|
|
)
|
|
elif inventory_flag == _DEFAULT_INVENTORY_FLAG and item.get("variantId"):
|
|
form_fields["variant_id"] = str(item.get("variantId"))
|
|
|
|
# 必填选项：调用方覆盖 > 自动填第一个候选值
|
|
options = information.get("options") or []
|
|
required_options = [o for o in options if o.get("isRequired")]
|
|
has_required = bool(required_options)
|
|
if intent_override.get("choice"):
|
|
# 调用方给的可能是 list 或 str
|
|
c = intent_override["choice"]
|
|
form_fields["choice"] = ",".join(c) if isinstance(c, list) else str(c)
|
|
elif has_required:
|
|
pairs: list[str] = []
|
|
for opt in required_options:
|
|
values = opt.get("values") or []
|
|
if values:
|
|
pairs.append(f"{opt.get('name')}:{values[0].get('name')}")
|
|
if pairs:
|
|
form_fields["choice"] = ",".join(pairs)
|
|
|
|
return {
|
|
"basket_domain": basket_domain,
|
|
"form_fields": form_fields,
|
|
"quantity_field": "units",
|
|
"variant_field": "variant_id",
|
|
"options_field": "choice" if options else "",
|
|
"options": options,
|
|
"has_required_options": has_required,
|
|
"inventory_flag": inventory_flag,
|
|
"purchase_condition": sell_type.get("purchaseCondition"),
|
|
"min_price": sell_type.get("minPrice"),
|
|
"shop_name": shop.get("shopName"),
|
|
"item_name": item.get("itemName"),
|
|
}
|
|
|
|
|
|
def _extract_error_message(body: str) -> str:
|
|
"""从 Rakuten 错误页 HTML 抽可读的提示文案"""
|
|
msgs: list[str] = []
|
|
for m in re.findall(r">([^<>]{20,200})<", body):
|
|
s = m.strip()
|
|
# 过滤 CSS/JS 标识与版权之类
|
|
if not s or any(c in s for c in ["(", ")", "=", "{", "}", "."]):
|
|
continue
|
|
if "Rakuten Group" in s or "SSL" in s:
|
|
continue
|
|
msgs.append(s)
|
|
# 取前两条拼起来（实测错误页一般 1~2 条核心提示）
|
|
return " / ".join(msgs[:2])
|