project/tbsg/main.py

"""
饿了么闪购 — 主入口  V1
步骤驱动，按步执行
"""
import sys
import time
import re
import cv2
import numpy as np
from pathlib import Path
from typing import Optional

sys.path.insert(0, str(Path(__file__).parent / "steps"))
from ocr import OCR
from executor import SafeExecutor
from ai_helper import AIParser

# ── 配置 ────────────────────────────────────────────────
APP_PACKAGE = "me.ele"
SCREENSHOT_DIR = Path(__file__).parent / "screenshots"
OCR = OCR()


def _find_device(device_id: str = "") -> str:
    import subprocess
    r = subprocess.run(["adb", "devices"], capture_output=True, text=True, timeout=5)
    devices = []
    for line in r.stdout.strip().split("\n")[1:]:
        if line.strip() and "device" in line and "offline" not in line:
            s = line.split("\t")[0].strip()
            if s:
                devices.append(s)

    if not devices:
        raise RuntimeError("未找到设备")

    # 如果指定了设备ID，精确匹配
    if device_id:
        for d in devices:
            if d == device_id:
                return d
        raise RuntimeError(f"未找到指定设备: {device_id}，可用设备: {devices}")

    # 只有一台直接返回
    if len(devices) == 1:
        return devices[0]

    # 多台设备：列出并让用户选择
    print(f"\n发现 {len(devices)} 台设备:")
    for i, d in enumerate(devices):
        print(f"  [{i}] {d}")
    while True:
        try:
            choice = input(f"请选择设备 [0-{len(devices)-1}]，回车默认第一台: ").strip()
            if choice == "":
                return devices[0]
            idx = int(choice)
            if 0 <= idx < len(devices):
                return devices[idx]
        except ValueError:
            pass
        print(f"输入无效，请输入 0-{len(devices)-1}")


def _find_text_in_area(shot_path: str, target: str, max_y: int) -> Optional[dict]:
    results = OCR.recognize(shot_path, detail="all")
    for r in results:
        if target in r["text"]:
            y = r["bbox"][0][1]
            if y < max_y:
                cx = r["bbox"][0][0] + (r["bbox"][2][0] - r["bbox"][0][0]) // 2
                cy = y + (r["bbox"][2][1] - y) // 2
                return {"x": cx, "y": cy, "text": r["text"], "conf": r["confidence"]}
    return None


def _screenshot(ex: SafeExecutor, name: str) -> str:
    import os
    SCREENSHOT_DIR.mkdir(exist_ok=True)
    path = str(SCREENSHOT_DIR / name)
    if os.path.exists(path):
        # 保留历史截图副本：固定文件名被 test/调试脚本引用，不能被后续运行覆盖丢失
        import shutil
        stem, ext = os.path.splitext(name)
        backup = str(SCREENSHOT_DIR / f"{stem}_{int(time.time() * 1000)}{ext}")
        try:
            shutil.copy2(path, backup)
        except Exception:
            pass
    ex.driver.screenshot(path)
    return path


def _is_search_page(ex: SafeExecutor) -> bool:
    """判断当前是否在搜索页面：只检测屏幕顶部20%区域内是否有「筛选」"""
    import tempfile
    w, h = ex.driver.window_size()
    tmp = str(SCREENSHOT_DIR / "_check_search.png")
    ex.driver.screenshot(tmp)
    texts = OCR.recognize(tmp, rect=[0, 0, w, int(h * 0.2)], detail="text")
    return "筛选" in texts


# ── 步骤 1：打开 App ────────────────────────────────────

def step1_open_app(ex: SafeExecutor) -> bool:
    print("=" * 40)
    print("  步骤 1：打开饿了么闪购")
    print("=" * 40)
    w, h = ex.driver.window_size()
    print(f"[step1] 屏幕尺寸: {w}x{h}")

    print(f"[step1] 关闭 {APP_PACKAGE}...")
    ex.driver.app_stop(APP_PACKAGE)
    time.sleep(2)

    print(f"[step1] 启动 {APP_PACKAGE}...")
    ex.driver.app_start(APP_PACKAGE)
    time.sleep(5)

    shot = _screenshot(ex, "step1_home.png")
    texts = OCR.recognize(shot, rect=[0, int(h * 0.88), w, h], detail="text")
    print(f"[step1] 底部识别: {texts}")

    for t in texts:
        if "我的" in t:
            print("[step1] OK - 成功进入 App")
            return True
    print("[step1] FAIL - 未检测到「我的」")
    return False


# ── 步骤 2：搜索商品 ────────────────────────────────────

def step2_search(ex: SafeExecutor, keyword: str) -> bool:
    print("\n" + "=" * 40)
    print(f"  步骤 2：搜索「{keyword}」")
    print("=" * 40)
    w, h = ex.driver.window_size()
    top_th = int(h * 0.3)

    # ── 阶段0：点击「看病买药」 ──
    shot0 = _screenshot(ex, "step2_phase0.png")
    btn_med = _find_text_in_area(shot0, "看病买药", h)
    if not btn_med:
        print("[step2] FAIL - 未找到「看病买药」")
        return False
    print(f"[step2] 找到「看病买药」: ({btn_med['x']}, {btn_med['y']})")
    ex.tap(btn_med["x"], btn_med["y"])
    time.sleep(3)

    # ── 阶段1：点击首页搜索栏 ──
    shot = _screenshot(ex, "step2_phase1.png")
    btn = _find_text_in_area(shot, "搜索", top_th)
    if not btn:
        print("[step2] FAIL - 未找到「搜索」")
        return False
    print(f"[step2] 找到「搜索」: ({btn['x']}, {btn['y']})")

    cx = btn["x"] - 120  # 搜索左边约120px
    cy = btn["y"]
    ex.tap(cx, cy)
    time.sleep(3)

    shot2 = _screenshot(ex, "step2_phase2.png")
    btn2 = _find_text_in_area(shot2, "搜索", top_th)
    if not btn2:
        print("[step2] FAIL - 进入搜索页后找不到「搜索」")
        return False
    moved = abs(btn2["x"] - btn["x"]) > 50 or abs(btn2["y"] - btn["y"]) > 50
    if not moved:
        print("[step2] FAIL - 搜索位置未改变")
        return False
    print(f"[step2] 搜索页搜索: ({btn2['x']}, {btn2['y']})")

    cx2 = btn2["x"] - 180  # 搜索页输入框在搜索左边约180px
    cy2 = btn2["y"]
    ex.tap(cx2, cy2)
    time.sleep(2)
    print(f"[step2] 聚焦输入框，等待2s")

    print(f"[step2] 输入关键词: {keyword}")
    ex.driver.set_input_ime(True)
    time.sleep(0.3)
    ex.driver.send_keys(keyword)
    time.sleep(1)

    ex.tap(btn2["x"], btn2["y"])
    time.sleep(3)

    shot3 = _screenshot(ex, "step2_result.png")
    raw3 = OCR.recognize(shot3, detail="all")
    all_texts = [r["text"] for r in raw3]
    has_filter = "筛选" in all_texts
    has_express = "快递" in all_texts
    kw_found = any(keyword in t for t in all_texts)

    print(f"[step2] 有筛选: {has_filter}, 有快递: {has_express}, 关键词存在: {kw_found}")

    # 如果有「快递」则点击它
    if has_express:
        for r in raw3:
            if "快递" in r["text"]:
                bx = r["bbox"]
                cx = (bx[0][0] + bx[2][0]) // 2
                cy = (bx[0][1] + bx[2][1]) // 2
                print(f"[step2] 点击「快递」: ({cx}, {cy})")
                ex.tap(cx, cy)
                time.sleep(3)
                break

    if has_filter or has_express:
        print("[step2] OK - 搜索成功")
        return True

    print("[step2] FAIL - 搜索未成功")
    return False


def _adb_swipe_up(ex: SafeExecutor, distance: int):
    """ADB 手指从下往上滑，内容下滑"""
    import subprocess
    w, h = ex.driver.window_size()
    swipe_x = w // 2
    seg = 3
    seg_px = distance // seg
    for i in range(seg):
        s = int(h * 0.8) - i * 80
        e = s - seg_px
        if e < 50:
            e = 50
        subprocess.run(
            ["adb", "-s", ex.device_id, "shell", "input", "swipe",
             str(swipe_x), str(s), str(swipe_x), str(e), "400"],
            capture_output=True, timeout=10
        )
        time.sleep(0.35)
    time.sleep(1.4)


def _get_named_shops(ex: SafeExecutor, shot_name: str) -> list:
    """截图 + OCR + AI → 返回有店铺名的列表"""
    shot = _screenshot(ex, shot_name)
    raw = OCR.recognize(shot, detail="all")
    w, h = ex.driver.window_size()
    parser = AIParser()
    shops = parser.parse_shops(raw, screen_size=(w, h))
    # 只保留有效店铺名+价格：店铺名必须含中文或字母（排除纯数字/标点/空格）
    import re as _re
    valid = []
    for s in shops:
        name = (s[0] or "").strip()
        price = (s[2] or "").strip()
        if name and _re.search(r'[一-鿿＀-￯a-zA-Z]', name) and price:
            valid.append(s)
    return valid


def _shop_key(shop: list) -> str:
    """用店铺名+价格去重（去括号内分店名、去尾部点号）"""
    import re
    name = shop[0]
    price = shop[2] if len(shop) > 2 else ""
    name = name.replace("(", "（").replace(")", "）")
    name = re.sub(r'（.*', '', name)
    name = re.sub(r'[.．…]+$', '', name)
    return f"{name.strip()}|{price.strip()}"


def _visit_shop(ex: SafeExecutor, shop: list, visited: set) -> dict:
    """点击进入店铺 → step4 → 返回完整数据 dict"""
    key = _shop_key(shop)
    if key in visited:
        return None

    visited.add(key)
    shop_name = shop[0]
    product_title = shop[1]
    price = shop[2]
    click_x, click_y = shop[3]
    print(f"  → 进入 [{shop_name}] 商品: {product_title[:30]}  价格: {price}")

    ex.tap(click_x, click_y)

    try:
        qr_url = step4_parse_qr(ex, product_title, shop_name)
    except Exception as e:
        print(f"    ⚠ step4异常: {e}，跳过此店铺")
        qr_url = ""

    if qr_url == "__TERMINATE__":
        print(f"    ⚠ 遇到终止信号，停止遍历")
        return {"__terminate__": True}

    if qr_url:
        print(f"    ✅ QR: {qr_url[:80]}")
        print(f"    📦 采集完成: {shop_name} | {product_title[:30]} | {price} | {qr_url[:60]}")
    else:
        print(f"    ⚠ 未获取到二维码链接")
        print(f"    📦 采集完成(无链接): {shop_name} | {product_title[:30]} | {price}")

    # 返回搜索页：最多退3次，每次检测顶部区域是否有「筛选」
    for _ in range(3):
        ex.driver.press("back")
        time.sleep(1.4)
        if _is_search_page(ex):
            break

    return {
        "shop": shop_name,
        "title": product_title,
        "price": price,
        "link": qr_url or "",
    }


def _handle_captcha(ex: SafeExecutor, ocr_texts: list) -> bool:
    """处理验证码, 重试5次, 失败等人工, 返回True=已解决"""
    import sys as _sys
    _sys.path.insert(0, str(Path(__file__).parent / "yzm"))

    for attempt in range(1, 6):
        print(f"    [验证码] 第{attempt}次尝试...")
        nine_kw = any("提交" in t or "没有新图片" in t for t in ocr_texts)
        if nine_kw:
            from nine_grid import solve as solve_nine
            ok = solve_nine(ex.driver)
        else:
            from tmp_captcha_test2 import solve_slider
            ok = solve_slider(ex.driver)
        if ok:
            print(f"    ✅ 验证码已解决")
            return True
        print(f"    ❌ 第{attempt}次失败")
        time.sleep(1)

    print(f"    ⚠ 5次自动处理失败, 请人工处理...")
    input("    处理完成后按回车继续...")
    return True


def step4_parse_qr(ex: SafeExecutor, product_title: str, shop_name: str = "") -> str:
    """
    1. 等待加载 → OCR → AI找商品标题坐标
    2. 点击商品标题 → 进入商品详情
    3. 找右上角"分享" → 点击 → 二维码弹窗
    4. 截图 → pyzbar 解析二维码
    返回 URL 或空字符串
    """
    # 安全的文件名前缀（用hash避免中文路径cv2兼容问题）
    import hashlib
    _hash = hashlib.md5(shop_name.encode()).hexdigest()[:8] if shop_name else "unknown"
    _pfx = lambda name: str(SCREENSHOT_DIR / f"_s4_{_hash}_{name}")

    time.sleep(6)

    # ── 检测页面类型：验证码/风控/正常（unknown/qrcode 重试3次）──
    for page_retry in range(3):
        shot_check = _pfx("page_check.png")
        ex.driver.screenshot(shot_check)
        check_raw = OCR.recognize(shot_check, detail="all")

        # 方法A: 模板匹配检测验证码
        import os as _os
        captcha_tpl = str(Path(__file__).parent / "files" / "captcha1.png")
        if _os.path.exists(captcha_tpl):
            si = cv2.imread(shot_check)
            ti = cv2.imread(captcha_tpl)
            if si is not None and ti is not None:
                gs = cv2.cvtColor(si, cv2.COLOR_BGR2GRAY)
                gt = cv2.cvtColor(ti, cv2.COLOR_BGR2GRAY)
                h_s, w_s = gs.shape
                crop_y1, crop_y2 = int(h_s * 0.25), int(h_s * 0.75)
                crop_x1, crop_x2 = 0, 400
                gs_crop = gs[crop_y1:crop_y2, crop_x1:crop_x2]
                scores = []
                for fn, ss, tt in [
                    ("gray", gs_crop, gt),
                    ("edge", cv2.Canny(gs_crop,30,100), cv2.Canny(gt,30,100)),
                    ("hist", cv2.equalizeHist(gs_crop), cv2.equalizeHist(gt)),
                    ("blur", cv2.GaussianBlur(gs_crop,(3,3),0), cv2.GaussianBlur(gt,(3,3),0)),
                    ("otsu", cv2.threshold(gs_crop,0,255,cv2.THRESH_BINARY+cv2.THRESH_OTSU)[1],
                            cv2.threshold(gt,0,255,cv2.THRESH_BINARY+cv2.THRESH_OTSU)[1]),
                ]:
                    if ss.ndim == 2 and tt.ndim == 2 and ss.shape[0] >= tt.shape[0] and ss.shape[1] >= tt.shape[1]:
                        r = cv2.matchTemplate(ss, tt, cv2.TM_CCOEFF_NORMED)
                        _, mv, _, _ = cv2.minMaxLoc(r)
                        scores.append((mv, fn))
                if scores:
                    best_v = max(s[0] for s in scores)
                    best_m = max(scores, key=lambda s: s[0])[1]
                    print(f"    验证码模板匹配: {best_m}={best_v:.3f}")
                    captcha_kw = any("拖动滑块" in r["text"] or "请按住滑块" in r["text"] or "安全验证" in r["text"] for r in check_raw)
                    nine_kw = any("提交" in r["text"] or "没有新图片" in r["text"] for r in check_raw)
                    if best_v >= 0.30 and (captcha_kw or nine_kw):
                        print(f"    ⚠ 检测到验证码，尝试自动处理...")
                        if _handle_captcha(ex, [r["text"] for r in check_raw]):
                            continue
                        return "__TERMINATE__"
                    elif best_v >= 0.30 and not captcha_kw:
                        print(f"    ⚠ 模板匹配命中但OCR无验证码关键词，忽略")
        page_type = AIParser().check_page(check_raw)
        ptype = page_type.get("type", "unknown")

        if ptype == "risk":
            print(f"    ⚠ AI检测到验证码，尝试自动处理...")
            if _handle_captcha(ex, [r["text"] for r in check_raw]):
                continue
            return "__TERMINATE__"

        if ptype == "normal":
            break  # 正常，跳出重试循环

        # qrcode 或 unknown → 可能未加载完成
        if page_retry < 2:
            print(f"    检测到{ptype}页面，可能未加载完成，第{page_retry+1}次重试...")
            time.sleep(2)
    else:
        # 3次重试后仍异常
        import shutil
        err_dir = SCREENSHOT_DIR / "unrecognized"
        err_dir.mkdir(exist_ok=True)
        shutil.copy(shot_check, str(err_dir / f"{ptype}_{int(time.time())}.png"))
        print(f"    ⚠ 3次检测均为{ptype}页面，终止程序")
        return "__TERMINATE__"
    # normal → 继续

    # ── 店铺页判断：OCR同时检测到「刚刚搜过」和「评价」说明在店铺页 ──
    in_shop = False
    for _ in range(10):
        shop_check = _pfx("shop_check.png")
        ex.driver.screenshot(shop_check)
        shop_raw = OCR.recognize(shop_check, detail="text")
        has_ganggang = any("刚刚搜过" in t for t in shop_raw)
        has_pingjia = any("评价" in t for t in shop_raw)
        if has_ganggang and has_pingjia:
            in_shop = True
            print(f"    已确认在店铺页")
            break
        time.sleep(1)
    if not in_shop:
        print(f"    ⚠ 未检测到店铺页，继续尝试...")

    # ── 第1步：截图 + AI找商品标题坐标 ──
    shot = _pfx("shop.png")
    ex.driver.screenshot(shot)
    raw = OCR.recognize(shot, detail="all")

    sorted_r = sorted(raw, key=lambda r: r["bbox"][0][1])
    lines = []
    for r in sorted_r:
        cx = (r["bbox"][0][0] + r["bbox"][2][0]) // 2
        cy = (r["bbox"][0][1] + r["bbox"][2][1]) // 2
        lines.append(f"[x={cx:4d}, y={cy:4d}] {r['text']}")
    ocr_text = "\n".join(lines)

    system_prompt = """你收到店铺页的OCR文字。商品标题文字坐标已知(从OCR中有x,y)。
请找到和以下商品标题匹配的文字块，返回其点击坐标。

【重要规则】
- 坐标必须从OCR数据中选取，不得编造或估算
- 如果找不到完全匹配的，找最相似的
- 如果完全找不到，返回null

只返回JSON：
{"title_xy": [x, y] 或 null, "shop": "店铺名"}"""

    parser = AIParser()
    resp = parser._call(system_prompt, f"商品标题: {product_title}\n\nOCR文字：\n{ocr_text}\n\n请返回商品标题坐标。")

    import json
    cleaned = resp.strip()
    if cleaned.startswith("```"):
        cl = cleaned.split("\n")
        if cl[0].startswith("```"): cl = cl[1:]
        if cl and cl[-1].strip() == "```": cl = cl[:-1]
        cleaned = "\n".join(cl).strip()
    try:
        data = json.loads(cleaned)
        title_xy = data.get("title_xy")
    except json.JSONDecodeError:
        title_xy = None

    if not title_xy or not isinstance(title_xy, list) or len(title_xy) != 2:
        print(f"    ⚠ AI未返回有效坐标: {title_xy}")
        return ""

    tx, ty = title_xy
    if tx is None or ty is None:
        print(f"    ⚠ AI返回空坐标")
        return ""

    tx, ty = int(tx), int(ty)
    w, h = ex.driver.window_size()
    if not (0 <= tx <= w and 0 <= ty <= h):
        print(f"    ⚠ 坐标越界: ({tx},{ty}) 超出屏幕 {w}x{h}")
        return ""

    # ── 第2步：点击商品标题 → 进入商品详情（最多重试3次）──
    entered_detail = False
    for attempt in range(3):
        print(f"    点击商品标题: ({tx},{ty}) (第{attempt+1}次)")
        ex.tap(tx, ty)

        # 检测是否进入商品详情页
        for _ in range(5):
            time.sleep(2)
            detail_check = _pfx("detail_check.png")
            ex.driver.screenshot(detail_check)
            detail_raw = OCR.recognize(detail_check, detail="all")
            detail_texts = [r["text"] for r in detail_raw]

            # 检测商品详情页关键词
            if any("加入购物车" in t or "立即购买" in t or "选规格" in t or "商品详情页" in t for t in detail_texts):
                print(f"    已进入商品详情页")
                entered_detail = True
                break

            # 检测验证码页面
            captcha_kw = any("拖动滑块" in t or "请按住滑块" in t or "安全验证" in t for t in detail_texts)
            captcha_tpl = str(Path(__file__).parent / "files" / "captcha1.png")
            tpl_match = False
            if _os.path.exists(captcha_tpl):
                si = cv2.imread(detail_check)
                ti = cv2.imread(captcha_tpl)
                if si is not None and ti is not None:
                    gs = cv2.cvtColor(si, cv2.COLOR_BGR2GRAY)
                    gt = cv2.cvtColor(ti, cv2.COLOR_BGR2GRAY)
                    h_s, w_s = gs.shape
                    crop_y1, crop_y2 = int(h_s * 0.25), int(h_s * 0.75)
                    gs_crop = gs[crop_y1:crop_y2, 0:400]
                    best_v = 0
                    for fn, ss, tt in [
                        ("gray", gs_crop, gt),
                        ("edge", cv2.Canny(gs_crop,30,100), cv2.Canny(gt,30,100)),
                        ("hist", cv2.equalizeHist(gs_crop), cv2.equalizeHist(gt)),
                        ("blur", cv2.GaussianBlur(gs_crop,(3,3),0), cv2.GaussianBlur(gt,(3,3),0)),
                        ("otsu", cv2.threshold(gs_crop,0,255,cv2.THRESH_BINARY+cv2.THRESH_OTSU)[1],
                                cv2.threshold(gt,0,255,cv2.THRESH_BINARY+cv2.THRESH_OTSU)[1]),
                    ]:
                        if ss.ndim == 2 and tt.ndim == 2 and ss.shape[0] >= tt.shape[0] and ss.shape[1] >= tt.shape[1]:
                            r = cv2.matchTemplate(ss, tt, cv2.TM_CCOEFF_NORMED)
                            _, mv, _, _ = cv2.minMaxLoc(r)
                            best_v = max(best_v, mv)
                    tpl_match = best_v >= 0.30
            if captcha_kw or tpl_match:
                print(f"    ⚠ 检测到验证码页面，尝试自动处理...")
                if _handle_captcha(ex, detail_texts):
                    continue
                return "__TERMINATE__"

            # 不在详情页，检测是否还在店铺页
            has_ganggang = any("刚刚搜过" in t for t in detail_texts)
            has_pingjia = any("评价" in t for t in detail_texts)
            if has_ganggang and has_pingjia:
                print(f"    仍在店铺页，重试...")
                break  # 跳出内层循环

        if entered_detail:
            break

        # 第1次失败后，重新OCR+AI获取坐标（可能是页面滚动导致坐标偏移）
        if attempt < 2:
            print(f"    重新OCR获取坐标...")
            re_shot = _pfx("shop.png")
            ex.driver.screenshot(re_shot)
            re_raw = OCR.recognize(re_shot, detail="all")
            re_sorted = sorted(re_raw, key=lambda r: r["bbox"][0][1])
            re_lines = []
            for r in re_sorted:
                r_cx = (r["bbox"][0][0] + r["bbox"][2][0]) // 2
                r_cy = (r["bbox"][0][1] + r["bbox"][2][1]) // 2
                re_lines.append(f"[x={r_cx:4d}, y={r_cy:4d}] {r['text']}")
            re_ocr_text = "\n".join(re_lines)
            re_resp = parser._call(system_prompt, f"商品标题: {product_title}\n\nOCR文字：\n{re_ocr_text}\n\n请返回商品标题坐标。")
            re_cleaned = re_resp.strip()
            if re_cleaned.startswith("```"):
                rl = re_cleaned.split("\n")
                if rl[0].startswith("```"): rl = rl[1:]
                if rl and rl[-1].strip() == "```": rl = rl[:-1]
                re_cleaned = "\n".join(rl).strip()
            try:
                re_data = json.loads(re_cleaned)
                re_xy = re_data.get("title_xy")
                if re_xy and isinstance(re_xy, list) and len(re_xy) == 2 and re_xy[0] is not None:
                    tx, ty = int(re_xy[0]), int(re_xy[1])
                    ww, hh = ex.driver.window_size()
                    if not (0 <= tx <= ww and 0 <= ty <= hh):
                        print(f"    ⚠ 新坐标越界: ({tx},{ty})，保持原坐标")
                    else:
                        print(f"    新坐标: ({tx},{ty})")
            except Exception:
                pass
    else:
        pass  # 3次重试结束

    if not entered_detail:
        print(f"    ⚠ 3次点击未进入商品详情页，跳过")
        return ""

    # ── 第3步：ORB特征匹配找分享图标 ──
    share_shot = _pfx("find_share.png")
    ex.driver.screenshot(share_shot)
    screen = cv2.imread(share_shot)
    template_path = str(Path(__file__).parent / "files" / "share.png")
    template = cv2.imread(template_path)
    sx, sy = None, None

    if screen is not None and template is not None:
        h_s, w_s = screen.shape[:2]

        # 右上角区域（分享图标永远在右上）
        roi_x1, roi_y1 = w_s * 2 // 3, 0
        roi = screen[roi_y1:h_s // 4, roi_x1:w_s]

        # 方法A: SIFT 特征匹配（限制右上角区域，减少干扰）
        sx, sy = None, None
        sift = cv2.SIFT_create(nfeatures=1500)
        kp1, des1 = sift.detectAndCompute(template, None)
        kp2, des2 = sift.detectAndCompute(roi, None)

        if des1 is not None and des2 is not None and len(kp1) >= 2 and len(kp2) >= 2:
            bf = cv2.BFMatcher()
            matches = bf.knnMatch(des1, des2, k=2)
            good = []
            for m, n in matches:
                if m.distance < 0.75 * n.distance:
                    good.append(m)
            print(f"    分享SIFT(右上区域): 模板{len(kp1)}特征 ROI{len(kp2)}特征 优质{len(good)}")
            if len(good) >= 4:
                src_pts = np.float32([kp1[m.queryIdx].pt for m in good]).reshape(-1, 1, 2)
                dst_pts = np.float32([kp2[m.trainIdx].pt for m in good]).reshape(-1, 1, 2)
                matrix, _ = cv2.findHomography(src_pts, dst_pts, cv2.RANSAC, 5.0)
                if matrix is not None:
                    h_t, w_t = template.shape[:2]
                    corners = np.float32([[0, 0], [w_t, 0], [w_t, h_t], [0, h_t]]).reshape(-1, 1, 2)
                    transformed = cv2.perspectiveTransform(corners, matrix)
                    sx = roi_x1 + int(np.mean(transformed[:, 0, 0]))
                    sy = int(np.mean(transformed[:, 0, 1]))
                    print(f"    分享SIFT匹配: ({sx},{sy})")

        # 方法B: 多尺度模板匹配（右上角区域）
        if sx is None:
            best_val, best_loc, best_sw, best_sh = 0, None, 0, 0
            for scale in [0.7, 0.8, 0.9, 1.0, 1.1, 1.2, 1.3]:
                scaled = cv2.resize(template, None, fx=scale, fy=scale)
                sw, sh = scaled.shape[1], scaled.shape[0]
                if sh > roi.shape[0] or sw > roi.shape[1]:
                    continue
                res = cv2.matchTemplate(roi, scaled, cv2.TM_CCOEFF_NORMED)
                _, mv, _, ml = cv2.minMaxLoc(res)
                if mv > best_val:
                    best_val, best_loc, best_sw, best_sh = mv, ml, sw, sh
                t_edge = cv2.Canny(scaled, 30, 100)
                r_edge = cv2.Canny(roi, 30, 100)
                if t_edge.shape[0] <= r_edge.shape[0] and t_edge.shape[1] <= r_edge.shape[1]:
                    res2 = cv2.matchTemplate(r_edge, t_edge, cv2.TM_CCOEFF_NORMED)
                    _, mv2, _, ml2 = cv2.minMaxLoc(res2)
                    if mv2 > best_val:
                        best_val, best_loc, best_sw, best_sh = mv2, ml2, sw, sh
            print(f"    分享模板匹配(右上): 最佳={best_val:.3f}")
            if best_val >= 0.26 and best_loc is not None:
                sx = roi_x1 + best_loc[0] + best_sw // 2
                sy = best_loc[1] + best_sh // 2

        if sx is not None and sy is not None:
            print(f"    分享图标: ({sx},{sy})")
            ex.tap(sx, sy)
        else:
            print(f"    ⚠ 未找到分享图标")
            return ""

    # 等弹窗出现，同时记录"分享到"y坐标用于QR裁剪
    share_y = None
    waimai_y = None
    for _ in range(8):
        time.sleep(1)
        ck = _pfx("share_popup.png")
        ex.driver.screenshot(ck)
        detail = OCR.recognize(ck, detail="all")
        texts = [r["text"] for r in detail]
        if any("分享到" in t for t in texts):
            print(f"    分享弹窗出现")
            # 记录"分享到"和"外卖"的y坐标
            for r in detail:
                cy = (r["bbox"][0][1] + r["bbox"][2][1]) // 2
                if "分享到" in r["text"] and share_y is None:
                    share_y = cy
                if "外卖" in r["text"] and waimai_y is None:
                    waimai_y = cy
            break
    if share_y is None:
        share_y = int(ex.driver.window_size()[1] * 0.74)  # fallback

    # ── 第4步：截图 → 多方法解析二维码（多次重试） ──
    def _decode_qr(img, share_y):
        """基于OCR定位的share_y裁剪QR区域解析"""
        if img is None: return ""
        h, w = img.shape[:2]
        gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
        detector = cv2.QRCodeDetector()

        # 裁剪区域：y从"外卖"(或估计值)到"分享到", x从60%到92%
        y_top = waimai_y if waimai_y else max(0, share_y - 280)
        y_bot = share_y
        x_l, x_r = int(w * 0.60), int(w * 0.92)
        crop_save = img[y_top:y_bot, x_l:x_r]
        cv2.imwrite(_pfx("qr_crop.png"), crop_save)

        def _try_decode(roi_gray, zooms=(1,)):
            """在灰度图上尝试多种方式解码"""
            if roi_gray is None or roi_gray.size == 0 or roi_gray.shape[0] == 0 or roi_gray.shape[1] == 0:
                return ""
            for z in zooms:
                if z > 1:
                    big = cv2.resize(roi_gray, None, fx=z, fy=z, interpolation=cv2.INTER_NEAREST)
                else:
                    big = roi_gray
                data, _, _ = detector.detectAndDecode(big)
                if data: return data
            # OTSU + zoom
            for z in zooms:
                _, th = cv2.threshold(roi_gray, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)
                big = cv2.resize(th, None, fx=z, fy=z, interpolation=cv2.INTER_NEAREST) if z > 1 else th
                data, _, _ = detector.detectAndDecode(big)
                if data: return data
            return ""

        # 方法A: 全图detect定位QR → 裁200x200
        ok, points = detector.detect(gray)
        if ok and points is not None and len(points) > 0:
            pts = points[0].astype(int)
            cx = int(np.mean(pts[:, 0]))
            cy = int(np.mean(pts[:, 1]))
            x1, y1 = max(0, cx - 100), max(0, cy - 100)
            x2, y2 = min(w, cx + 100), min(h, cy + 100)
            if x2 > x1 and y2 > y1:
                data = _try_decode(gray[y1:y2, x1:x2], (1, 2, 3))
                if data: return data
        # 方法B: 200x200滑动窗口扫描（基于OCR定位区域）
        scan_area = gray[y_top:y_bot, x_l:x_r]
        sh, sw = scan_area.shape
        step = min(80, max(40, sh // 3, sw // 3))
        for y in range(0, max(1, sh - 200), step):
            for x in range(0, max(1, sw - 200), step):
                patch = scan_area[y:y+200, x:x+200]
                data = _try_decode(patch, (1, 2))
                if data: return data

        # 方法C: 固定区域 fallback（基于OCR定位）
        crop = gray[y_top:y_bot, x_l:x_r]
        data = _try_decode(crop, (1, 2, 3, 4))
        if data: return data

        # 方法D: 全图兜底（裁剪失败时直接在全图上尝试）
        data = _try_decode(gray, (1, 2, 3))
        if data: return data

        # 方法E: 全图 OTSU + 放大
        _, full_th = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)
        for z in (1, 2, 3):
            big = cv2.resize(full_th, None, fx=z, fy=z, interpolation=cv2.INTER_CUBIC) if z > 1 else full_th
            data, _, _ = detector.detectAndDecode(big)
            if data: return data

        return ""

    for retry in range(6):  # 最多等 5+2*5=15秒
        time.sleep(5 if retry == 0 else 2)
        qr_shot = _pfx("qr.png")
        ex.driver.screenshot(qr_shot)
        data = _decode_qr(cv2.imread(qr_shot), share_y)
        if data:
            print(f"    QR链接: {data[:100]}")
            return data

    return ""


# ── 步骤 3：滑动 + 逐个点击店铺 ──────────────────────

def step3_swipe_and_enter(ex: SafeExecutor, keyword: str) -> list:
    """
    截图 → AI分析 → 逐个点击全部可见店铺 → 下滑加载更多 → 继续点击 → 直到全部遍历
    """
    print("\n" + "=" * 40)
    print("  步骤 3：遍历店铺")
    print("=" * 40)

    visited = set()
    w, h = ex.driver.window_size()
    batch_no = 0
    empty_streak = 0  # 连续没有新店铺的批次数
    all_results = []

    while True:
        named = _get_named_shops(ex, f"step3_b{batch_no}.png")

        new_ones = [s for s in named if _shop_key(s) not in visited]

        print(f"[step3] 批次{batch_no}: 共{len(named)}个, 新{len(new_ones)}个")

        if not new_ones:
            empty_streak += 1
            print(f"[step3] 无新店铺 (连续{empty_streak}/3)")
            if empty_streak >= 3:
                print(f"[step3] 连续3批无新店铺，结束")
                break
            # 滑动后再试
            print(f"[step3] 滑动查看下一批")
            if len(named) >= 2:
                target_y = named[-2][4]
                swipe_dist = target_y - int(h * 0.15)
                if swipe_dist > 0:
                    _adb_swipe_up(ex, swipe_dist)
                else:
                    _adb_swipe_up(ex, int(h * 0.15))
            else:
                _adb_swipe_up(ex, int(h * 0.3))
            time.sleep(2)
            batch_no += 1
            continue

        empty_streak = 0  # 有新店铺，重置计数

        for shop in new_ones:
            result = _visit_shop(ex, shop, visited)
            if result and result.get("__terminate__"):
                print("[step3] 收到终止信号，停止遍历")
                all_results = [r for r in all_results if not r.get("__terminate__")]
                break
            if result:
                all_results.append(result)
        else:
            # for 正常结束 → 滑动到倒数第二个卡片的配送距离位置
            print(f"[step3] 已访问 {len(visited)} 个，滑动查看下一批")
            if len(named) >= 2:
                target_y = named[-2][4]  # 倒数第二个卡片的配送距离y坐标
                swipe_dist = target_y - int(h * 0.15)
                if swipe_dist > 0:
                    _adb_swipe_up(ex, swipe_dist)
                else:
                    _adb_swipe_up(ex, int(h * 0.15))
            else:
                _adb_swipe_up(ex, int(h * 0.3))
            time.sleep(2)
            batch_no += 1
            continue
        # break 出来 → 结束
        break

    # ── 输出最终结果表 ──
    print("\n" + "=" * 70)
    print(f"  最终结果 ({len(all_results)} 个店铺)")
    print("=" * 70)
    for i, r in enumerate(all_results, 1):
        link_short = r["link"][:55] + "..." if len(r["link"]) > 55 else r["link"]
        print(f"  [{i}] {r['shop']}")
        print(f"      商品: {r['title'][:40]}")
        print(f"      价格: {r['price']}")
        print(f"      链接: {link_short}")
        print()

    return all_results


# ── 步骤 4：（保留，当前为空 ──────────────────────────

def step4_empty(ex: SafeExecutor):
    """占位，供后续扩展"""
    pass


# ── 主入口 ──────────────────────────────────────────────

if __name__ == "__main__":
    args = sys.argv[1:]
    device_id = "T4VK4LM7AAUOV8AY"
    # 解析 --device 参数
    filtered = []
    i = 0
    while i < len(args):
        if args[i] == "--device" and i + 1 < len(args):
            device_id = args[i + 1]
            i += 2
        else:
            filtered.append(args[i])
            i += 1

    cmd = filtered[0] if filtered else "all"
    keyword = filtered[1] if len(filtered) > 1 else "矿泉水"

    print("设备连接中...")
    device_id = _find_device(device_id)
    print(f"设备: {device_id}")
    ex = SafeExecutor(device_id)

    if cmd in ("all", "step1"):
        ok = step1_open_app(ex)
        if not ok:
            sys.exit(1)

    if cmd in ("all", "step2"):
        ok = step2_search(ex, keyword)
        if not ok:
            sys.exit(1)

    if cmd in ("all", "step3"):
        visited = step3_swipe_and_enter(ex, keyword)
        print(f"\n最终访问: {visited}")
        sys.exit(0)

    if cmd in ("all", "step4"):
        # step4 需要先跑完 step3 获取所有商品标题，单独跑时需要手动传标题
        title = keyword
        link = step4_parse_qr(ex, title)
        print(f"\n链接: {link}")
        sys.exit(0)

    sys.exit(0)