aiData/Apps/AiTeJiYiChong/Crawler.py

# coding=utf-8
import asyncio
import logging
import uuid
import os
import sys
import time
from PIL import Image

# 将项目根目录添加到 sys.path
project_root = os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
if project_root not in sys.path:
    sys.path.append(project_root)

import uiautomator2 as u2
from Apps.AiTeJiYiChong import Kit
from Apps.AiTeJiYiChong.Kit import take_screenshot
from Apps.AiTeJiYiChong.ReadImageKit import ReadImageKit
from Util.RedisKit import RedisKit
from Apps.AiTeJiYiChong.Service import AiTeJiYiChongService
from Config.Config import TEMP_IMAGE_DIR
from Apps.AiTeJiYiChong.Config.Setting import (
    SCROLL_DISTANCE_RATIO,
    MAX_SCROLLS, REDIS_STATION_EXPIRE,
    WAIT_AFTER_SCROLL,
    MAX_CRAWL_DISTANCE
)

logger = logging.getLogger("AiTeJiYiChongCrawler")

async def get_station_list(d, service, max_scrolls=MAX_SCROLLS):
    """
    获取场站列表并处理翻页
    """
    redis_kit = RedisKit()
    window_size = d.window_size()
    w, h = window_size[0], window_size[1]
    
    device_info = d.info
    device_info['width'] = w
    device_info['height'] = h

    logger.info(f"开始爬取列表，设备: {device_info.get('productName')} | 分辨率: {w}x{h}")

    for i in range(max_scrolls + 1):
        logger.info(f"正在处理第 {i + 1} 页...")

        # 1. 拍摄截图
        image_uuid = str(uuid.uuid4())
        screenshot_path = take_screenshot(d, image_uuid, save_dir=TEMP_IMAGE_DIR)
        logger.info(f"列表页截图已完成: {screenshot_path}")

        # 2. 执行图形学分析，生成 _flag.jpg, _vl.jpg 和 .json
        logger.info("正在执行图形学切片分析...")
        json_data = Kit.crop_cards_from_image(screenshot_path)
        
        # 3. 调用 VL 模型识别并保存数据
        stations = await service.process_station_list_vl(screenshot_path, device_info=device_info)
        logger.info(f"本页识别到 {len(stations)} 个场站")

        # 4. 匹配几何卡片与 VL 识别结果
        if json_data and json_data.get("cards") and stations:
            for card in json_data["cards"]:
                card_rect = card["rect"] # [x1, y1, x2, y2]
                for st in stations:
                    st_bounds = st.get("bounds") # [x1, y1, x2, y2] (0-1000)
                    if not st_bounds: continue
                    
                    # 转换 VL 坐标到像素坐标
                    st_y1_px = st_bounds[1] * h / 1000
                    st_y2_px = st_bounds[3] * h / 1000
                    
                    # 计算 y 轴重叠
                    overlap = min(card_rect[3], st_y2_px) - max(card_rect[1], st_y1_px)
                    if overlap > 50: # 有显著重叠
                        card["station_name"] = st.get("station_name")
                        logger.info(f"匹配成功: 几何卡片 {card_rect} -> 场站 {card['station_name']}")
                        break

        # 5. 遍历处理本页所有场站
        if json_data and json_data.get("cards"):
            for card_idx, card in enumerate(json_data["cards"]):
                station_name = card.get("station_name")
                if not station_name:
                    logger.warning(f"第 {card_idx + 1} 个几何卡片未匹配到场站名称，跳过。")
                    continue
                
                # 检查 Redis 去重
                redis_key = f"crawled:aite:{station_name}"
                if await redis_kit.get_data(redis_key):
                    logger.info(f"场站 {station_name} 已处理，跳过。")
                    continue

                click_x, click_y = card["click_point"]
                logger.info(f"准备处理第 {card_idx + 1} 个场站: {station_name}, 点击坐标: ({click_x}, {click_y})")
                d.click(click_x, click_y)
                
                # 等待二级页面加载
                await asyncio.sleep(3)
                
                # 截取二级页面图
                detail_uuid = f"detail_{station_name}_{image_uuid}"
                detail_path = take_screenshot(d, detail_uuid, save_dir=TEMP_IMAGE_DIR)
                
                # 5. 调用详情页处理逻辑 (二级页面：提取地址)
                logger.info(f"正在解析详情页基础数据: {detail_path}")
                detail_data = await service.process_station_detail(detail_path, station_name=station_name)

                # 6. 寻找 timePrice.jpg 图标并进入三级页面 (分时价格页)
                time_price_template = os.path.join(os.path.dirname(__file__), "BiaoShi", "timePrice.jpg")
                coords = Kit.find_template_coords(detail_path, time_price_template)
                
                if coords:
                    cx, cy, conf = coords
                    logger.info(f"找到分时价格图标，进入三级页面...")
                    d.click(cx, cy)
                    await asyncio.sleep(3)
                    
                    # 截取三级页面并处理滑动价格
                    price_detail_uuid = f"price_detail_{station_name}_{image_uuid}"
                    price_detail_path = take_screenshot(d, price_detail_uuid, save_dir=TEMP_IMAGE_DIR)
                    
                    all_prices = []
                    # 初始识别
                    prices = await ReadImageKit.get_price_detail_from_image(price_detail_path)
                    if prices: all_prices.extend(prices)
                    
                    last_md5 = Kit.get_file_md5(price_detail_path)
                    
                    # 滑动逻辑
                    for scroll_idx in range(3):
                        logger.info(f"执行第 {scroll_idx + 1} 次滑动以抓取更多价格...")
                        d.swipe(w // 2, int(h * 0.7), w // 2, int(h * 0.3), duration=0.5)
                        await asyncio.sleep(2)
                        
                        scroll_path = take_screenshot(d, f"price_scroll_{scroll_idx}_{station_name}", save_dir=TEMP_IMAGE_DIR)
                        current_md5 = Kit.get_file_md5(scroll_path)
                        
                        if current_md5 == last_md5:
                            logger.info("检测到屏幕未发生变化（已滑到底部），停止滑动识别。")
                            break
                        
                        last_md5 = current_md5
                        new_prices = await ReadImageKit.get_price_detail_from_image(scroll_path)
                        if new_prices:
                            for np_item in new_prices:
                                if not any(np_i.get("start") == np_item.get("start") for np_i in all_prices):
                                    all_prices.append(np_item)
                        else: break

                    if all_prices:
                        all_prices.sort(key=lambda x: x.get("start", "00:00"))
                        hourly_schedule = ReadImageKit.expand_schedule_to_24h(all_prices)
                        await service.process_price_detail_data(station_name, hourly_schedule)
                        logger.info(f"场站 {station_name} 三级页面价格处理完成。")
                    
                    # 从三级页面返回二级页面
                    logger.info("从三级页面返回二级页面...")
                    d.press("back")
                    await asyncio.sleep(1.5)
                else:
                    logger.warning(f"场站 {station_name} 未找到分时价格入口。")

                # 从二级页面返回列表页
                logger.info("从二级页面返回列表页...")
                d.press("back")
                await asyncio.sleep(1.5)
                
                # 记录 Redis
                await redis_kit.set_data(redis_key, "1", expire=REDIS_STATION_EXPIRE)

        # 5. 翻页滑动 (如果没进入二级页面)
        logger.info("执行翻页滑动...")
        start_x, start_y = w // 2, int(h * 0.8)
        end_x, end_y = w // 2, int(h * (0.8 - SCROLL_DISTANCE_RATIO))
        d.swipe(start_x, start_y, end_x, end_y, duration=0.5)
        
        await asyncio.sleep(WAIT_AFTER_SCROLL)

    logger.info("达到最大翻页次数，爬取结束。")
    return True

async def main(service=None, do_cleanup=True):
    """
    爬虫主入口
    """
    if do_cleanup:
        Kit.clear_temp_dir()

    if service is None:
        service = AiTeJiYiChongService()
        await service.init_db()

    d = u2.connect()
    
    try:
        await get_station_list(d, service)
        return True
    except Exception as e:
        logger.error(f"爬取过程中出现异常: {e}")
        return False
    finally:
        # 如果是内部初始化的 service，则在此关闭
        pass

if __name__ == "__main__":
    asyncio.run(main())