aiData/Apps/XinDianTu/Crawler.py

# coding=utf-8
import asyncio
import logging
import uuid
import os
import sys
import json
import time
import hashlib
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 Core.BaseCrawler import BaseCrawler
from Apps.XinDianTu import Kit
from Apps.XinDianTu.Kit import take_screenshot
from Util.ObsUtil import ObsUploader
from Util.RedisKit import RedisKit
from Util.PaddleOCRKit import get_ocr_kit
import cv2
from Apps.XinDianTu.Service import XinDianTuService
from Apps.XinDianTu.ReadImageKit import ReadImageKit
from Config.Config import (
    OBS_TMP_PREFIX, CDN_DOMAIN, TEMP_IMAGE_DIR
)
from Apps.XinDianTu.Config.Setting import (
    SCROLL_DISTANCE_RATIO,
    MAX_SCROLLS, REDIS_STATION_EXPIRE,
    WAIT_DETAIL_PAGE_LOAD, WAIT_BACK_TO_LIST, WAIT_AFTER_SCROLL,
    MAX_CRAWL_DISTANCE
)

# --- 用户配置区域 ---
# 是否保留截图文件（True=保留备查，False=随用随删）
KEEP_SCREENSHOTS = True

# [Testing] 是否在启动时清除 Redis 中的场站处理记录
# True: 每次运行前清除记录，方便反复测试同一个场站
# False: 生产模式，保留记录以避免重复爬取
TEST_CLEAR_REDIS = True

# 配置说明：
# SCROLL_DISTANCE_RATIO 控制翻页时的滑动距离（在 Config.py 中修改）。
# 对于华为 Mate 20x 等分辨率较低或屏幕较小的手机，如果发现翻页时跳过了某些场站，
# 请尝试减小 SCROLL_DISTANCE_RATIO（例如设置为 0.4 或 0.3）。
# 这样每次滑动的距离变短，可以确保所有场站都能被完整显示并识别。

# 配置日志输出
logging.basicConfig(
    level=logging.INFO,
    format='%(asctime)s - %(name)s - %(levelname)s - %(message)s',
    handlers=[
        logging.StreamHandler(sys.stdout)
    ]
)
logger = logging.getLogger("StationList")

# 强制设置所有相关模块的日志级别为 INFO，防止被第三方库干扰
logging.getLogger("PaddleOCRKit").setLevel(logging.INFO)
logging.getLogger("OpenXinDianTu").setLevel(logging.INFO)
logging.getLogger("FullProcess").setLevel(logging.INFO)


class XinDianTuCrawler(BaseCrawler):
    """
    新电途小程序爬虫实现
    """

    def __init__(self, service=None):
        super().__init__(service)
        # 初始化配置参数
        self.max_scrolls = MAX_SCROLLS
        self.uploader = ObsUploader()
        self.redis_kit = RedisKit()

    async def start(self):
        """
        实现 BaseCrawler 的启动入口
        """
        # 兼容旧逻辑，直接调用 main
        await main(self.service)

    async def open_app(self):
        # 实际逻辑在 Opener.py，此处可作为封装层
        pass

    async def crawl_list(self):
        # 实际逻辑在 get_station_list，此处可作为封装层
        pass

    async def crawl_detail(self, station_info):
        pass


async def is_already_crawled(redis_kit, station_name):
    """
    检查场站是否已经爬取过，仅按名称去重
    """
    cleaned_name = Kit.clean_station_name(station_name)
    if not cleaned_name:
        return False

    redis_key = f"crawled:xdt:{cleaned_name}"
    if await redis_kit.get_data(redis_key):
        return True
    return False


async def analyze_prices_background(service, station_name, image_paths):
    """
    后台异步处理价格图片分析
    """
    try:
        # 使用多图解析并去重
        all_rows = await ReadImageKit.parse_price_schedule_multi(station_name, image_paths)

        if all_rows:
            # 24小时铺平
            hourly_schedule = ReadImageKit.hourly_full_day(all_rows)
            await service.process_price_detail_data(station_name, hourly_schedule)
            logger.info(f"后台处理完成: {station_name} 的分时价格已保存。")
        else:
            logger.warning(f"后台处理失败: {station_name} 未能解析出价格时段。")

        # 处理完成后清理图片
        for path in image_paths:
            try:
                if os.path.exists(path):
                    os.remove(path)
            except:
                pass

    except Exception as e:
        logger.error(f"分析价格后台任务异常 ({station_name}): {e}")
    return True


async def get_station_list(d, service, uploader, max_scrolls=MAX_SCROLLS):
    """
    获取场站列表并处理翻页 (异步优化版)
    """
    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}")

    background_tasks = []

    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. 执行本地图形学分析，生成 _vl.jpg 和 .json
        logger.info("正在执行图形学切片分析...")
        Kit.crop_cards_from_image(screenshot_path)
        
        json_path = screenshot_path.replace(".jpg", ".json")
        vl_img_path = screenshot_path.replace(".jpg", "_vl.jpg")

        if not os.path.exists(json_path) or not os.path.exists(vl_img_path):
            logger.warning("未识别到任何卡片，跳过当前页")
            continue

        with open(json_path, 'r', encoding='utf-8') as f:
            json_metadata = json.load(f)

        # 3. 【优化】后台异步上传 _vl.jpg 供以后参考，不再等待上传
        vl_object_key = f"{OBS_TMP_PREFIX}/{image_uuid}_vl.jpg"
        loop = asyncio.get_running_loop()
        loop.run_in_executor(None, uploader.upload_file, vl_object_key, vl_img_path)
        
        # 4. 【优化】直接使用本地路径调用 VL 模型识别，避免等待上传
        logger.info("正在调用 VL 模型识别场站信息...")
        stations = await service.process_station_list_vl(vl_img_path, json_metadata, device_info=device_info)
        logger.info(f"本页识别到 {len(stations)} 个场站")

        # 5. 匹配几何卡片与 VL 识别结果 (XinDianTu 的 parse_vl_image 已经按顺序返回了)
        # 这里的 stations 列表长度应该与 json_metadata["cards"] 对应
        if json_metadata.get("cards") and stations:
            for idx, card in enumerate(json_metadata["cards"]):
                # 检查索引是否越界 (VL 模型可能返回的数组长度不一致)
                if idx < len(stations) and stations[idx]:
                    st = stations[idx]
                    station_name = st.get("station_name")
                    if not station_name: continue

                    # 检查 Redis 去重
                    if await is_already_crawled(redis_kit, station_name):
                        logger.info(f"场站 {station_name} 匹配到已处理记录，跳过。")
                        continue

                    click_x, click_y = card["click_point"]
                    logger.info(f"准备处理第 {idx + 1} 个场站: {station_name}, 点击坐标: ({click_x}, {click_y})")
                    
                    d.click(int(click_x), int(click_y))

                    # 等待二级页面加载
                    await asyncio.sleep(WAIT_DETAIL_PAGE_LOAD)

                    # 截取二级页面图
                    detail_uuid = str(uuid.uuid4())
                    detail_path = take_screenshot(d, detail_uuid, save_dir=TEMP_IMAGE_DIR)

                    # 【优化】后台解析详情页地址，直接传本地路径，避免等待上传
                    logger.info(f"已启动后台分析详情页: {station_name}")
                    task_addr = asyncio.create_task(service.process_station_address(station_name, detail_path, device_info=device_info))
                    background_tasks.append(task_addr)

                    # 【优化】后台异步上传详情页截图供以后参考
                    detail_object_key = f"{OBS_TMP_PREFIX}/{detail_uuid}.jpg"
                    loop = asyncio.get_running_loop()
                    loop.run_in_executor(None, uploader.upload_file, detail_object_key, detail_path)

                    # --- 抓取价格时段信息 ---
                    # 识别 "全部时段" 按钮
                    pos = Kit.find_expand_button_position(detail_path, debug_dir=TEMP_IMAGE_DIR, debug_filename_prefix=station_name)
                    if pos:
                        ex, ey = pos
                        logger.info(f"找到 '全部时段' 按钮: ({ex}, {ey})")
                        d.click(ex, ey)
                        await asyncio.sleep(1.5)

                        price_screenshots = []
                        for p_idx in range(1, 4):
                            p_uuid = f"{hashlib.md5(station_name.encode('utf-8')).hexdigest()}_p_{p_idx}"
                            p_path = take_screenshot(d, p_uuid, save_dir=TEMP_IMAGE_DIR)
                            price_screenshots.append(p_path)
                            if p_idx < 3:
                                d.swipe_ext("up", scale=0.7)
                                await asyncio.sleep(1.0)
                        
                        # 【异步优化】后台处理价格
                        logger.info(f"已启动后台分析价格页: {station_name}")
                        task_price = asyncio.create_task(analyze_prices_background(service, station_name, price_screenshots))
                        background_tasks.append(task_price)

                        # 从三级页面返回
                        d.press("back")
                        await asyncio.sleep(0.5)

                    # 从二级页面返回
                    d.press("back")
                    await asyncio.sleep(WAIT_BACK_TO_LIST)

                    # 记录 Redis 去重 (仅按名称去重)
                    cleaned = Kit.clean_station_name(station_name)
                    await redis_kit.set_data(f"crawled:xdt:{cleaned}", "1", expire=REDIS_STATION_EXPIRE)

        # 清理已完成的后台任务
        done_tasks = [t for t in background_tasks if t.done()]
        for t in done_tasks:
            if t.exception():
                logger.error(f"后台任务异常: {t.exception()}")
            background_tasks.remove(t)

        # 6. 翻页
        logger.info("执行翻页滑动...")
        d.swipe_ext("up", scale=SCROLL_DISTANCE_RATIO)
        await asyncio.sleep(WAIT_AFTER_SCROLL)

    # 等待所有后台任务完成
    if background_tasks:
        logger.info(f"正在等待剩余 {len(background_tasks)} 个后台任务完成...")
        await asyncio.gather(*background_tasks, return_exceptions=True)

    logger.info("采集任务完成")
    return True


def clean_images_dir():
    """清理 Images 目录下除保留文件外的所有文件"""
    base_dir = os.path.dirname(os.path.abspath(__file__))
    images_dir = os.path.join(base_dir, "Images")

    if not os.path.exists(images_dir):
        return

    keep_files = {'1.jpg', '2.jpg', '3.jpg', '4.jpg'}
    logger.info(f"正在清理 Images 目录 (保留: {keep_files})...")

    deleted_count = 0
    for filename in os.listdir(images_dir):
        if filename in keep_files:
            continue

        file_path = os.path.join(images_dir, filename)
        try:
            if os.path.isfile(file_path):
                os.remove(file_path)
                deleted_count += 1
        except Exception as e:
            logger.warning(f"删除文件失败 {filename}: {e}")

    logger.info(f"清理完成，共删除 {deleted_count} 个文件。")


async def clean_redis_data(redis_kit):
    """清除 Redis 中的场站处理记录"""
    if TEST_CLEAR_REDIS:
        logger.info("测试模式开启：正在清除 Redis 中的场站处理记录 (processed_station:*)...")
        keys = await redis_kit.keys("processed_station:*")
        if keys:
            count = await redis_kit.delete(*keys)
            logger.info(f"已清除 {count} 条场站处理记录")
        else:
            logger.info("未发现旧的场站处理记录")


async def main(service=None, do_cleanup=True):
    # 连接设备
    d = u2.connect()

    # 初始化服务
    should_close_service = False
    if service is None:
        service = XinDianTuService()
        should_close_service = True
        # 初始化数据库连接（XinDianTuService 需要）
        await service.init_db()

    uploader = ObsUploader()
    redis_kit = RedisKit()

    try:
        if do_cleanup:
            # 清理图片目录
            clean_images_dir()

            # [Testing] 如果配置为测试模式，启动时清除 Redis 记录
            await clean_redis_data(redis_kit)

        # 清理过期数据
        # await service.cleanup_old_data()

        # 获取场站列表
        stations = await get_station_list(d, service, uploader, max_scrolls=MAX_SCROLLS)

        if stations:
            logger.info("场站列表采集完成。")
        else:
            logger.warning("未采集到任何场站信息。")

        return True

    except Exception as e:
        logger.exception(f"运行过程中出现异常: {e}")
        return False
    finally:
        # 关闭数据库连接
        if should_close_service:
            await service.close_db()


if __name__ == "__main__":
    try:
        asyncio.run(main())
    except KeyboardInterrupt:
        logger.info("程序被用户中断.")
    except Exception as e:
        logger.exception(f"程序崩溃: {e}")