340 lines
14 KiB
Python
340 lines
14 KiB
Python
# 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,
|
||
SAFE_EXCLUDE_RATIO,
|
||
BOTTOM_SAFE_EXCLUDE_RATIO
|
||
)
|
||
|
||
logger = logging.getLogger("AiTeJiYiChongCrawler")
|
||
|
||
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:aite:{cleaned_name}"
|
||
if await redis_kit.get_data(redis_key):
|
||
return True
|
||
return False
|
||
|
||
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}")
|
||
|
||
# 用于追踪后台分析任务
|
||
background_tasks = []
|
||
last_list_md5 = None
|
||
no_new_data_count = 0
|
||
|
||
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)
|
||
|
||
# 1.5 检查是否存在广告 (VL)
|
||
logger.info("检查是否存在广告弹窗...")
|
||
ad_res = await ReadImageKit.detect_ad_popup(screenshot_path, device_info=device_info)
|
||
if ad_res:
|
||
ad_type = ad_res.get("ad_type")
|
||
logger.info(f"检测到广告弹窗，准备关闭: {ad_res} [Type: {ad_type}]")
|
||
|
||
x, y = ad_res['x'], ad_res['y']
|
||
|
||
if ad_type == "rabbit":
|
||
logger.info(">>> 检测到顽固的兔子广告，执行强力双击策略...")
|
||
# 使用 u2 的 double_click，它比两次 click + sleep 更快
|
||
d.double_click(x, y, duration=0.05)
|
||
|
||
# 处理“误触背景卡片”的逻辑
|
||
logger.info(">>> 考虑到可能误触背景卡片，等待 2s 后执行返回操作...")
|
||
await asyncio.sleep(2.0)
|
||
d.press("back")
|
||
await asyncio.sleep(1.0)
|
||
logger.info(">>> 已尝试从误触页面返回。")
|
||
else:
|
||
d.click(x, y)
|
||
await asyncio.sleep(1.5)
|
||
# 重新截图
|
||
if os.path.exists(screenshot_path): os.remove(screenshot_path)
|
||
screenshot_path = take_screenshot(d, image_uuid, save_dir=TEMP_IMAGE_DIR)
|
||
|
||
# 检查是否已经滚动到底部 (排除状态栏后，内容与上次一致)
|
||
current_md5 = Kit.get_image_content_md5(
|
||
screenshot_path,
|
||
top_ratio=SAFE_EXCLUDE_RATIO,
|
||
bottom_ratio=BOTTOM_SAFE_EXCLUDE_RATIO
|
||
)
|
||
if last_list_md5 and current_md5 == last_list_md5:
|
||
logger.info("检测到列表核心内容无变化，已到达底部或加载完成，提前结束。")
|
||
if os.path.exists(screenshot_path): os.remove(screenshot_path)
|
||
break
|
||
last_list_md5 = current_md5
|
||
|
||
logger.info(f"列表页截图已完成: {screenshot_path}")
|
||
|
||
# 2. 调用混合模式识别 (内部包含图形学切片 + VL 模型)
|
||
logger.info("正在执行混合模式识别 (切片 + VL)...")
|
||
stations = await service.process_station_list_hybrid(screenshot_path, device_info=device_info)
|
||
logger.info(f"本页识别到 {len(stations)} 个有效场站卡片")
|
||
|
||
# 3. 遍历处理本页所有场站
|
||
for card_idx, station in enumerate(stations):
|
||
station_name = station.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
|
||
|
||
# 使用识别结果中自带的点击坐标
|
||
click_x = station.get("uia_center_x")
|
||
click_y = station.get("uia_center_y")
|
||
|
||
if click_x is None or click_y is None:
|
||
logger.warning(f"场站 {station_name} 缺失点击坐标，跳过。")
|
||
continue
|
||
|
||
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)
|
||
|
||
should_back_to_list = True
|
||
|
||
# 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)
|
||
|
||
# 后台分析详情页基础数据
|
||
logger.info(f"已启动后台分析详情页: {station_name}")
|
||
|
||
async def detail_task_wrapper(p, name):
|
||
try:
|
||
await service.process_station_detail(p, station_name=name)
|
||
if os.path.exists(p): os.remove(p)
|
||
except Exception as ex:
|
||
logger.error(f"详情页分析异常 ({name}): {ex}")
|
||
|
||
task_detail = asyncio.create_task(detail_task_wrapper(detail_path, station_name))
|
||
background_tasks.append(task_detail)
|
||
|
||
# 4. 寻找分时价格入口并进入三级页面
|
||
# 优先使用 VL 模型精准识别，避免误判导致退回微信
|
||
res = await ReadImageKit.find_time_price_button_coordinate(detail_path, device_info=device_info)
|
||
pos = (res.get("uia_center_x"), res.get("uia_center_y")) if res.get("uia_center_x") else None
|
||
|
||
entered_price_page = False
|
||
if pos and pos[0] is not None and pos[1] is not None:
|
||
ex, ey = pos
|
||
logger.info(f"找到 '分时价格' 按钮: ({ex}, {ey})")
|
||
|
||
# 记录点击前的页面特征，用于验证是否成功进入三级页面
|
||
before_click_md5 = Kit.get_image_content_md5(detail_path)
|
||
|
||
d.click(ex, ey)
|
||
await asyncio.sleep(2)
|
||
|
||
# 检查页面是否真的变化了
|
||
after_click_path = take_screenshot(d, f"check_{detail_uuid}", save_dir=TEMP_IMAGE_DIR)
|
||
after_click_md5 = Kit.get_image_content_md5(after_click_path)
|
||
|
||
if before_click_md5 != after_click_md5:
|
||
entered_price_page = True
|
||
# 抓取三级页面图片
|
||
price_screenshots = []
|
||
price_screenshots.append(after_click_path)
|
||
|
||
# 滑动处理
|
||
last_price_md5 = after_click_md5
|
||
for scroll_idx in range(2):
|
||
d.swipe(w // 2, int(h * 0.7), w // 2, int(h * 0.3), duration=0.4)
|
||
await asyncio.sleep(1)
|
||
scroll_path = take_screenshot(d, f"price_scroll_{scroll_idx}_{station_name}", save_dir=TEMP_IMAGE_DIR)
|
||
curr_price_md5 = Kit.get_image_content_md5(
|
||
scroll_path,
|
||
top_ratio=SAFE_EXCLUDE_RATIO,
|
||
bottom_ratio=BOTTOM_SAFE_EXCLUDE_RATIO
|
||
)
|
||
if curr_price_md5 == last_price_md5: break
|
||
price_screenshots.append(scroll_path)
|
||
last_price_md5 = curr_price_md5
|
||
|
||
# 后台处理价格图片
|
||
logger.info(f"已启动后台分析价格页: {station_name}，共 {len(price_screenshots)} 张图")
|
||
task_price = asyncio.create_task(analyze_prices_background(service, station_name, price_screenshots))
|
||
background_tasks.append(task_price)
|
||
|
||
# 立即返回
|
||
d.press("back")
|
||
await asyncio.sleep(0.5)
|
||
|
||
# 检查返回后的页面状态
|
||
check_back_path = take_screenshot(d, f"check_back_{detail_uuid}", save_dir=TEMP_IMAGE_DIR)
|
||
|
||
check_list_md5 = Kit.get_image_content_md5(
|
||
check_back_path,
|
||
top_ratio=SAFE_EXCLUDE_RATIO,
|
||
bottom_ratio=BOTTOM_SAFE_EXCLUDE_RATIO
|
||
)
|
||
check_detail_md5 = Kit.get_image_content_md5(check_back_path)
|
||
|
||
if os.path.exists(check_back_path): os.remove(check_back_path)
|
||
|
||
if check_list_md5 == current_md5:
|
||
logger.info("检测到已直接返回列表页，跳过后续返回操作。")
|
||
should_back_to_list = False
|
||
elif check_detail_md5 == before_click_md5:
|
||
logger.info("检测到返回详情页，需执行第二次返回。")
|
||
should_back_to_list = True
|
||
else:
|
||
logger.warning(f"返回后状态未知 (ListMD5:{check_list_md5[:8]} vs {current_md5[:8]}, DetailMD5:{check_detail_md5[:8]} vs {before_click_md5[:8]})，默认执行返回。")
|
||
should_back_to_list = True
|
||
|
||
else:
|
||
logger.warning(f"点击 '{station_name}' 的 '分时价格' 按钮后页面无明显变化，跳过三级页面处理。")
|
||
if os.path.exists(after_click_path): os.remove(after_click_path)
|
||
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
|
||
if should_back_to_list:
|
||
d.press("back")
|
||
await asyncio.sleep(0.8)
|
||
|
||
# 记录 Redis
|
||
full_name_key = f"crawled:aite:{Kit.clean_station_name(station_name)}"
|
||
await redis_kit.set_data(full_name_key, "1", expire=REDIS_STATION_EXPIRE)
|
||
|
||
# 在每一页结束时，清理已完成的任务
|
||
done_tasks = [t for t in background_tasks if t.done()]
|
||
for t in done_tasks:
|
||
if t.exception():
|
||
logger.error(f"后台任务执行异常: {t.exception()}")
|
||
background_tasks.remove(t)
|
||
|
||
if stations and new_stations_processed == 0:
|
||
no_new_data_count += 1
|
||
logger.info(f"本页所有场站均已处理过，连续 {no_new_data_count} 页无新数据。")
|
||
if no_new_data_count >= 3:
|
||
logger.info("连续 3 页无新数据，判定为已到底或重复循环，提前结束。")
|
||
break
|
||
else:
|
||
no_new_data_count = 0
|
||
|
||
# 5. 列表页翻页滑动
|
||
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)
|
||
|
||
# 最终等待所有后台分析任务完成
|
||
if background_tasks:
|
||
logger.info(f"正在等待剩余 {len(background_tasks)} 个后台分析任务完成...")
|
||
await asyncio.gather(*background_tasks, return_exceptions=True)
|
||
|
||
logger.info("达到最大翻页次数，爬取结束。")
|
||
return True
|
||
|
||
async def analyze_prices_background(service, station_name, image_paths):
|
||
"""
|
||
后台异步处理价格图片分析
|
||
"""
|
||
try:
|
||
all_prices = []
|
||
for path in image_paths:
|
||
prices = await ReadImageKit.get_price_detail_from_image(path)
|
||
if prices and isinstance(prices, list):
|
||
for p in prices:
|
||
if not isinstance(p, dict): continue
|
||
if not any(isinstance(np_i, dict) and np_i.get("start") == p.get("start") for np_i in all_prices):
|
||
all_prices.append(p)
|
||
|
||
if all_prices:
|
||
all_prices = [p for p in all_prices if isinstance(p, dict)]
|
||
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"后台处理完成: {station_name} 的分时价格已保存。")
|
||
|
||
# 处理完成后清理图片，释放磁盘空间
|
||
for path in image_paths:
|
||
try:
|
||
if os.path.exists(path):
|
||
os.remove(path)
|
||
logger.debug(f"已删除已处理的图片: {path}")
|
||
except Exception as e:
|
||
logger.warning(f"删除图片失败: {path}, {e}")
|
||
|
||
except Exception as e:
|
||
logger.error(f"分析价格后台任务异常 ({station_name}): {e}")
|
||
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())
|