439 lines
20 KiB
Python
439 lines
20 KiB
Python
# coding=utf-8
|
||
import asyncio
|
||
import logging
|
||
import uuid
|
||
import os
|
||
import sys
|
||
import time
|
||
from datetime import datetime
|
||
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_STATIONS_COUNT, REDIS_STATION_EXPIRE,
|
||
WAIT_AFTER_SCROLL,
|
||
SAFE_EXCLUDE_RATIO,
|
||
BOTTOM_SAFE_EXCLUDE_RATIO,
|
||
TEST_CLEAR_REDIS
|
||
)
|
||
|
||
logger = logging.getLogger("AiTeJiYiChongCrawler")
|
||
|
||
async def clean_redis_data(redis_kit):
|
||
"""
|
||
[Testing] 清除 Redis 中的已爬取记录
|
||
"""
|
||
if not TEST_CLEAR_REDIS:
|
||
return
|
||
|
||
logger.warning("!!! [Testing] 正在清除 Redis 中的艾特吉易充已爬取记录...")
|
||
keys = await redis_kit.keys("crawled:aite:*")
|
||
if keys:
|
||
for key in keys:
|
||
await redis_kit.delete(key)
|
||
logger.info(f"已清除 {len(keys)} 条记录。")
|
||
else:
|
||
logger.info("Redis 中没有找到相关记录。")
|
||
|
||
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_stations_count=MAX_STATIONS_COUNT):
|
||
"""
|
||
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} | 目标数量: {max_stations_count}")
|
||
|
||
# 用于追踪后台分析任务
|
||
background_tasks = []
|
||
last_list_md5 = None
|
||
no_new_data_count = 0
|
||
total_encountered_count = 0
|
||
total_new_processed_count = 0
|
||
scroll_count = 0
|
||
|
||
while total_encountered_count < max_stations_count:
|
||
scroll_count += 1
|
||
logger.info(f"正在处理第 {scroll_count} 次滚动 (已遇到: {total_encountered_count}/{max_stations_count}, 新采集: {total_new_processed_count})...")
|
||
|
||
# 1. 拍摄截图
|
||
image_uuid = str(uuid.uuid4())
|
||
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. 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...")
|
||
json_metadata = Kit.crop_cards_from_image(screenshot_path, save_debug=True)
|
||
|
||
vl_img_path = screenshot_path.replace(".jpg", "_vl.jpg")
|
||
|
||
if not json_metadata or not json_metadata.get("cards"):
|
||
logger.warning("未识别到任何卡片，跳过当前页")
|
||
continue
|
||
|
||
# 3. 后台异步上传 _vl.jpg 供以后参考 (如果需要，目前仅本地处理)
|
||
|
||
# 4. 调用 VL 模型识别场站信息 (整页识别)
|
||
logger.info("正在调用 VL 模型识别场站信息 (整页识别)...")
|
||
# 优先使用带绿框的图片进行识别
|
||
img_to_process = vl_img_path if os.path.exists(vl_img_path) else screenshot_path
|
||
stations = await service.process_station_list_vl(img_to_process, json_metadata, device_info=device_info, max_count=max_stations_count - total_encountered_count)
|
||
logger.info(f"本页识别到 {len(stations)} 个有效场站")
|
||
|
||
ad_top_y_norm = 0.78 # 默认点击边界
|
||
|
||
# 5. 遍历处理本页所有场站
|
||
new_stations_processed_in_page = 0
|
||
if json_metadata.get("cards") and stations:
|
||
for card_idx, card in enumerate(json_metadata["cards"]):
|
||
# 检查是否已达到最大采集数量
|
||
if total_encountered_count >= max_stations_count:
|
||
break
|
||
|
||
# 检查索引是否越界 (VL 模型可能返回的数组长度不一致)
|
||
if card_idx < len(stations) and stations[card_idx]:
|
||
station = stations[card_idx]
|
||
station_name = station.get("station_name")
|
||
if not station_name: continue
|
||
|
||
# 只要是有效的场站，就计入已遇到数量
|
||
total_encountered_count += 1
|
||
|
||
# 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。({total_encountered_count}/{max_stations_count})")
|
||
continue
|
||
|
||
# 检查是否被遮挡或太靠近底部
|
||
card_bottom = card["bounds_norm"]["bottom"]
|
||
if card_bottom > ad_top_y_norm:
|
||
logger.warning(f"场站 '{station_name}' 被遮挡或太靠近底部 (Bottom {card_bottom:.2f} > {ad_top_y_norm})，留待下次滚动处理。")
|
||
# 还没处理，不能算作已遇到
|
||
total_encountered_count -= 1
|
||
continue
|
||
|
||
# 正常处理新场站
|
||
click_x, click_y = card["click_point"]
|
||
logger.info(f">>> 发现新场站 '{station_name}'，开始处理... ({total_encountered_count}/{max_stations_count})")
|
||
new_stations_processed_in_page += 1
|
||
total_new_processed_count += 1
|
||
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
|
||
# 【优化】梯级识别策略：优先模板匹配 (timePrice.jpg)，失败则降级为 VL 识别
|
||
template_time_price = os.path.join(os.path.dirname(__file__), "Template", "timePrice.jpg")
|
||
|
||
# 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)
|
||
|
||
entered_price_page = False
|
||
click_pos = None
|
||
|
||
try:
|
||
# 1. 尝试模板匹配
|
||
if os.path.exists(template_time_price):
|
||
match_res = d.image.match(template_time_price)
|
||
if match_res:
|
||
# 兼容 uiautomator2 不同版本的返回结果 (Match对象或dict)
|
||
if hasattr(match_res, 'point') and match_res.point:
|
||
click_pos = match_res.point
|
||
elif isinstance(match_res, dict):
|
||
if 'point' in match_res and match_res['point']:
|
||
click_pos = match_res['point']
|
||
elif 'x' in match_res and 'y' in match_res:
|
||
click_pos = (match_res['x'], match_res['y'])
|
||
elif isinstance(match_res, (list, tuple)) and len(match_res) >= 2:
|
||
click_pos = (match_res[0], match_res[1])
|
||
|
||
if click_pos:
|
||
logger.info(f"通过 timePrice.jpg 成功找到！坐标: {click_pos}")
|
||
|
||
# 如果模板匹配未成功解析坐标，或者匹配直接失败，则降级到 VL
|
||
if not click_pos:
|
||
logger.info("模板匹配未找到或解析失败，降级使用 VL 识别...")
|
||
res = await ReadImageKit.find_time_price_button_coordinate(detail_path, device_info=device_info)
|
||
if res.get("uia_center_x"):
|
||
click_pos = (res.get("uia_center_x"), res.get("uia_center_y"))
|
||
logger.info(f"VL 识别成功找到 '分时价格' 按钮: {click_pos}")
|
||
|
||
if click_pos:
|
||
d.click(click_pos[0], click_pos[1])
|
||
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。")
|
||
|
||
except Exception as e:
|
||
logger.error(f"处理三级页面详情异常 ({station_name}): {e}")
|
||
|
||
# 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)
|
||
|
||
# 如果内层循环已达上限，外层循环也应退出，避免不必要的滑动
|
||
if total_encountered_count >= max_stations_count:
|
||
break
|
||
|
||
# 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)
|
||
|
||
if stations and new_stations_processed_in_page == 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 >= 5:
|
||
logger.info("连续 5 页无新数据，判定为已到底，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(f"采集任务完成，共遇到 {total_encountered_count} 个场站，新处理 {total_new_processed_count} 个。")
|
||
return total_new_processed_count
|
||
|
||
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
|
||
"""
|
||
should_close_service = False
|
||
if service is None:
|
||
service = AiTeJiYiChongService()
|
||
should_close_service = True
|
||
await service.init_db()
|
||
|
||
redis_kit = RedisKit()
|
||
d = u2.connect()
|
||
|
||
# 任务日志记录
|
||
task_id = str(uuid.uuid4())
|
||
start_time = datetime.now()
|
||
operator = "艾特吉易充"
|
||
|
||
# 记录任务开始
|
||
try:
|
||
await service.db.save("t_crawl_task_log", {
|
||
"task_id": task_id,
|
||
"operator": operator,
|
||
"start_time": start_time,
|
||
"status": "running"
|
||
}, "task_id")
|
||
except Exception as e:
|
||
logger.error(f"无法记录任务开始日志: {e}")
|
||
|
||
total_count = 0
|
||
status = "success"
|
||
error_msg = None
|
||
|
||
try:
|
||
if do_cleanup:
|
||
# 清理临时目录
|
||
Kit.clear_temp_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)
|
||
|
||
total_count = await get_station_list(d, service, max_stations_count=MAX_STATIONS_COUNT)
|
||
|
||
if total_count:
|
||
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.error(f"爬取过程中出现异常: {e}")
|
||
status = "failed"
|
||
error_msg = str(e)
|
||
return False
|
||
finally:
|
||
# 记录任务结束
|
||
end_time = datetime.now()
|
||
duration = int((end_time - start_time).total_seconds())
|
||
try:
|
||
await service.db.update("t_crawl_task_log", {
|
||
"task_id": task_id,
|
||
"end_time": end_time,
|
||
"duration_seconds": duration,
|
||
"station_count": total_count,
|
||
"status": status,
|
||
"error_msg": error_msg
|
||
}, "task_id")
|
||
logger.info(f"任务执行日志已更新: {operator} | 耗时: {duration}s | 数量: {total_count} | 状态: {status}")
|
||
except Exception as e:
|
||
logger.error(f"无法更新任务执行日志: {e}")
|
||
|
||
# 如果是内部初始化的 service，则在此关闭
|
||
if should_close_service:
|
||
await service.close_db()
|
||
|
||
if __name__ == "__main__":
|
||
asyncio.run(main())
|