'commit'

Apps/AiTeJiYiChong/Crawler.py

@@ -21,9 +21,8 @@ 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,
+    MAX_STATIONS_COUNT, REDIS_STATION_EXPIRE,
     WAIT_AFTER_SCROLL,
-    MAX_CRAWL_DISTANCE,
     SAFE_EXCLUDE_RATIO,
     BOTTOM_SAFE_EXCLUDE_RATIO
 )
@@ -43,7 +42,7 @@ async def is_already_crawled(redis_kit, station_name):
         return True
     return False
 
-async def get_station_list(d, service, max_scrolls=MAX_SCROLLS):
+async def get_station_list(d, service, max_stations_count=MAX_STATIONS_COUNT):
     """
     获取场站列表并处理翻页
     """
@@ -55,15 +54,18 @@ async def get_station_list(d, service, max_scrolls=MAX_SCROLLS):
     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}")
+    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_processed_count = 0
+    scroll_count = 0
 
-    for i in range(max_scrolls + 1):
-        logger.info(f"正在处理第 {i + 1} 页...")
+    while total_processed_count < max_stations_count:
+        scroll_count += 1
+        logger.info(f"正在处理第 {scroll_count} 次滚动 (已采集: {total_processed_count}/{max_stations_count})...")
         
         # 1. 拍摄截图
         image_uuid = str(uuid.uuid4())
@@ -127,8 +129,9 @@ async def get_station_list(d, service, max_scrolls=MAX_SCROLLS):
 
                     # 正常处理新场站
                     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})")
+                    logger.info(f">>> 发现新场站 '{station_name}'，开始处理... ({total_processed_count + 1}/{max_stations_count})")
                     new_stations_processed += 1
+                    total_processed_count += 1
                     d.click(click_x, click_y)
                     
                     # 等待二级页面加载
@@ -230,6 +233,13 @@ async def get_station_list(d, service, max_scrolls=MAX_SCROLLS):
                     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)
 
+                    # 检查是否已达到最大采集数量
+                    if total_processed_count >= max_stations_count:
+                        logger.info(f"已达到目标采集数量 {max_stations_count}，准备结束采集。")
+                        break
+            if total_processed_count >= max_stations_count:
+                break
+
         # 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:
@@ -258,7 +268,7 @@ async def get_station_list(d, service, max_scrolls=MAX_SCROLLS):
         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。")
+    logger.info(f"采集任务完成，共采集 {total_processed_count} 个场站。")
     return True
 
 async def analyze_prices_background(service, station_name, image_paths):