'commit'

Apps/AiTeJiYiChong/Crawler.py

@@ -60,6 +60,7 @@ async def get_station_list(d, service, max_scrolls=MAX_SCROLLS):
     # 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...")
@@ -112,6 +113,8 @@ async def get_station_list(d, service, max_scrolls=MAX_SCROLLS):
             # 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)
@@ -178,6 +181,29 @@ async def get_station_list(d, service, max_scrolls=MAX_SCROLLS):
                     # 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)
@@ -185,8 +211,9 @@ async def get_station_list(d, service, max_scrolls=MAX_SCROLLS):
                 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
-            d.press("back")
-            await asyncio.sleep(0.8)
+            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)}"
@@ -199,6 +226,15 @@ async def get_station_list(d, service, max_scrolls=MAX_SCROLLS):
                 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)

Apps/AiTeJiYiChong/ReadImageKit.py

@@ -217,6 +217,7 @@ class ReadImageKit:
         try:
             response = await cls._client.chat.completions.create(
                 model=VL_MODEL_NAME,
+                timeout=30,
                 messages=[
                     {
                         "role": "user",
@@ -275,6 +276,7 @@ class ReadImageKit:
         try:
             response = await cls._client.chat.completions.create(
                 model=VL_MODEL_NAME,
+                timeout=30,
                 messages=[
                     {
                         "role": "user",
@@ -342,6 +344,7 @@ class ReadImageKit:
         try:
             resp = await ReadImageKit._client.chat.completions.create(
                 model=VL_MODEL_NAME,
+                timeout=30,
                 messages=[
                     {
                         "role": "user",
@@ -470,6 +473,7 @@ class ReadImageKit:
         try:
             response = await cls._client.chat.completions.create(
                 model=VL_MODEL_NAME,
+                timeout=30,
                 messages=[
                     {
                         "role": "user",
@@ -524,6 +528,7 @@ class ReadImageKit:
         try:
             resp = await cls._client.chat.completions.create(
                 model=VL_MODEL_NAME,
+                timeout=30,
                 messages=[
                     {
                         "role": "user",