'commit'

Apps/AiTeJiYiChong/Crawler.py

@@ -23,7 +23,9 @@ from Apps.AiTeJiYiChong.Config.Setting import (
     SCROLL_DISTANCE_RATIO,
     MAX_SCROLLS, REDIS_STATION_EXPIRE,
     WAIT_AFTER_SCROLL,
-    MAX_CRAWL_DISTANCE
+    MAX_CRAWL_DISTANCE,
+    SAFE_EXCLUDE_RATIO,
+    BOTTOM_SAFE_EXCLUDE_RATIO
 )
 
 logger = logging.getLogger("AiTeJiYiChongCrawler")
@@ -66,10 +68,14 @@ async def get_station_list(d, service, max_scrolls=MAX_SCROLLS):
         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 (截图内容与上次一致)
-        current_md5 = Kit.get_file_md5(screenshot_path)
+        # 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("检测到列表截图内容无变化，已到达底部或加载完成，提前结束。")
+            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
@@ -123,41 +129,58 @@ async def get_station_list(d, service, max_scrolls=MAX_SCROLLS):
             task_detail = asyncio.create_task(detail_task_wrapper(detail_path, station_name))
             background_tasks.append(task_detail)
 
-            # 4. 寻找 timePrice.jpg 图标并进入三级页面
-            time_price_template = os.path.join(os.path.dirname(__file__), "BiaoShi", "timePrice.jpg")
-            coords = Kit.find_template_coords(detail_path, time_price_template)
+            # 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
             
-            if coords:
-                cx, cy, conf = coords
-                logger.info(f"找到分时价格图标，进入三级页面...")
-                d.click(cx, cy)
+            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)
                 
-                # 抓取三级页面图片
-                price_screenshots = []
-                price_detail_uuid = f"price_detail_{station_name}_{image_uuid}"
-                price_path = take_screenshot(d, price_detail_uuid, save_dir=TEMP_IMAGE_DIR)
-                price_screenshots.append(price_path)
+                # 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)
                 
-                # 滑动处理
-                last_price_md5 = Kit.get_file_md5(price_path)
-                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_file_md5(scroll_path)
-                    if curr_price_md5 == last_price_md5: break
-                    price_screenshots.append(scroll_path)
-                    last_price_md5 = curr_price_md5
+                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)
+                    # 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)
+                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。")