'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。")
 

Apps/AiTeJiYiChong/Kit.py

@@ -36,6 +36,29 @@ def get_file_md5(file_path):
     return hash_md5.hexdigest()
 
 
+def get_image_content_md5(file_path, top_ratio=0.1, bottom_ratio=0.1):
+    """
+    计算图片核心内容的 MD5 值（排除状态栏和导航栏）
+    """
+    img = read_image(file_path)
+    if img is None:
+        return None
+
+    h, w = img.shape[:2]
+    top = int(h * top_ratio)
+    bottom = int(h * (1 - bottom_ratio))
+
+    # 裁剪中间部分
+    content = img[top:bottom, :]
+
+    # 将图片数据转换为字节流计算 MD5
+    # 使用 cv2.imencode 转为 jpg 字节流，避免原始 numpy 数组可能的细微差异（虽然通常没问题）
+    success, encoded_img = cv2.imencode(".jpg", content)
+    if success:
+        return hashlib.md5(encoded_img.tobytes()).hexdigest()
+    return hashlib.md5(content.tobytes()).hexdigest()
+
+
 def read_image(path):
     """读取图片，支持中文路径"""
     if not path or not os.path.exists(path):

Apps/AiTeJiYiChong/ReadImageKit.py

@@ -21,6 +21,16 @@ from Apps.AiTeJiYiChong import Kit
 
 logger = logging.getLogger(__name__)
 
+# 场站过滤黑名单
+STATION_EXCLUDED_TITLES = {
+    "推荐站点", "距离优先", "价格最低", "空闲较多", "筛选", "地图", "列表",
+    "我的订单", "收藏站点", "优惠券", "站内搜索"
+}
+
+STATION_BLACKLIST_KEYWORDS = [
+    "广告", "点击进入", "立即参与", "咨询电话", "活动详情", "导航到", "停车说明"
+]
+
 
 class ReadImageKit:
     _client = AsyncOpenAI(
@@ -42,14 +52,17 @@ class ReadImageKit:
         "   - 场站名称 (station_name)；\n"
         "   - 距离信息 (distance, 例如 '2.82km' 或 '90m')，通常位于卡片右侧蓝色胶囊区域内；\n"
         "   - 金额/电费 (price，例如 '1.2500')，通常以红色字体显示；\n"
-        "   - 充电枪信息 (piles，包含'快'或'慢'的类型、总枪数和空闲枪数，例如 '快 4/4')。\n"
+        "   - **充电枪信息 (piles)**: 必须包含类型('快充'、'慢充'、'超充')、总枪数和空闲枪数。识别规则如下：\n"
+        "     - 如果明确标有'快'、'慢'或'超'，则对应为'快充'、'慢充'、'超充'。\n"
+        "     - 如果图中只显示数字（如 '34/42'）而没有明确标明类型，请统一识别为 `type: \"慢充\"`。\n"
+        "     - 必须以 JSON 对象列表形式输出，例如：`[{\"type\": \"快充\", \"free\": 4, \"total\": 4}, {\"type\": \"慢充\", \"free\": 1, \"total\": 2}]`。\n"
         "3. 如果绿色方框内缺少上述任何一项要素，说明它不是真正的场站卡片，请直接跳过。\n"
         "\n"
         "JSON对象字段要求：\n"
         "1. b_use: 状态标识（1或0）。如果场站名称为灰色或带有“暂停使用”等标签，则为0，否则为1。\n"
         "2. station_name: 场站名称；\n"
         "3. price: 一度电的价格（数字，如 1.2500）；\n"
-        "4. piles: 充电枪列表 [{type: '快', free: 4, total: 4}]；\n"
+        "4. piles: 充电枪列表 [{type: '快'|'慢'|'超', free: 4, total: 4}]；\n"
         "5. parking: 停车费用描述（通常在蓝色'P'图标后，例如 '免费停车三小时'）；\n"
         "6. distance: 距离信息字符串（例如 '2.82km' 或 '90m'）；\n"
         "7. bounds: {x1,y1,x2,y2} 区域像素坐标（0-1000）；\n"
@@ -303,15 +316,27 @@ class ReadImageKit:
             img_input = {"url": f"data:image/jpeg;base64,{encoded}"}
 
         prompt = (
-            "请识别图片中的充电站卡片信息，并以 JSON 格式输出：\n"
+            "你是一个专业的充电桩信息提取助手。请识别图片中充电站卡片的核心信息。\n"
+            "注意以下识别规则：\n"
+            "1. **场站名称 (station_name)**: 场站名称通常位于卡片的第一行（左上角），字体最大且加粗。严禁提取'距离优先'、'空闲较多'、'价格最低'等筛选标签。严禁将卡片中下部的描述信息（如'导航到...'、'停车说明...'、'距您...'等）识别为名称。名称通常是一个具体的地点或品牌名。\n"
+            "2. **价格 (price)**: 提取数字部分，通常以'元/度'结尾，字体颜色通常为红色或加粗。\n"
+            "3. **桩数 (piles)**: 识别所有类型的充电桩。请提取'快'、'慢'或'超'字样及其对应的'空闲/总数'（如 '快 4/4'）。\n"
+            "   - 如果明确标有'快'、'慢'或'超'，则对应为'快充'、'慢充'、'超充'。\n"
+            "   - 如果图中只显示数字（如 '34/42'）而没有明确标明类型，请统一识别为 `type: \"慢充\"`。\n"
+            "   - 必须以 JSON 对象列表形式输出，例如：`[{\"type\": \"快充\", \"free\": 4, \"total\": 4}]`。\n"
+            "4. **距离 (distance)**: 提取如 '2.5km' 格式，通常在蓝色胶囊背景内。\n"
+            "5. **停车 (parking)**: 简要描述停车收费信息，通常在蓝色'P'图标后。\n\n"
+            "请以 JSON 格式输出：\n"
             "{\n"
             "  \"station_name\": \"场站名称\",\n"
-            "  \"price\": \"价格(数字)\",\n"
-            "  \"piles\": \"空闲/总数(如 4/4)\",\n"
-            "  \"distance\": \"距离(如 2.5km)\",\n"
-            "  \"parking\": \"停车描述\"\n"
+            "  \"price\": \"价格\",\n"
+            "  \"piles\": [\n"
+            "    {\"type\": \"快\", \"free\": 4, \"total\": 4}\n"
+            "  ],\n"
+            "  \"distance\": \"距离\",\n"
+            "  \"parking\": \"停车信息\"\n"
             "}\n"
-            "只输出 JSON，不要有其他文字。"
+            "只输出 JSON，不要有任何解释文字。"
         )
 
         try:
@@ -410,6 +435,20 @@ class ReadImageKit:
             except:
                 pass
 
+        # 3. 后置过滤
+        if final_stations:
+            processed_excluded_titles = {str(x).replace(" ", "").strip() for x in STATION_EXCLUDED_TITLES}
+            filtered = []
+            for item in final_stations:
+                name = item.get("station_name")
+                normalized_name = str(name).replace(" ", "").strip()
+                if normalized_name in processed_excluded_titles:
+                    continue
+                if any(kw in normalized_name for kw in STATION_BLACKLIST_KEYWORDS):
+                    continue
+                filtered.append(item)
+            final_stations = filtered
+
         return final_stations
 
     @classmethod
@@ -460,3 +499,55 @@ class ReadImageKit:
         except Exception as e:
             logger.error(f"Error calling VL model: {e}")
             return []
+
+    @classmethod
+    async def find_time_price_button_coordinate(cls, image_path: str, device_info=None):
+        """
+        使用 VL 模型定位详情页中的 '分时价格' 按钮
+        """
+        if not os.path.exists(image_path):
+            return {}
+
+        with open(image_path, "rb") as f:
+            encoded = base64.b64encode(f.read()).decode("utf-8")
+            img_input = {"url": f"data:image/jpeg;base64,{encoded}"}
+
+        prompt = (
+            "请识别图片中 '分时价格' 或 '查看分时电价' 按钮的中心坐标。\n"
+            "该按钮通常位于充电站详情页，可能是一个带有价格图标或箭头的小型矩形区域。\n"
+            "请直接以 JSON 格式输出该按钮的中心点坐标：\n"
+            "{\"uia_center_x\": 500, \"uia_center_y\": 500}\n"
+            "注意：坐标系为 0-1000 归一化坐标，其中 (0,0) 为左上角，(1000,1000) 为右下角。\n"
+            "只输出 JSON，不要有任何解释文字。"
+        )
+
+        try:
+            resp = await cls._client.chat.completions.create(
+                model=VL_MODEL_NAME,
+                messages=[
+                    {
+                        "role": "user",
+                        "content": [
+                            {"type": "text", "text": prompt},
+                            {"type": "image_url", "image_url": img_input}
+                        ]
+                    }
+                ],
+                max_tokens=100,
+                temperature=0.01
+            )
+            content = resp.choices[0].message.content.strip()
+            raw = cls._extract_json(content)
+            res = json.loads(raw)
+            
+            # 转换 0-1000 坐标到实际像素坐标
+            if res.get("uia_center_x") is not None and device_info:
+                w = device_info.get("width", FALLBACK_WIDTH)
+                h = device_info.get("height", FALLBACK_HEIGHT)
+                res["uia_center_x"] = int(res["uia_center_x"] * w / 1000)
+                res["uia_center_y"] = int(res["uia_center_y"] * h / 1000)
+                
+            return res
+        except Exception as e:
+            logger.error(f"VL find_time_price_button_coordinate error: {e}")
+            return {}

Apps/AiTeJiYiChong/Service.py

@@ -36,6 +36,25 @@ class AiTeJiYiChongService:
     def get_hash(self, s: str) -> str:
         return hashlib.md5(s.encode('utf-8')).hexdigest()
 
+    def _to_float(self, value) -> float:
+        """
+        从字符串中提取浮点数，过滤掉非数字字符
+        """
+        if value is None:
+            return 0.0
+        if isinstance(value, (int, float)):
+            return float(value)
+        
+        import re
+        try:
+            # 提取第一个匹配的数字部分（包含小数点）
+            match = re.search(r"[-+]?\d*\.?\d+", str(value))
+            if match:
+                return float(match.group())
+            return 0.0
+        except:
+            return 0.0
+
     async def init_db(self):
         await self.db.init_db()
 
@@ -163,10 +182,23 @@ class AiTeJiYiChongService:
                 # 处理 piles 字段
                 piles_data = station.get("piles")
                 total, free = 0, 0
+                standardized_piles = []
                 if isinstance(piles_data, list):
-                    for p in piles_data:
-                        total += int(p.get("total", 0))
-                        free += int(p.get("free", 0))
+                    for idx, p in enumerate(piles_data):
+                        try:
+                            t = int(p.get("total", 0))
+                            f = int(p.get("free", 0))
+                            total += t
+                            free += f
+                            standardized_piles.append({
+                                "pile_no": f"G{idx+1}",
+                                "type": p.get("type", "未知"),
+                                "power": "",
+                                "status_text": f"空闲{f}/总{t}",
+                                "remark": "列表页VL"
+                            })
+                        except:
+                            pass
 
                 await self.station_status_model.save(
                     session=session,
@@ -174,8 +206,8 @@ class AiTeJiYiChongService:
                     station_hash=station_hash,
                     total_piles=total,
                     free_piles=free,
-                    piles_detail_json=piles_data,
-                    current_price=float(station.get("price", 0)) if station.get("price") else 0.0,
+                    piles_detail_json=standardized_piles if standardized_piles else None,
+                    current_price=self._to_float(station.get("price")),
                     parking_info=station.get("parking", ""),
                     distance=station.get("distance", ""),
                     valid_start_time=now
@@ -234,10 +266,23 @@ class AiTeJiYiChongService:
                 # 处理 piles 字段
                 piles_data = station.get("piles")
                 total, free = 0, 0
+                standardized_piles = []
                 if isinstance(piles_data, list):
-                    for p in piles_data:
-                        total += int(p.get("total", 0))
-                        free += int(p.get("free", 0))
+                    for idx, p in enumerate(piles_data):
+                        try:
+                            t = int(p.get("total", 0))
+                            f = int(p.get("free", 0))
+                            total += t
+                            free += f
+                            standardized_piles.append({
+                                "pile_no": f"G{idx+1}",
+                                "type": p.get("type", "未知"),
+                                "power": "",
+                                "status_text": f"空闲{f}/总{t}",
+                                "remark": "列表页VL"
+                            })
+                        except:
+                            pass
 
                 await self.station_status_model.save(
                     session=session,
@@ -245,8 +290,8 @@ class AiTeJiYiChongService:
                     station_hash=station_hash,
                     total_piles=total,
                     free_piles=free,
-                    piles_detail_json=piles_data,
-                    current_price=float(station.get("price", 0)) if station.get("price") else 0.0,
+                    piles_detail_json=standardized_piles if standardized_piles else None,
+                    current_price=self._to_float(station.get("price")),
                     parking_info=station.get("parking", ""),
                     distance=station.get("distance", ""),
                     valid_start_time=now