'commit'

.idea/Crawler.iml

@@ -1,14 +0,0 @@
-<?xml version="1.0" encoding="UTF-8"?>
-<module type="PYTHON_MODULE" version="4">
-  <component name="NewModuleRootManager">
-    <content url="file://$MODULE_DIR$">
-      <excludeFolder url="file://$MODULE_DIR$/venv" />
-    </content>
-    <orderEntry type="jdk" jdkName="D:\anaconda3\envs\py310" jdkType="Python SDK" />
-    <orderEntry type="sourceFolder" forTests="false" />
-  </component>
-  <component name="PyDocumentationSettings">
-    <option name="format" value="PLAIN" />
-    <option name="myDocStringFormat" value="Plain" />
-  </component>
-</module>

.idea/modules.xml

@@ -2,7 +2,7 @@
 <project version="4">
   <component name="ProjectModuleManager">
     <modules>
-      <module fileurl="file://$PROJECT_DIR$/.idea/Crawler.iml" filepath="$PROJECT_DIR$/.idea/Crawler.iml" />
+      <module fileurl="file://$PROJECT_DIR$/.idea/aIData.iml" filepath="$PROJECT_DIR$/.idea/aIData.iml" />
     </modules>
   </component>
 </project>

Apps/AiTeJiYiChong/Crawler.py

@@ -74,11 +74,11 @@ async def get_station_list(d, service, max_scrolls=MAX_SCROLLS):
         logger.info("正在执行图形学切片分析...")
         json_data = Kit.crop_cards_from_image(screenshot_path)
         
-        # 3. 调用 VL 模型识别并保存数据
-        stations = await service.process_station_list_vl(screenshot_path, device_info=device_info)
+        # 3. 调用混合模式识别 (图形学切片 + 本地 OCR)
+        stations = await service.process_station_list_hybrid(screenshot_path, device_info=device_info)
         logger.info(f"本页识别到 {len(stations)} 个场站")
 
-        # 4. 匹配几何卡片与 VL 识别结果
+        # 4. 匹配几何卡片与识别结果 (混合模式下已经包含在 stations 中，但为了兼容旧逻辑进行填充)
         if json_data and json_data.get("cards") and stations:
             for card in json_data["cards"]:
                 card_rect = card["rect"] # [x1, y1, x2, y2]

Apps/AiTeJiYiChong/Opener.py

@@ -27,18 +27,9 @@ async def open_mini_program():
     await asyncio.sleep(5)
 
     # 2. 确保在消息列表页并点击搜索
-    logger.info("尝试查找并点击 '搜索按钮'...")
-    # 优先尝试从 XinDianTu 的模板中复用 SearchButton.jpg (如果存在)
-    search_template = os.path.join(os.path.dirname(BASE_DIR), "XinDianTu", "Templates", "SearchButton.jpg")
-    if not os.path.exists(search_template):
-        search_template = os.path.join(BASE_DIR, "Templates", "SearchButton.jpg")
-
-    if click_image_template(d, search_template):
-        logger.info("点击了搜索按钮")
-    else:
-        logger.warning("未找到搜索按钮，使用坐标点击 (84%, 8%)")
-        w, h = d.window_size()
-        d.click(int(w * 0.84), int(h * 0.08))
+    logger.info("直接使用坐标点击 '搜索按钮' (84%, 8%)...")
+    w, h = d.window_size()
+    d.click(int(w * 0.84), int(h * 0.08))
 
     await asyncio.sleep(2)
 

Apps/AiTeJiYiChong/ReadImageKit.py

@@ -7,6 +7,7 @@ import json
 import aiohttp
 import logging
 import base64
+import cv2
 from openai import AsyncOpenAI, BadRequestError
 from Config.Config import (
     ALY_LLM_API_KEY, VL_MODEL_NAME, VL_MODEL_NAME_AD
@@ -15,6 +16,8 @@ from Apps.AiTeJiYiChong.Config.Setting import (
     SAFE_EXCLUDE_RATIO, FALLBACK_WIDTH, FALLBACK_HEIGHT,
     BOTTOM_SAFE_EXCLUDE_RATIO
 )
+from Util.PaddleOCRKit import get_ocr_kit
+from Apps.AiTeJiYiChong import Kit
 
 logger = logging.getLogger(__name__)
 
@@ -287,6 +290,65 @@ class ReadImageKit:
             logger.error(f"Error calling VL model for detail: {e}")
             return None
 
+    @classmethod
+    async def get_stations_hybrid(cls, image_path: str, device_info=None):
+        """
+        混合识别模式：图形学切片 + 本地 PaddleOCR 识别
+        """
+        if not os.path.exists(image_path):
+            logger.error(f"Image not found: {image_path}")
+            return []
+
+        # 1. 使用 Kit 中的图形学算法识别卡片区域
+        # Kit.crop_cards_from_image 会生成 .json, _flag.jpg, _vl.jpg
+        # 我们主要需要它返回的 json_data
+        json_data = Kit.crop_cards_from_image(image_path, save_debug=True)
+        if not json_data or not json_data.get("cards"):
+            logger.warning("No cards detected by graphical slicing.")
+            return []
+
+        img = Image.open(image_path).convert("RGB")
+        ocr_kit = get_ocr_kit()
+        
+        final_stations = []
+        
+        # 2. 对每个卡片区域进行 OCR 识别
+        # 注意：PaddleOCR 识别过程较快，且通常不涉及网络请求，可以根据需要选择并行或串行
+        # 这里使用串行以保证日志输出整齐，如果追求极致性能可改用 asyncio.to_thread 并行
+        for card in json_data["cards"]:
+            rect = card["rect"] # [x1, y1, x2, y2]
+            # 裁剪卡片
+            patch = img.crop((rect[0], rect[1], rect[2], rect[3]))
+            
+            # 转换为 ndarray 供 PaddleOCR 使用
+            patch_cv = cv2.cvtColor(np.array(patch), cv2.COLOR_RGB2BGR)
+            
+            # OCR 识别
+            logger.info(f"正在识别卡片 {card['id']}: {rect}")
+            res = ocr_kit.recognize(patch_cv)
+            
+            if res and res.get("station_name"):
+                # 注入点击坐标和原始区域信息
+                res["uia_center_x"] = card["click_point"][0]
+                res["uia_center_y"] = card["click_point"][1]
+                res["rect"] = rect
+                
+                # 转换 bounds 到 0-1000 空间（保持与 VL 模式兼容）
+                w, h = img.size
+                res["bounds"] = [
+                    int(rect[0] * 1000 / w),
+                    int(rect[1] * 1000 / h),
+                    int(rect[2] * 1000 / w),
+                    int(rect[3] * 1000 / h)
+                ]
+                
+                final_stations.append(res)
+                logger.info(f"卡片 {card['id']} 识别成功: {res['station_name']}")
+            else:
+                logger.warning(f"卡片 {card['id']} 识别失败或无名称")
+
+        return final_stations
+
     @classmethod
     async def get_stations_from_image(cls, image_path: str, device_info=None):
         """

Apps/AiTeJiYiChong/Service.py

@@ -125,6 +125,69 @@ class AiTeJiYiChongService:
         logger.info(f"场站详情处理完成: {name}")
         return detail
 
+    async def process_station_list_hybrid(self, image_path, device_info=None) -> list:
+        """
+        基于混合模式处理场站列表 (图形学切片 + 本地 OCR)
+        """
+        station_list = await ReadImageKit.get_stations_hybrid(image_path, device_info=device_info)
+        if not station_list:
+            return []
+
+        processed_stations = []
+        async with await self.db.get_session() as session:
+            for station in station_list:
+                name = station.get("station_name")
+                if not name:
+                    continue
+
+                station_hash = self.get_hash(name)
+                now = datetime.now()
+                station["station_hash"] = station_hash
+                
+                # 1. 保存 Profile
+                profile_id = self.generate_id()
+                await self.station_profile_model.save(
+                    session=session,
+                    id=profile_id,
+                    station_hash=station_hash,
+                    operator=self.operator,
+                    station_name=name,
+                    valid_start_time=now
+                )
+                station["profile_id"] = profile_id
+                station["valid_start_time"] = now.isoformat()
+
+                # 2. 保存 Status (解析价格和电桩)
+                status_id = self.generate_id()
+                
+                # 处理 piles 字段
+                piles_data = station.get("piles")
+                total, free = 0, 0
+                if isinstance(piles_data, list):
+                    for p in piles_data:
+                        total += int(p.get("total", 0))
+                        free += int(p.get("free", 0))
+
+                await self.station_status_model.save(
+                    session=session,
+                    id=status_id,
+                    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,
+                    parking_info=station.get("parking", ""),
+                    distance=station.get("distance", ""),
+                    valid_start_time=now
+                )
+                station["status_id"] = status_id
+                
+                processed_stations.append(station)
+            
+            await session.commit()
+            
+        return processed_stations
+
     async def process_station_list_vl(self, image_path, device_info=None) -> list:
         """
         基于 VL 模式处理场站列表

Apps/AiTeJiYiChong/TestClick.py

@@ -1,41 +0,0 @@
-# coding=utf-8
-import asyncio
-import uiautomator2 as u2
-import os
-import sys
-import uuid
-
-project_root = r"D:\dsWork\aiData"
-if project_root not in sys.path:
-    sys.path.append(project_root)
-
-from Apps.AiTeJiYiChong import Kit
-from Apps.AiTeJiYiChong.Kit import take_screenshot, read_image
-from Config.Config import TEMP_IMAGE_DIR
-
-async def test_click_and_detail():
-    d = u2.connect()
-    image_uuid = str(uuid.uuid4())
-    print(f"Taking initial screenshot...")
-    screenshot_path = take_screenshot(d, image_uuid, save_dir=TEMP_IMAGE_DIR)
-    
-    print(f"Analyzing cards in {screenshot_path}...")
-    json_data = Kit.crop_cards_from_image(screenshot_path)
-    
-    if json_data and json_data.get("cards"):
-        first_card = json_data["cards"][0]
-        click_x, click_y = first_card["click_point"]
-        print(f"Clicking card at ({click_x}, {click_y})...")
-        d.click(click_x, click_y)
-        
-        print("Waiting for detail page...")
-        await asyncio.sleep(5)
-        
-        detail_uuid = f"detail_{image_uuid}"
-        detail_path = take_screenshot(d, detail_uuid, save_dir=TEMP_IMAGE_DIR)
-        print(f"Detail page screenshot: {detail_path}")
-    else:
-        print("No cards found on current screen.")
-
-if __name__ == "__main__":
-    asyncio.run(test_click_and_detail())

Apps/AiTeJiYiChong/说明.txt

@@ -1 +0,0 @@
-微信小程序名称： 艾特吉易充

Config/Config.py

@@ -1,16 +1,16 @@
 # 黄海在公司内网开发时的配置信息
-DORIS_HOST = "10.10.14.204"
-DORIS_PORT = 9030
-DORIS_FENODES = "10.10.14.204:8030"
-REDIS_HOST = '10.10.14.14'
-REDIS_PASSWORD = None  # 如果没有密码则设为 None
+# DORIS_HOST = "10.10.14.204"
+# DORIS_PORT = 9030
+# DORIS_FENODES = "10.10.14.204:8030"
+# REDIS_HOST = '10.10.14.14'
+# REDIS_PASSWORD = None  # 如果没有密码则设为 None
 
 # 黄海在家开发时的配置信息
-#DORIS_HOST = "www.hzkjai.com"
-#DORIS_PORT = 27025
-#DORIS_FENODES = "www.hzkjai.com:27024"
-#REDIS_HOST = '127.0.0.1'
-#REDIS_PASSWORD = "DsideaL147258369"
+DORIS_HOST = "www.hzkjai.com"
+DORIS_PORT = 27025
+DORIS_FENODES = "www.hzkjai.com:27024"
+REDIS_HOST = '127.0.0.1'
+REDIS_PASSWORD = "DsideaL147258369"
 
 # 视觉模型配置
 VL_MODEL_NAME = "qwen3-vl-flash"

Util/OcrParser.py

@@ -50,8 +50,8 @@ class OcrParser:
             
         # 2. 距离 (Distance)
         for line in clean_lines:
-            # 匹配 "7.4km", "17.4km"
-            m = re.search(r"(\d+(\.\d+)?)\s*km", line, re.IGNORECASE)
+            # 匹配 "7.4km", "17.4km", "90m"
+            m = re.search(r"(\d+(\.\d+)?)\s*(km|m)", line, re.IGNORECASE)
             if m:
                 result["distance"] = m.group(0)
                 break

Util/PaddleOCRKit.py

@@ -26,13 +26,23 @@ class PaddleOCRKit:
         Using PP-OCRv4 mobile model for speed.
         """
         try:
+            # 1. 抑制 PaddlePaddle 的日志输出
+            os.environ['GLOG_minloglevel'] = '3'  # 抑制 GLOG (C++) 日志
+            os.environ['FLAGS_allocator_strategy'] = 'auto_growth' # 减少显存占用警告
+            
+            # 2. 抑制 Python 层的 paddle 日志
+            import logging as py_logging
+            py_logging.getLogger('paddle').setLevel(py_logging.ERROR)
+            py_logging.getLogger('ppocr').setLevel(py_logging.ERROR)
+
             logger.info("Initializing PaddleOCR (PP-OCRv4 Mobile)...")
             # use_angle_cls is deprecated, using use_textline_orientation instead
             # ocr_version='PP-OCRv4' defaults to mobile model
             self._ocr = PaddleOCR(
                 use_textline_orientation=True, 
                 lang="ch", 
-                ocr_version='PP-OCRv4'
+                ocr_version='PP-OCRv4',
+                show_log=False  # 关键：关闭 PaddleOCR 内部日志打印
             )
             logger.info("PaddleOCR initialized successfully.")
         except Exception as e: