'commit'

Apps/TelaiDian/Crawler.py

@@ -0,0 +1,127 @@
+# coding=utf-8
+import asyncio
+import logging
+import os
+import sys
+import time
+from Apps.TelaiDian.Kit import take_screenshot, get_image_content_md5, clean_station_name
+from Apps.TelaiDian.ReadImageKit import ReadImageKit
+from Apps.TelaiDian.Service import TelaiDianService
+from Apps.TelaiDian.Config.Setting import (
+    SCROLL_DISTANCE_RATIO, WAIT_AFTER_SCROLL, MAX_STATIONS_COUNT,
+    SAFE_EXCLUDE_RATIO, BOTTOM_SAFE_EXCLUDE_RATIO, WAIT_DETAIL_PAGE_LOAD,
+    WAIT_BACK_TO_LIST
+)
+from Core.BaseCrawler import BaseCrawler
+import uiautomator2 as u2
+
+# 项目根目录处理
+project_root = os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+if project_root not in sys.path:
+    sys.path.append(project_root)
+
+logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(name)s - %(levelname)s - %(message)s')
+logger = logging.getLogger("TelaiDianCrawler")
+
+class TelaiDianCrawler(BaseCrawler):
+    def __init__(self, service=None):
+        super().__init__(service or TelaiDianService())
+        self.read_image_kit = ReadImageKit()
+
+    async def start(self):
+        """
+        实现 BaseCrawler 的启动入口
+        """
+        success = await self.open_app()
+        if not success:
+            logger.error("打开特来电小程序失败。")
+            return
+
+        d = u2.connect()
+        await self.crawl_list_logic(d)
+
+    async def open_app(self):
+        """
+        打开特来电小程序
+        """
+        from Apps.TelaiDian import Opener
+        return await Opener.open_mini_program()
+
+    async def crawl_list_logic(self, d):
+        processed_count = 0
+        last_md5 = None
+        
+        while processed_count < MAX_STATIONS_COUNT:
+            # 1. 截图并分析
+            screenshot_path = take_screenshot(d, f"tld_list_{int(time.time())}.jpg")
+            
+            # 检测是否滚动到底部
+            curr_md5 = get_image_content_md5(screenshot_path, top_ratio=SAFE_EXCLUDE_RATIO, bottom_ratio=BOTTOM_SAFE_EXCLUDE_RATIO)
+            if last_md5 == curr_md5:
+                logger.info("内容无变化，判定已到底部")
+                if os.path.exists(screenshot_path): os.remove(screenshot_path)
+                break
+            last_md5 = curr_md5
+            
+            stations = await self.read_image_kit.analyze_station_list(screenshot_path)
+            if not stations:
+                logger.info("本页未检测到场站，尝试滑动...")
+                d.swipe_ext("up", scale=SCROLL_DISTANCE_RATIO)
+                await asyncio.sleep(WAIT_AFTER_SCROLL)
+                continue
+            
+            for station in stations:
+                if processed_count >= MAX_STATIONS_COUNT:
+                    break
+                
+                name = station.get("name")
+                point = station.get("point")
+                
+                if not name or not point:
+                    continue
+                
+                logger.info(f"处理场站: {name}")
+                
+                # 点击进入详情
+                d.click(point[0], point[1])
+                await asyncio.sleep(WAIT_DETAIL_PAGE_LOAD)
+                
+                # 爬取详情
+                await self.crawl_detail_logic(d, station)
+                
+                # 返回列表
+                d.press("back")
+                await asyncio.sleep(WAIT_BACK_TO_LIST)
+                processed_count += 1
+            
+            # 滑动到下一页
+            d.swipe_ext("up", scale=SCROLL_DISTANCE_RATIO)
+            await asyncio.sleep(WAIT_AFTER_SCROLL)
+            
+            if os.path.exists(screenshot_path): os.remove(screenshot_path)
+
+    async def crawl_detail_logic(self, d, station_info):
+        """
+        在详情页提取价格和状态信息
+        """
+        screenshot_path = take_screenshot(d, f"tld_detail_{int(time.time())}.jpg")
+        
+        # 1. 提取价格
+        prices = await self.read_image_kit.analyze_detail_price(screenshot_path)
+        
+            # 2. 保存数据
+        if prices:
+            station_name = clean_station_name(station_info.get("name"))
+            address = station_info.get("address")
+            
+            logger.info(f"场站 {station_name} 提取到 {len(prices)} 条价格信息，准备保存...")
+            await self.service.save_station_data(station_name, address, prices)
+        
+        if os.path.exists(screenshot_path): os.remove(screenshot_path)
+
+async def main(service=None):
+    crawler = TelaiDianCrawler(service=service)
+    await crawler.start()
+
+if __name__ == "__main__":
+    asyncio.run(main())