feat: 产品参数爬取系统 v1.0.0

功能:
- 多步骤爬取流程（入口页→列表页→详情页）
- 浏览器爬虫支持（Playwright，处理JS渲染）
- 比亚迪汽车爬虫示例
- 后台管理界面
- 数据存储和导出

技术栈:
- Python 3 + Flask
- Playwright (浏览器自动化)
- BeautifulSoup (HTML解析)

端口:
- API服务: 19011
- 后台管理: 19012

config/settings.py

@@ -0,0 +1,77 @@
+"""
+产品参数爬取系统 - 配置文件
+"""
+
+# 服务配置
+SERVER_CONFIG = {
+    "host": "0.0.0.0",
+    "port": 19011,
+    "debug": True,
+}
+
+ADMIN_CONFIG = {
+    "host": "0.0.0.0",
+    "port": 19012,
+    "debug": True,
+}
+
+# 爬虫配置
+CRAWLER_CONFIG = {
+    "timeout": 30,
+    "retry_times": 3,
+    "retry_delay": 2,
+    "concurrent_limit": 3,  # 并发限制
+    "request_delay": 1,     # 请求间隔（秒）
+    "user_agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36",
+}
+
+# 数据存储
+DATA_DIR = "data"
+PRODUCTS_FILE = "products.json"
+TASKS_FILE = "tasks.json"
+
+# 浏览器配置
+BROWSER_CONFIG = {
+    "headless": True,
+    "timeout": 30000,
+}
+
+# 爬虫任务配置示例
+DEFAULT_SPIDERS = {
+    "byd": {
+        "name": "比亚迪汽车",
+        "enabled": True,
+        "start_url": "https://www.byd.com/cn/",
+        "steps": [
+            {
+                "name": "获取车型列表",
+                "type": "browser",
+                "url": "https://www.byd.com/cn/",
+                "wait_for": ".car-list",
+                "parse": {
+                    "type": "css",
+                    "selector": ".car-item a",
+                    "extract": {
+                        "name": "text",
+                        "url": "href"
+                    }
+                }
+            },
+            {
+                "name": "获取车型详情",
+                "type": "browser",
+                "url_from": "previous.url",
+                "wait_for": ".car-detail",
+                "parse": {
+                    "type": "css",
+                    "selector": ".param-item",
+                    "extract": {
+                        "param_name": ".name::text",
+                        "param_value": ".value::text"
+                    }
+                }
+            }
+        ],
+        "schedule": "0 2 * * *",  # 每天凌晨2点
+    }
+}