chromedriver

schoolNewsCrawler/crawler/BaseCrawler.py

@@ -2,7 +2,8 @@
 from typing import Callable, Dict, Optional, List, Any, Union
 from abc import ABC, abstractmethod
 import requests
-from bs4 import BeautifulSoup, NavigableString
+from bs4 import BeautifulSoup
+from bs4.element import Tag, NavigableString
 from loguru import logger
 from pydantic import BaseModel, Field, HttpUrl
 import json
@@ -45,6 +46,7 @@ class NewsItem(BaseModel):
     title: str = Field(..., description="新闻标题")
     contentRows: List[Dict[str, Any]] = Field(..., description="新闻内容")
     url: str = Field(..., description="新闻链接")
+    viewCount: Optional[int] = Field(default=None, description="浏览数")
     publishTime: Optional[str] = Field(default=None, description="发布时间")
     author: Optional[str] = Field(default=None, description="作者")
     source: Optional[str] = Field(default=None, description="来源")