新华网热点

schoolNewsCrawler/crawler/xhw/XhwCrawler.py

@@ -120,10 +120,8 @@ class XhwCrawler(BaseCrawler):
         
         # 访问主页获取初始Cookie
         logger.info("访问主页获取初始Cookie")
-        logger.info(f"准备访问URL: {self.config.base_url}")
         try:
             driver.get(self.config.base_url)
-            logger.info(f"成功访问URL: {self.config.base_url}")
         except Exception as e:
             logger.error(f"访问URL失败: {self.config.base_url}, 错误: {str(e)}")
             return None
@@ -537,22 +535,41 @@ class XhwCrawler(BaseCrawler):
             resultDomain.success = False
             return resultDomain
 
-
+        # 访问搜索页
+        try:
+            self.driver.get(hot_point_config.url)
+            time.sleep(2)
+        except Exception as e:
+            logger.warning(f"访问搜索页失败: {hot_point_config.url}, {e}")
+            return resultDomain
 
         try:
             # 获取新闻url
             url_base_map = {}
-            
+            news_div = self.driver.find_element(By.CSS_SELECTOR, "section.wrapper > div.page-news.center-1200")
-            
+            hot_news_div = news_div.find_element(By.CSS_SELECTOR, "div.page-news-l")
-            
+
+            news_items_div = hot_news_div.find_element(By.CSS_SELECTOR, "div.page-news-list")
+            news_items = news_items_div.find_elements(By.CSS_SELECTOR, "div.item")
+            for news in news_items:
+                a_tag = news.find_element(By.TAG_NAME, "a")
+                news_url = a_tag.get_attribute("href")
+                news_title = a_tag.text.strip()
+                url_base_map[news_url] = {"title": news_title}
+                news_urls.append(news_url)
+
+                
             # 从新闻url中获取新闻详情
+            count = 0
             for news_url in news_urls:
                 try:
                     news = self.parse_news_detail(news_url)
                     if news:
                         news.title = url_base_map.get(news_url, {}).get("title") or news.title
-                        news.publishTime = url_base_map.get(news_url, {}).get("date") or news.publishTime
                         news_list.append(news)
+                        count += 1
+                        if count >= 5:
+                            break
                 except Exception as e:
                     logger.warning(f"解析新闻失败: {news_url}, {e}")
                     continue

schoolNewsCrawler/crawler/xhw/XhwHotPoint.py

@@ -0,0 +1,88 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+"""
+新华网搜索爬虫命令行工具
+用法: python RmrbSearch.py --key "关键词" --total 10 --type 0
+"""
+
+import argparse
+import json
+import sys
+from pathlib import Path
+import time
+# Add project root directory to path to import crawler
+sys.path.insert(0, str(Path(__file__).parent.parent.parent))
+
+from crawler.xhw.XhwCrawler import XhwCrawler
+from loguru import logger
+
+
+def main():
+    """主函数"""
+    parser = argparse.ArgumentParser(
+        description='新华网新闻搜索工具',
+        formatter_class=argparse.RawDescriptionHelpFormatter,
+        epilog="""
+        """
+    )
+
+
+    parser.add_argument(
+        '--output', '-o',
+        type=str,
+        help='输出文件路径'
+    )
+
+    args = parser.parse_args()
+
+
+    output_file = args.output
+
+    logger.info("使用直接参数模式")
+
+
+    try:
+        crawler = XhwCrawler()
+        time.sleep(5)
+        result = crawler.hot_point()
+        # print(result)
+        output = {
+            "code": result.code,
+            "message": result.message,
+            "success": result.success,
+            "data": None,
+            "dataList": [item.model_dump() for item in result.dataList] if result.dataList else []
+        }
+        # result = None
+        # with open("F:\Project\schoolNews\schoolNewsCrawler\output\output.json", "r", encoding="utf-8") as f:
+        #     result = json.load(f)
+        # print(result)
+        # output = result
+
+        
+        if output_file:
+            output_path = Path(output_file)
+            output_path.parent.mkdir(parents=True, exist_ok=True)
+            with open(output_path, 'w', encoding='utf-8') as f:
+                json.dump(output, f, ensure_ascii=False, indent=2)
+            logger.info(f"结果已保存到: {output_file}")
+
+        crawler.close()
+        sys.exit(0 if result.success else 1)
+        # print(json.dumps(output, ensure_ascii=False, indent=2))
+        # sys.exit(0 if result["success"] else 1)
+    except Exception as e:
+        logger.error(f"执行失败: {str(e)}")
+        error_output = {
+            "code": 500,
+            "message": f"执行失败: {str(e)}",
+            "success": False,
+            "data": None,
+            "dataList": []
+        }
+        print(json.dumps(error_output, ensure_ascii=False, indent=2))
+        sys.exit(1)
+
+
+if __name__ == "__main__":
+    main()

schoolNewsCrawler/crawler/xhw/XhwSearch.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python
 # -*- coding: utf-8 -*-
 """
-人民日报搜索爬虫命令行工具
+新华网搜索爬虫命令行工具
 用法: python RmrbSearch.py --key "关键词" --total 10 --type 0
 """
 
@@ -20,7 +20,7 @@ from loguru import logger
 def main():
     """主函数"""
     parser = argparse.ArgumentParser(
-        description='人民日报新闻搜索工具',
+        description='新华网新闻搜索工具',
         formatter_class=argparse.RawDescriptionHelpFormatter,
         epilog="""
         """