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