推荐脚本+分页处理

schoolNewsCrawler/crawler/xhw/XhwCommend.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.commend()
+        # 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/XhwCrawler.py

@@ -348,11 +348,7 @@ class XhwCrawler(BaseCrawler):
 
         title = head_div.find_element(By.CSS_SELECTOR, "h1").text
         news_item.title = title
-        
-        # 内容
-        try:
-            article_div = self.driver.find_element(By.CSS_SELECTOR, "div.main.clearfix")
-            content_div = article_div.find_element(By.CSS_SELECTOR, "div#detail span#detailContent")
+        def parse_content(content_div):
             children = content_div.find_elements(By.XPATH, "./*")
             for child in children:
                 try:
@@ -401,6 +397,27 @@ class XhwCrawler(BaseCrawler):
                 except Exception as e:
                     logger.warning(f"解析段落失败: {e}")
                     continue
+        # 内容
+        try:
+            article_div = self.driver.find_element(By.CSS_SELECTOR, "div.main.clearfix")
+            content_div = article_div.find_element(By.CSS_SELECTOR, "div#detail span#detailContent")
+            parse_content(content_div)
+
+            page_div = content_div.find_element(By.CSS_SELECTOR, "center.xinhuaPager")
+            page_urls = []
+            if page_div:
+                page_as = page_div.find_elements(By.CSS_SELECTOR, "span#xinhuaPagerBox > a")
+                for page_a in page_as:
+                    page_url = page_a.get_attribute("href")
+                    if page_url and not page_url.startswith("http"):
+                        page_url = self._normalize_url(page_url)
+                    page_urls.append(page_url)
+                for page_url in page_urls:
+                    self.driver.get(page_url)
+                    time.sleep(2)
+                    content_div = self.driver.find_element(By.CSS_SELECTOR, "div#detail span#detailContent")
+                    parse_content(content_div)
+        
         except:
             logger.warning(f"新闻内容解析失败: {url}")