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
-        
+        def parse_content(content_div):
-        # 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")
             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}")
 

schoolNewsCrawler/test.ipynb

@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 19,
    "id": "948be230",
    "metadata": {},
    "outputs": [
@@ -41,7 +41,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 20,
    "id": "31a8a0dd",
    "metadata": {},
    "outputs": [
@@ -49,9 +49,9 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "\u001b[32m2025-11-20 15:39:21.410\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36mcrawler.BaseCrawler\u001b[0m:\u001b[36m__init__\u001b[0m:\u001b[36m71\u001b[0m - \u001b[1m初始化爬虫: XhwCrawler\u001b[0m\n",
+      "\u001b[32m2025-11-20 16:06:16.802\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36mcrawler.BaseCrawler\u001b[0m:\u001b[36m__init__\u001b[0m:\u001b[36m71\u001b[0m - \u001b[1m初始化爬虫: XhwCrawler\u001b[0m\n",
-      "\u001b[32m2025-11-20 15:39:22.502\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36mcrawler.xhw.XhwCrawler\u001b[0m:\u001b[36m_init_driver\u001b[0m:\u001b[36m20\u001b[0m - \u001b[1mChrome浏览器初始化成功\u001b[0m\n",
+      "\u001b[32m2025-11-20 16:06:17.899\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36mcrawler.xhw.XhwCrawler\u001b[0m:\u001b[36m_init_driver\u001b[0m:\u001b[36m20\u001b[0m - \u001b[1mChrome浏览器初始化成功\u001b[0m\n",
-      "\u001b[32m2025-11-20 15:39:22.502\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36mcrawler.xhw.XhwCrawler\u001b[0m:\u001b[36m_init_driver\u001b[0m:\u001b[36m24\u001b[0m - \u001b[1m访问主页获取初始Cookie\u001b[0m\n"
+      "\u001b[32m2025-11-20 16:06:17.900\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36mcrawler.xhw.XhwCrawler\u001b[0m:\u001b[36m_init_driver\u001b[0m:\u001b[36m24\u001b[0m - \u001b[1m访问主页获取初始Cookie\u001b[0m\n"
      ]
     }
    ],
@@ -61,7 +61,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 21,
    "id": "e5a6e91c",
    "metadata": {},
    "outputs": [],
@@ -76,7 +76,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 22,
    "id": "7e0f56fa",
    "metadata": {},
    "outputs": [],
@@ -86,45 +86,35 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 26,
    "id": "47327ebf",
    "metadata": {},
-   "outputs": [],
-   "source": [
-    "#crawler.parse_xh_news_detail(\"https://www.news.cn/politics/leaders/20250224/5384be3d47c643b3a68e3bb724656152/c.html\")\n",
-    "# crawler.parse_xh_news_detail(\"https://www.news.cn/politics/leaders/20240207/2819fe60663140eab9599581dcae8c1e/c.html\") #视频"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 17,
-   "id": "fa359d5b",
-   "metadata": {},
    "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\u001b[32m2025-11-20 15:45:21.322\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36mcrawler.xhw.XhwCrawler\u001b[0m:\u001b[36mcommend\u001b[0m:\u001b[36m44\u001b[0m - \u001b[1m轮播图新闻url: 5\u001b[0m\n",
-      "\u001b[32m2025-11-20 15:45:21.483\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36mcrawler.xhw.XhwCrawler\u001b[0m:\u001b[36mcommend\u001b[0m:\u001b[36m54\u001b[0m - \u001b[1m聚焦新闻url: 21\u001b[0m\n",
-      "\u001b[32m2025-11-20 15:45:22.214\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36mcrawler.xhw.XhwCrawler\u001b[0m:\u001b[36mcommend\u001b[0m:\u001b[36m44\u001b[0m - \u001b[1m轮播图新闻url: 7\u001b[0m\n",
-      "\u001b[32m2025-11-20 15:45:23.134\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36mcrawler.xhw.XhwCrawler\u001b[0m:\u001b[36mcommend\u001b[0m:\u001b[36m54\u001b[0m - \u001b[1m聚焦新闻url: 124\u001b[0m\n",
-      "\u001b[32m2025-11-20 15:45:23.135\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36mcrawler.xhw.XhwCrawler\u001b[0m:\u001b[36mcommend\u001b[0m:\u001b[36m55\u001b[0m - \u001b[1m获取到新闻url:157\u001b[0m\n"
-     ]
-    },
     {
      "data": {
       "text/plain": [
-       "ResultDomain(code=0, message='', success=True, data=None, dataList=[])"
+       "NewsItem(title='全国精神文明建设表彰大会在京召开', contentRows=[{'tag': 'img', 'content': \"<img src='https://www.news.cn/photo/20250523/9fc5e377b19047918dfe0eca2aad5c67/202505239fc5e377b19047918dfe0eca2aad5c67_202505232bbfd057329e448b9540fc5dbf050283.jpg' />\"}, {'tag': 'p', 'content': '<p>\\u2003\\u20035月23日，全国精神文明建设表彰大会在北京召开。中央宣传思想文化工作领导小组决定，授予202个城市（区）全国文明城市（区）称号，授予3316个村镇全国文明村镇称号，授予4688个单位全国文明单位称号，授予798户家庭全国文明家庭称号，授予890所学校全国文明校园称号；授予60名（组）同志第九届全国道德模范荣誉称号，授予239名（组）同志第九届全国道德模范提名奖。</p>'}, {'tag': 'p', 'content': '<p>\\u2003\\u2003新华社记者 翟健岚 摄</p>'}, {'tag': 'img', 'content': \"<img src='https://www.news.cn/photo/20250523/9fc5e377b19047918dfe0eca2aad5c67/202505239fc5e377b19047918dfe0eca2aad5c67_20250523ead9d290ee4c45928fc7ca35e227727b.jpg' />\"}, {'tag': 'p', 'content': '<p>\\u2003\\u20035月23日，全国精神文明建设表彰大会在北京召开。中央宣传思想文化工作领导小组决定，授予202个城市（区）全国文明城市（区）称号，授予3316个村镇全国文明村镇称号，授予4688个单位全国文明单位称号，授予798户家庭全国文明家庭称号，授予890所学校全国文明校园称号；授予60名（组）同志第九届全国道德模范荣誉称号，授予239名（组）同志第九届全国道德模范提名奖。</p>'}, {'tag': 'p', 'content': '<p>\\u2003\\u2003新华社记者 翟健岚 摄</p>'}, {'tag': 'img', 'content': \"<img src='https://www.news.cn/photo/20250523/9fc5e377b19047918dfe0eca2aad5c67/202505239fc5e377b19047918dfe0eca2aad5c67_20250523971c4e94467b451c93cd4810992e2025.jpg' />\"}, {'tag': 'p', 'content': '<p>\\u2003\\u20035月23日，全国精神文明建设表彰大会在北京召开。中央宣传思想文化工作领导小组决定，授予202个城市（区）全国文明城市（区）称号，授予3316个村镇全国文明村镇称号，授予4688个单位全国文明单位称号，授予798户家庭全国文明家庭称号，授予890所学校全国文明校园称号；授予60名（组）同志第九届全国道德模范荣誉称号，授予239名（组）同志第九届全国道德模范提名奖。</p>'}, {'tag': 'p', 'content': '<p>\\u2003\\u2003新华社记者 翟健岚 摄</p>'}, {'tag': 'img', 'content': \"<img src='https://www.news.cn/photo/20250523/9fc5e377b19047918dfe0eca2aad5c67/202505239fc5e377b19047918dfe0eca2aad5c67_20250523cf0f3bf322184d339a91049891f265bb.jpg' />\"}, {'tag': 'p', 'content': '<p>\\u2003\\u20035月23日，全国精神文明建设表彰大会在北京召开。中央宣传思想文化工作领导小组决定，授予202个城市（区）全国文明城市（区）称号，授予3316个村镇全国文明村镇称号，授予4688个单位全国文明单位称号，授予798户家庭全国文明家庭称号，授予890所学校全国文明校园称号；授予60名（组）同志第九届全国道德模范荣誉称号，授予239名（组）同志第九届全国道德模范提名奖。</p>'}, {'tag': 'p', 'content': '<p>\\u2003\\u2003新华社记者 翟健岚 摄</p>'}], url='https://www.news.cn/photo/20250523/9fc5e377b19047918dfe0eca2aad5c67/c.html', viewCount=None, publishTime='2025-05-23 18:33:10', author=None, source='新华网', category=None, executeStatus=0, executeMessage=None)"
       ]
      },
-     "execution_count": 17,
+     "execution_count": 26,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "crawler.commend()"
+    "#crawler.parse_xh_news_detail(\"https://www.news.cn/politics/leaders/20250224/5384be3d47c643b3a68e3bb724656152/c.html\")\n",
+    "# crawler.parse_xh_news_detail(\"https://www.news.cn/politics/leaders/20240207/2819fe60663140eab9599581dcae8c1e/c.html\") #视频\n",
+    "crawler.parse_xh_news_detail(\"https://www.news.cn/photo/20250523/9fc5e377b19047918dfe0eca2aad5c67/c.html\") # 分页"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 24,
+   "id": "fa359d5b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# crawler.commend()"
    ]
   },
   {