schoolNews/schoolNewsCrawler/test.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "948be230",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "项目根目录: f:\\Project\\schoolNews\n",
      "✓ 已启用自动重载模块功能 - 修改 .py 文件后会自动生效\n"
     ]
    }
   ],
   "source": [
    "# 自动重载模块（当文件修改后自动刷新）\n",
    "%reload_ext autoreload\n",
    "%autoreload 2\n",
    "\n",
    "import sys\n",
    "import os\n",
    "\n",
    "# 先添加项目根目录到路径（必须在导入之前）\n",
    "project_root = os.path.abspath(os.path.join(os.getcwd(), '..'))\n",
    "if project_root not in sys.path:\n",
    "    sys.path.insert(0, project_root)\n",
    "\n",
    "# 然后再导入模块\n",
    "from crawler.xhw.XhwCrawler import XhwCrawler\n",
    "from crawler.BaseCrawler import NewsItem\n",
    "from loguru import logger\n",
    "import json\n",
    "from pprint import pprint\n",
    "\n",
    "print(f\"项目根目录: {project_root}\")\n",
    "print(\"✓ 已启用自动重载模块功能 - 修改 .py 文件后会自动生效\")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "31a8a0dd",
   "metadata": {},
   "outputs": [
    {
     "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 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 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"
     ]
    }
   ],
   "source": [
    "crawler = XhwCrawler()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "e5a6e91c",
   "metadata": {},
   "outputs": [],
   "source": [
    "#crawler.search(\"大学\", 1)\n",
    "# crawler.search(\"中国\", 10, \"xhsz\")\n",
    "# crawler.search(\"中国\", 10, \"news\")\n",
    "# crawler.search(\"中国\", 10, \"xhsz\")\n",
    "# crawler.search(\"中国\", 10, \"news\")\n",
    "# crawler.search(\"中国\", 10, \"news\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "7e0f56fa",
   "metadata": {},
   "outputs": [],
   "source": [
    "# crawler.parse_xhsz_news_detail(\"https://xhsz.news.cn/focus_news/detail?id=9752\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "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=[])"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "crawler.commend()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "ebabbd5b",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "schoolNewsCrawler",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.12.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}