Java实现网路爬虫爬取新闻信息

Java实现网路爬虫爬取新闻信息，运用了正则匹配，后台使用Spring+SpringMVC+Mybatis+Mysql

package com.ssm.controller;

import org.springframework.beans.factory.annotation.Autowired;
import org.springframework.stereotype.Controller;
import org.springframework.web.bind.annotation.PathVariable;
import org.springframework.web.bind.annotation.RequestMapping;
import org.springframework.web.bind.annotation.RequestMethod;
import org.springframework.web.servlet.ModelAndView;

import com.ssm.service.NewsService;

@Controller
public class NewsController {

	@Autowired
	private NewsService newsService;

	@RequestMapping（“/home“）
	public String home（） {
		return “home“;
	}

	@RequestMapping（value = “/findPageNews/{pageId}“ method = RequestMethod.GET）
	public ModelAndView findPageNews（@PathVariable（“pageId“） int pageId）
			throws Exception {
		String json = newsService.findPageNews（pageId）;
		ModelAndView modelAndView = new ModelAndView（）;
		modelAndView.addobject（“json“ json）;
		modelAndView.setViewName（“home“）;
		System.out.println（json）;
		return modelAndView;
	}
}

 属性            大小     日期    时间   名称
----------- ---------  ---------- -----  ----

     文件        841  2016-07-22 09:26  SCU_News_Notice\.classpath

     文件       1048  2016-07-22 09:26  SCU_News_Notice\.project

     文件        503  2016-07-22 09:26  SCU_News_Notice\.settings\.jsdtscope

     文件        199  2016-07-27 17:24  SCU_News_Notice\.settings\org.eclipse.core.resources.prefs

     文件        364  2016-07-22 09:26  SCU_News_Notice\.settings\org.eclipse.jdt.core.prefs

     文件        497  2016-07-22 09:26  SCU_News_Notice\.settings\org.eclipse.wst.common.component

     文件        345  2016-07-22 09:26  SCU_News_Notice\.settings\org.eclipse.wst.common.project.facet.core.xml

     文件         49  2016-07-22 09:26  SCU_News_Notice\.settings\org.eclipse.wst.jsdt.ui.superType.container

     文件          6  2016-07-22 09:26  SCU_News_Notice\.settings\org.eclipse.wst.jsdt.ui.superType.name

     文件       1172  2016-07-26 11:47  SCU_News_Notice\build\classes\com\ssm\controller\converter\CustomDateConverter.class

     文件       1799  2016-07-26 11:47  SCU_News_Notice\build\classes\com\ssm\controller\NewsController.class

     文件        122  2016-07-26 11:47  SCU_News_Notice\build\classes\com\ssm\mapper\AcademyMapper.class

     文件        615  2016-07-26 11:47  SCU_News_Notice\build\classes\com\ssm\mapper\NewsMapper.class

     文件       1819  2016-07-26 11:14  SCU_News_Notice\build\classes\com\ssm\mapper\NewsMapper.xml

     文件        120  2016-07-26 11:47  SCU_News_Notice\build\classes\com\ssm\mapper\NoticeMapper.class

     文件        711  2016-07-26 11:47  SCU_News_Notice\build\classes\com\ssm\po\Academy.class

     文件       1707  2016-07-26 11:47  SCU_News_Notice\build\classes\com\ssm\po\News.class

     文件       1349  2016-07-26 11:47  SCU_News_Notice\build\classes\com\ssm\po\Notice.class

     文件       2080  2016-07-26 11:47  SCU_News_Notice\build\classes\com\ssm\service\impl\NewsServiceImpl.class

     文件        618  2016-07-26 11:47  SCU_News_Notice\build\classes\com\ssm\service\NewsService.class

     文件       7809  2016-07-28 10:57  SCU_News_Notice\build\classes\com\ssm\service\task\Spider.class

     文件       1309  2016-07-26 11:47  SCU_News_Notice\build\classes\com\ssm\utils\EncoderUtil.class

     文件       1686  2016-07-26 15:29  SCU_News_Notice\build\classes\com\ssm\utils\FileUtil.class

     文件       3850  2016-07-27 17:24  SCU_News_Notice\build\classes\com\ssm\utils\HttpUtil.class

     文件       4179  2016-07-26 11:47  SCU_News_Notice\build\classes\test\dao\MyBatisDao.class

     文件        585  2016-07-24 12:04  SCU_News_Notice\src\com\ssm\controller\converter\CustomDateConverter.java

     文件       1016  2016-07-24 15:36  SCU_News_Notice\src\com\ssm\controller\NewsController.java

     文件         66  2016-07-22 09:31  SCU_News_Notice\src\com\ssm\mapper\AcademyMapper.java

     文件        659  2016-07-24 12:14  SCU_News_Notice\src\com\ssm\mapper\NewsMapper.java

     文件       1819  2016-07-26 11:14  SCU_News_Notice\src\com\ssm\mapper\NewsMapper.xml

............此处省略497个文件信息