读取html代码,Java代码库,德仔网

代码语言
代码分类
【Java】读取html
作者:偶喜欢春天 / 发布于2014/7/2/ 550

	package test;
	import java.io.BufferedReader;
	import java.io.IOException;
	import java.io.InputStreamReader;
	import java.net.MalformedURLException;
	import java.net.URL;
	import java.util.ArrayList;
	import java.util.HashMap;
	import java.util.List;
	import java.util.regex.Matcher;
	import java.util.regex.Pattern;

	public class WebContent
	{

	public String getOneHtml(final String htmlurl) throws IOException
	{
	URL url;
	String temp;
	final StringBuffer sb = new StringBuffer();
	try
	{
	 url = new URL(htmlurl);
	 final BufferedReader in = new BufferedReader(new InputStreamReader(url.openStream(), "utf-8"));// 读取网页全部内容
	 while ((temp = in.readLine()) != null)
	 {
	 sb.append(temp);
	 }
	 in.close();
	}
	catch (final MalformedURLException me)
	{
	 System.out.println("你输入的URL格式有问题！请仔细输入");
	 me.getMessage();
	 throw me;
	}
	catch (final IOException e)
	{
	 e.printStackTrace();
	 throw e;
	}
	return sb.toString();
	}

	public String getTitle(final String s)
	{
	String regex;
	String title = "";
	final List<String> list = new ArrayList<String>();
	regex = "<title>.*?</title>";
	final Pattern pa = Pattern.compile(regex, Pattern.CANON_EQ);
	final Matcher ma = pa.matcher(s);
	while (ma.find())
	{
	 list.add(ma.group());
	}
	for (int i = 0; i < list.size(); i++)
	{
	 title = title + list.get(i);
	}
	return outTag(title);
	}

	public List<String> getLink(final String s)
	{
	String regex;
	final List<String> list = new ArrayList<String>();
	regex = "<a[^>]*href=("([^"]*)"|\'([^\']*)\'|([^\\s>]*))[^>]*>(.*?)</a>";
	final Pattern pa = Pattern.compile(regex, Pattern.DOTALL);
	final Matcher ma = pa.matcher(s);
	while (ma.find())
	{
	 list.add(ma.group());
	}
	return list;
	}

	public List<String> getScript(final String s)
	{
	String regex;
	final List<String> list = new ArrayList<String>();
	regex = "<script.*?</script>";
	final Pattern pa = Pattern.compile(regex, Pattern.DOTALL);
	final Matcher ma = pa.matcher(s);
	while (ma.find())
	{
	 list.add(ma.group());
	}
	return list;
	}

	public List<String> getCSS(final String s)
	{
	String regex;
	final List<String> list = new ArrayList<String>();
	regex = "<style.*?</style>";
	final Pattern pa = Pattern.compile(regex, Pattern.DOTALL);
	final Matcher ma = pa.matcher(s);
	while (ma.find())
	{
	 list.add(ma.group());
	}
	return list;
	}

	public String outTag(final String s)
	{
	return s.replaceAll("<.*?>", "");
	}

	public HashMap<String, String> getFromYahoo(final String s)
	{
	final HashMap<String, String> hm = new HashMap<String, String>();
	final StringBuffer sb = new StringBuffer();
	String html = "";
	System.out.println("\n------------------开始读取网页(" + s + ")--------------------");
	try
	{
	 html = getOneHtml(s);
	}
	catch (final Exception e)
	{
	 e.getMessage();
	}
	// System.out.println(html);
	System.out.println("------------------读取网页(" + s + ")结束--------------------\n");
	System.out.println("------------------分析(" + s + ")结果如下--------------------\n");
	String title = outTag(getTitle(html));
	title = title.replaceAll("_雅虎知识堂", "");
	// Pattern pa=Pattern.compile("<div
	// class="original">(.*?)((\r\n)*)(.*?)((\r\n)*)(.*?)</div>",Pattern.DOTALL);
	final Pattern pa = Pattern.compile("<div class="original">(.*?)</div>", Pattern.DOTALL);
	final Matcher ma = pa.matcher(html);
	while (ma.find())
	{
	 sb.append(ma.group());
	}
	String temp = sb.toString();
	temp = temp.replaceAll("()+?", "\n");// 转化换行
	temp = temp.replaceAll("<em>.*?</em>", "");// 去图片注释
	hm.put("title", title);
	hm.put("original", outTag(temp));
	return hm;
	}

	public static void main(final String args[])
	{
	String url = "";
	final List<String> list = new ArrayList<String>();
	System.out.print("输入URL，一行一个，输入结束后输入 go 程序开始运行: \n");

	final BufferedReader br = new BufferedReader(new InputStreamReader(System.in));
	try
	{
	 while (!(url = br.readLine()).equals("go"))
	 {
	 list.add(url);
	 }
	}
	catch (final Exception e)
	{
	 e.getMessage();
	}
	final WebContent wc = new WebContent();
	HashMap<String, String> hm = new HashMap<String, String>();
	for (int i = 0; i < list.size(); i++)
	{
	 hm = wc.getFromYahoo(list.get(i));
	 System.out.println("标题： " + hm.get("title"));
	 System.out.println("内容： \n" + hm.get("original"));
	}

	// System.out.println(htmlurl+"网页内容结束");

	}
	}
评论列表
本站所提供的代码，版权归原作者所有，若有侵犯作者版权，请与我们联系，我们将立即删除或修改。谢谢!
本站所有代码发布及提供者。
试试其它关键字
　读取html　
同语言下
可能有用的
偶喜欢春天贡献的其它代码(18)