求java爬虫学习实际案例

大家好，我刚开始学习java爬虫，请问有java爬虫学习实际案例吗，谢谢大家帮忙

提供几个学习案例：

1. java爬虫程序简单例子（获取页面所有邮箱地址）

[Java] 纯文本查看 复制代码

这是一段在网页里面爬邮箱地址的代码，可以获得页面里面所有的邮箱地址。

import java.io.*;
import java.util.regex.*;
import java.net.*;
public class Test {
 public static void main(String[] args) throws Exception{
  getMails_1();
 }
 public static void getMails_1() throws Exception
 {
  URL url=new URL(“[url=http://jingyan.baidu.com/article/647f01157ea4ca7f2148a8ce.html]http://jingyan.baidu.com/article/647f01157ea4ca7f2148a8ce.html[/url]”);
  URLConnection Conn=url.openConnection();
  BufferedReader bufin=new BufferedReader(new InputStreamReader(Conn.getInputStream()));
  String line=null;
  String mailreg=”\\w+@\\w+(\\.\\w+)+”;
  Pattern p=Pattern.compile(mailreg);
  while((line=bufin.readLine())!=null){
   Matcher m=p.matcher(line);
   while(m.find()){
    System.out.println(m.group());
   }
  }
 }
}

2. java 爬虫抓取数据一个简单例子。用来备份用的。

[Java] 纯文本查看 复制代码

java 爬虫抓取数据一个简单例子。用来备份用的。 
 
package com.util;
import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.net.HttpURLConnection;
import java.net.URL;
import java.util.ArrayList;
import java.util.HashMap;
import java.util.List;
import java.util.Map;
 
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;
 
public class  BbsTest {
    public static void main(String[] args) {
        Map<String, String> map = new HashMap<String, String>();
        String con;
        try {
            for(int j=5;j<20;j++){
                String url = "http://xxxxxxxxxxxxxxxx.html?page="+j;
                List<String> links = getAllLinks(url);
                for(int i=1;i<links.size();i++){
                    if(map.get(links.get(i))==null){
                        map.put(links.get(i), "true");
                        con = GetWebContent(links.get(i),"utf-8",10000);
                        Document doc = Jsoup.parse(con);
                        String title = getTitle(doc);
                        String content = getContent(doc);
                        System.out.println(title);
                    }
                }
            }
        } catch (IOException e) {
            e.printStackTrace();
        }
    }
     
     
     
    /**
     *网页抓取方法
     * @param urlString      要抓取的url地址
     * @param charset        网页编码方式
     * @param timeout        超时时间
     * <a href="http://my.oschina.net/u/556800" class="referer" target="_blank">@return</a>                抓取的网页内容
     * @throws IOException   抓取异常
     */
    public static String GetWebContent(String urlString, final String charset, int timeout) throws IOException {
        if (urlString == null || urlString.length() == 0) {
            return null;
        }
        urlString = (urlString.startsWith("http://") || urlString.startsWith("https://")) ? urlString : ("http://" + urlString).intern();
        URL url = new URL(urlString);
 
 
        HttpURLConnection conn = (HttpURLConnection) url.openConnection();
        conn.setRequestProperty(
                "User-Agent",
                "Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 5.2; Trident/4.0; .NET CLR 1.1.4322; .NET CLR 2.0.50727)");//增加报头，模拟浏览器，防止屏蔽
        conn.setRequestProperty("Accept", "text/html");//只接受text/html类型，当然也可以接受图片,pdf,*/*任意，就是tomcat/conf/web里面定义那些
 
        conn.setConnectTimeout(timeout);
        try {
            if (conn.getResponseCode() != HttpURLConnection.HTTP_OK) {
                return null;
            }
        } catch (IOException e) {
            e.printStackTrace();
            return null;
        }
        InputStream input = conn.getInputStream();
        BufferedReader reader = new BufferedReader(new InputStreamReader(input,
                charset));
        String line = null;
        StringBuffer sb = new StringBuffer();
        while ((line = reader.readLine()) != null) {
            sb.append(line).append("\r\n");
        }
        if (reader != null) {
            reader.close();
        }
        if (conn != null) {
            conn.disconnect();
        }
        return sb.toString();
    }
 
    public static String getContent(Document doc){
        String content = "";
        try {
            String link = ".article_content";
            content = doc.select(link).html();
        } catch (Exception e) {
            e.printStackTrace();
        }
        return content;
    }
     
    public static String getTitle(Document doc){
        String content = "";
        try {
            String link = "h3";
            content=  doc.select(link).text();
        } catch (Exception e) {
            e.printStackTrace();
        }
        return content;
    }
    public static List<String> getAllLinks(String url){
        List<String> links = new ArrayList<String>();
        try {
            String con = GetWebContent(url,"utf-8",15000);
            Document doc = Jsoup.parse(con);
            String link = ".blog_list h1 a[class!=category]";
            String href = "abs:href";
            Elements ele = doc.select(link);
            for (Element el : ele) {
                String path = el.attr(href);
                links.add(path);
            }
        } catch (Exception e) {
            e.printStackTrace();
        }
        return links;
    }    
}

通过jsoup实现网络爬虫程序，理想的把数据流中的链接分为三种情况：1.带协议头的绝对地址，2.不带协议头的相对地址，3.#自连接。

第一种情况直接访问，第二种情况使用基地址加上资源地址组成绝对地址再访问，第三种情况直接返回。

[AppleScript] 纯文本查看 复制代码

import java.io.IOException;
import java.util.HashSet;
import java.util.Set;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;

public class MainClass {

        private static Set<String> urlSet = new HashSet<String>();

        private static Pattern p = Pattern
                        .compile(
                                        "^(((http|https)://" +
                                        "(www.|([1-9]|[1-9]\\d|1\\d{2}|2[0-1]\\d|25[0-5])" +
                                        "(\\.(\\d|[1-9]\\d|1\\d{2}|2[0-4]\\d|25[0-5])){3}:[0-9]+/)?)" +
                                        "{1}.+){1}quot;,
                                        Pattern.CASE_INSENSITIVE);

        public static void main(String[] args) {
                String baseUrl = "http://www.sina.com";
                spiderInternet(baseUrl, "");
        }

        private static void spiderInternet(String baseUrl, String exUrl) {
                if (baseUrl.endsWith("/") && exUrl.startsWith("/")) {
                        baseUrl = baseUrl.substring(0, baseUrl.length() - 1);
                }
                String new_url = baseUrl + exUrl;
                if (urlSet.contains(new_url)) {
                        return;
                }
                System.out.println(new_url);
                try {
                        Document doc = Jsoup.connect(new_url).get();
                        urlSet.add(new_url);
                        Elements links = doc.select("a[href]");
                        for (Element link : links) {
                                String linkHref = link.attr("href");
                                if (linkHref.equals("#")) {
                                        return;
                                }
                                Matcher matcher = p.matcher(linkHref);
                                if (matcher.matches()) {
                                        spiderInternet(linkHref, "");
                                } else {
                                        spiderInternet(baseUrl, linkHref);
                                }
                        }
                } catch (IOException e) {
                        e.printStackTrace();
                }
        }

}