Home  >  Article  >  类库下载  >  Crawl all links on a website

Crawl all links on a website

高洛峰
高洛峰Original
2016-11-02 14:42:073943browse

一 算法简介

       程序在思路上采用了广度优先算法,对未遍历过的链接逐次发起GET请求,然后对返回来的页面用正则表达式进行解析,取出其中未被发现的新链接,加入集合中,待下一次循环时遍历。

       具体实现上使用了Map

二 程序实现

上面相关思路已经说得很清楚了,并且代码中关键地方有注释,因此这里就不多说了,代码如下:

package action;
 
import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.net.HttpURLConnection;
import java.net.MalformedURLException;
import java.net.URL;
import java.util.LinkedHashMap;
import java.util.Map;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
 
public class WebCrawlerDemo {
 
    public static void main(String[] args) {
        WebCrawlerDemo webCrawlerDemo = new WebCrawlerDemo();
        webCrawlerDemo.myPrint("http://www.zifangsky.cn");
    }
 
    public void myPrint(String baseUrl) {
        Map oldMap = new LinkedHashMap(); // 存储链接-是否被遍历
                                                                            // 键值对
        String oldLinkHost = "";  //host
 
        Pattern p = Pattern.compile("(https?://)?[^/\\s]*"); //比如:http://www.zifangsky.cn
        Matcher m = p.matcher(baseUrl);
        if (m.find()) {
            oldLinkHost = m.group();
        }
 
        oldMap.put(baseUrl, false);
        oldMap = crawlLinks(oldLinkHost, oldMap);
        for (Map.Entry mapping : oldMap.entrySet()) {
            System.out.println("链接:" + mapping.getKey());
 
        }
 
    }
 
    /**
     * 抓取一个网站所有可以抓取的网页链接,在思路上使用了广度优先算法
     * 对未遍历过的新链接不断发起GET请求,一直到遍历完整个集合都没能发现新的链接
     * 则表示不能发现新的链接了,任务结束
     * 
     * @param oldLinkHost  域名,如:http://www.zifangsky.cn
     * @param oldMap  待遍历的链接集合
     * 
     * @return 返回所有抓取到的链接集合
     * */
    private Map crawlLinks(String oldLinkHost,
            Map oldMap) {
        Map newMap = new LinkedHashMap();
        String oldLink = "";
 
        for (Map.Entry mapping : oldMap.entrySet()) {
            System.out.println("link:" + mapping.getKey() + "--------check:"
                    + mapping.getValue());
            // 如果没有被遍历过
            if (!mapping.getValue()) {
                oldLink = mapping.getKey();
                // 发起GET请求
                try {
                    URL url = new URL(oldLink);
                    HttpURLConnection connection = (HttpURLConnection) url
                            .openConnection();
                    connection.setRequestMethod("GET");
                    connection.setConnectTimeout(2000);
                    connection.setReadTimeout(2000);
 
                    if (connection.getResponseCode() == 200) {
                        InputStream inputStream = connection.getInputStream();
                        BufferedReader reader = new BufferedReader(
                                new InputStreamReader(inputStream, "UTF-8"));
                        String line = "";
                        Pattern pattern = Pattern
                                .compile("(.+)");
                        Matcher matcher = null;
                        while ((line = reader.readLine()) != null) {
                            matcher = pattern.matcher(line);
                            if (matcher.find()) {
                                String newLink = matcher.group(1).trim(); // 链接
                                // String title = matcher.group(3).trim(); //标题
                                // 判断获取到的链接是否以http开头
                                if (!newLink.startsWith("http")) {
                                    if (newLink.startsWith("/"))
                                        newLink = oldLinkHost + newLink;
                                    else
                                        newLink = oldLinkHost + "/" + newLink;
                                }
                                //去除链接末尾的 /
                                if(newLink.endsWith("/"))
                                    newLink = newLink.substring(0, newLink.length() - 1);
                                //去重,并且丢弃其他网站的链接
                                if (!oldMap.containsKey(newLink)
                                        && !newMap.containsKey(newLink)
                                        && newLink.startsWith(oldLinkHost)) {
                                    // System.out.println("temp2: " + newLink);
                                    newMap.put(newLink, false);
                                }
                            }
                        }
                    }
                } catch (MalformedURLException e) {
                    e.printStackTrace();
                } catch (IOException e) {
                    e.printStackTrace();
                }
 
                try {
                    Thread.sleep(1000);
                } catch (InterruptedException e) {
                    e.printStackTrace();
                }
                oldMap.replace(oldLink, false, true);
            }
        }
        //有新链接,继续遍历
        if (!newMap.isEmpty()) {
            oldMap.putAll(newMap);
            oldMap.putAll(crawlLinks(oldLinkHost, oldMap));  //由于Map的特性,不会导致出现重复的键值对
        }
        return oldMap;
    }
 
}

三 最后的测试效果

Crawl all links on a website

Statement:
The content of this article is voluntarily contributed by netizens, and the copyright belongs to the original author. This site does not assume corresponding legal responsibility. If you find any content suspected of plagiarism or infringement, please contact admin@php.cn