第一步，实现 LinkQueue，对url进行过滤和存储的操作
import java.util.ArrayList;
import java.util.Collections;
import java.util.HashSet;
import java.util.List;
import java.util.Set;
public class LinkQueue {
// 已访问的 url 集合
private static Set<String> visitedUrl = Collections.synchronizedSet(new HashSet<String>());
// 未访问的url
private static List<String> unVisitedUrl = Collections.synchronizedList(new ArrayList<String>());
// 未访问的URL出队列
public static String unVisitedUrlDeQueue() {
if (unVisitedUrl.size() > 0) {
String url = unVisitedUrl.remove(0);
visitedUrl.add(url);
return url;
}
return null;
}
// 新的url添加进来的时候进行验证，保证只是添加一次
public static void addUnvisitedUrl(String url) {
if (url != null && !url.trim().equals("") && !visitedUrl.contains(url)
&& !unVisitedUrl.contains(url))
unVisitedUrl.add(url);
}
// 判断未访问的URL队列中是否为空
public static boolean unVisitedUrlsEmpty() {
return unVisitedUrl.isEmpty();
}
}
第二步，收集每一个url下的链接进行过滤产生新的链接
import java.util.HashSet;
import java.util.Set;
import org.htmlparser.Node;
import org.htmlparser.NodeFilter;
import org.htmlparser.Parser;
import org.htmlparser.filters.NodeClassFilter;
import org.htmlparser.filters.OrFilter;
import org.htmlparser.tags.LinkTag;
import org.htmlparser.util.NodeList;
import org.htmlparser.util.ParserException;
/**
* 过滤http的url，获取可以符合规则的url
* @author Administrator
*
*/
public class ParserHttpUrl {
// 获取一个网站上的链接,filter 用来过滤链接
public static Set<String> extracLinks(String url, LinkFilter filter) {
Set<String> links = new HashSet<String>();
try {
Parser parser = new Parser(url);
// 过滤 <frame >标签的 filter，用来提取 frame 标签里的 src 属性所表示的链接
NodeFilter frameFilter = new NodeFilter() {
public boolean accept(Node node) {
if (node.getText().startsWith("frame src=")) {
return true;
} else {
return false;
}
}
};
// OrFilter 来设置过滤 <a> 标签，和 <frame> 标签
OrFilter linkFilter = new OrFilter(new NodeClassFilter(
LinkTag.class), frameFilter);
// 得到所有经过过滤的标签
NodeList list = parser.extractAllNodesThatMatch(linkFilter);
for (int i = 0; i < list.size(); i++) {
Node tag = list.elementAt(i);
if (tag instanceof LinkTag)// <a> 标签
{
LinkTag link = (LinkTag) tag;
String linkUrl = link.getLink();// url
if (filter.accept(linkUrl))
links.add(linkUrl);
} else// <frame> 标签
{
// 提取 frame 里 src 属性的链接如 <frame src="test.html"/>
String frame = tag.getText();
int start = frame.indexOf("src=");
frame = frame.substring(start);
int end = frame.indexOf(" ");
if (end == -1)
end = frame.indexOf(">");
String frameUrl = frame.substring(5, end - 1);
if (filter.accept(frameUrl))
links.add(frameUrl);
}
}
} catch (ParserException e) {
e.printStackTrace();
}
return links;
}
}
第三步，实现图片下载功能
import java.io.File;
import java.io.FileOutputStream;
import java.io.InputStream;
import java.net.URL;
import java.net.URLConnection;
import java.util.ArrayList;
import java.util.List;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
/***
* java抓取网络图片
*
* @author swinglife
*/
public class DownLoadPic {
// 编码
private static final String ECODING = "UTF-8";
// 获取img标签正则
private static final String IMGURL_REG = "<img.*src=(.*?)[^>]*?>";
// 获取src路径的正则
private static final String IMGSRC_REG = "http:\"?(.*?)(\"|>|\\s+)";
public static void downloadPic(String url) {
// 获得html文本内容
String HTML = null;
try {
HTML = DownLoadPic.getHTML(url);
} catch (Exception e) {
e.printStackTrace();
}
if (null != HTML && !"".equals(HTML)) {
// 获取图片标签
List<String> imgUrl = DownLoadPic.getImageUrl(HTML);
// 获取图片src地址
List<String> imgSrc = DownLoadPic.getImageSrc(imgUrl);
// 下载图片
DownLoadPic.download(imgSrc);
}
}
/***
* 获取HTML内容
*
* @param url
* @return
* @throws Exception
*/
private static String getHTML(String url) throws Exception {
URL uri = new URL(url);
URLConnection connection = uri.openConnection();
InputStream in = connection.getInputStream();
byte[] buf = new byte[1024];
int length = 0;
StringBuffer sb = new StringBuffer();
while ((length = in.read(buf, 0, buf.length)) > 0) {
sb.append(new String(buf, ECODING));
}
in.close();
return sb.toString();
}
/***
* 获取ImageUrl地址
*
* @param HTML
* @return
*/
private static List<String> getImageUrl(String HTML) {
Matcher matcher = Pattern.compile(IMGURL_REG).matcher(HTML);
List<String> listImgUrl = new ArrayList<String>();
while (matcher.find()) {
listImgUrl.add(matcher.group());
}
return listImgUrl;
}
/***
* 获取ImageSrc地址
*
* @param listImageUrl
* @return
*/
private static List<String> getImageSrc(List<String> listImageUrl) {
List<String> listImgSrc = new ArrayList<String>();
for (String image : listImageUrl) {
Matcher matcher = Pattern.compile(IMGSRC_REG).matcher(image);
while (matcher.find()) {
listImgSrc.add(matcher.group().substring(0, matcher.group().length() - 1));
}
}
return listImgSrc;
}
/***
* 下载图片
*
* @param listImgSrc
*/
private static void download(List<String> listImgSrc) {
for (String url : listImgSrc) {
try {
String imageName = url.substring(url.lastIndexOf("/") + 1, url.length());
URL uri = new URL(url);
InputStream in = uri.openStream();
FileOutputStream fo = new FileOutputStream(new File(imageName));
byte[] buf = new byte[1024];
int length = 0;
while ((length = in.read(buf, 0, buf.length)) != -1) {
fo.write(buf, 0, length);
}
in.close();
fo.close();
} catch (Exception e) {
e.printStackTrace();
}
}
}
}
实在Filter接口，定义过滤接口：
public interface Filter {
public boolean accept(String url);
}
第四步，过滤规则的实现：
public class Crawler {
/**
* 抓取过程
*
* @return
* @param seeds
*/
public void crawling(String url) { // 定义过滤器
Filter filter = new Filter() {
public boolean accept(String url) {
//这里过滤规则随需要爬的网站的规则进行改变，推荐使用正则实现，本人是爬豆瓣网站
if(url.indexOf("douban.com/group/topic") != -1 || url.indexOf("douban.com/group/haixiuzu/discussion?start") != -1 )
return true;
else
return false;
}
};
// 初始化 URL 队列
LinkQueue.addUnvisitedUrl(url);
// 循环条件，待抓取的链接不空
while (!LinkQueue.unVisitedUrlsEmpty()) {
// 队头URL出队列
String visitUrl = (String) LinkQueue.unVisitedUrlDeQueue();
if (visitUrl == null)
continue;
DownLoadPic.downloadPic(visitUrl);
// 提取出下载网页中的 URL
Set<String> links = ParserHttpUrl.extracLinks(visitUrl, filter);
// 新的未访问的 URL 入队
for (String link : links) {
LinkQueue.addUnvisitedUrl(link);
}
}
}
// main 方法入口
public static void main(String[] args) {
Crawler crawler = new Crawler();
crawler.crawling("http://www.douban.com/group/haixiuzu/discussion?start=0");
}
}
转载请注明原文地址：
http://blog.csdn.net/javaxiaojian/article/details/46680297
