Java 实现网络爬虫框架详细代码
Java 实现网络爬虫框架
最近在做一个搜索相关的项目,需要爬取网络上的一些链接存储到索引库中,虽然有很多开源的强大的爬虫框架,但本着学习的态度,自己写了一个简单的网络爬虫,以便了解其中的原理。今天,就为小伙伴们分享下这个简单的爬虫程序!!
一、每个类的功能介绍
- DownloadPage.java的功能是下载此超链接的页面源代码.
- FunctionUtils.java 的功能是提供不同的静态方法,包括:页面链接正则表达式匹配,获取URL链接的元素,判断是否创建文件,获取页面的Url并将其转换为规范的Url,截取网页网页源文件的目标内容。
- HrefOfPage.java 的功能是获取页面源代码的超链接。
- UrlDataHanding.java 的功能是整合各个给类,实现url到获取数据到数据处理类。
- UrlQueue.java 的未访问Url队列。
- VisitedUrlQueue.java 已访问过的URL队列。
二、每个类的源代码
DownloadPage.java 此类要用到HttpClient组件。
package com.sreach.spider;
import java.io.IOException;
import org.apache.http.HttpEntity;
import org.apache.http.HttpResponse;
import org.apache.http.client.ClientProtocolException;
import org.apache.http.client.HttpClient;
import org.apache.http.client.methods.HttpGet;
import org.apache.http.impl.client.DefaultHttpClient;
import org.apache.http.util.EntityUtils;
public class DownloadPage {
public static String getContentFormUrl(String url) {
HttpClient client = new DefaultHttpClient();
HttpGet getHttp = new HttpGet(url);
String content = null;
HttpResponse response;
try {
response = client.execute(getHttp);
HttpEntity entity = response.getEntity();
VisitedUrlQueue.addElem(url);
if (entity != null) {
content = EntityUtils.toString(entity);
if (FunctionUtils.isCreateFile(url)
&& FunctionUtils.isHasGoalContent(content) != -1) {
FunctionUtils.createFile(
FunctionUtils.getGoalContent(content), url);
}
}
} catch (ClientProtocolException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
} finally {
client.getConnectionManager().shutdown();
}
return content;
}
}
FunctionUtils.java 此类的方法均为static方法
package com.sreach.spider;
import java.io.BufferedWriter;
import java.io.File;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.OutputStreamWriter;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
public class FunctionUtils {
private static String pat = "http://www\\.oschina\\.net/code/explore/.*/\\w+\\.[a-zA-Z]+";
private static Pattern pattern = Pattern.compile(pat);
private static BufferedWriter writer = null;
public static int depth = 0;
public static String[] divUrl(String url) {
return url.split("/");
}
public static boolean isCreateFile(String url) {
Matcher matcher = pattern.matcher(url);
return matcher.matches();
}
public static void createFile(String content, String urlPath) {
String[] elems = divUrl(urlPath);
StringBuffer path = new StringBuffer();
File file = null;
for (int i = 1; i < elems.length; i++) {
if (i != elems.length - 1) {
path.append(elems[i]);
path.append(File.separator);
file = new File("D:" + File.separator + path.toString());
}
if (i == elems.length - 1) {
Pattern pattern = Pattern.compile("\\w+\\.[a-zA-Z]+");
Matcher matcher = pattern.matcher(elems[i]);
if ((matcher.matches())) {
if (!file.exists()) {
file.mkdirs();
}
String[] fileName = elems[i].split("\\.");
file = new File("D:" + File.separator + path.toString()
+ File.separator + fileName[0] + ".txt");
try {
file.createNewFile();
writer = new BufferedWriter(new OutputStreamWriter(
new FileOutputStream(file)));
writer.write(content);
writer.flush();
writer.close();
System.out.println("创建文件成功");
} catch (IOException e) {
e.printStackTrace();
}
}
}
}
}
public static String getHrefOfInOut(String href) {
String resultHref = null;
if (href.startsWith("http://")) {
resultHref = href;
} else {
if (href.startsWith("/")) {
resultHref = "http://www.oschina.net" + href;
}
}
return resultHref;
}
public static String getGoalContent(String content) {
int sign = content.indexOf("<pre class=\"");
String signContent = content.substring(sign);
int start = signContent.indexOf(">");
int end = signContent.indexOf("</pre>");
return signContent.substring(start + 1, end);
}
public static int isHasGoalContent(String content) {
return content.indexOf("<pre class=\"");
}
}
HrefOfPage.java 此类为获取页面的超链接
package com.sreach.spider;
public class HrefOfPage {
public static void getHrefOfContent(String content) {
System.out.println("开始");
String[] contents = content.split("<a href=\"");
for (int i = 1; i < contents.length; i++) {
int endHref = contents[i].indexOf("\"");
String aHref = FunctionUtils.getHrefOfInOut(contents[i].substring(
0, endHref));
if (aHref != null) {
String href = FunctionUtils.getHrefOfInOut(aHref);
if (!UrlQueue.isContains(href)
&& href.indexOf("/code/explore") != -1
&& !VisitedUrlQueue.isContains(href)) {
UrlQueue.addElem(href);
}
}
}
System.out.println(UrlQueue.size() + "--抓取到的连接数");
System.out.println(VisitedUrlQueue.size() + "--已处理的页面数");
}
}
UrlDataHanding.java 此类主要是从未访问队列中获取url,下载页面,分析url,保存已访问url等操作,实现Runnable接口
package com.sreach.spider;
public class UrlDataHanding implements Runnable {
public void dataHanding(String url) {
HrefOfPage.getHrefOfContent(DownloadPage.getContentFormUrl(url));
}
public void run() {
while (!UrlQueue.isEmpty()) {
dataHanding(UrlQueue.outElem());
}
}
}
UrlQueue.java 此类主要是用来存放未访问的URL队列
package com.sreach.spider;
import java.util.LinkedList;
public class UrlQueue {
public static LinkedList<String> urlQueue = new LinkedList<String>();
public static final int MAX_SIZE = 10000;
public synchronized static void addElem(String url) {
urlQueue.add(url);
}
public synchronized static String outElem() {
return urlQueue.removeFirst();
}
public synchronized static boolean isEmpty() {
return urlQueue.isEmpty();
}
public static int size() {
return urlQueue.size();
}
public static boolean isContains(String url) {
return urlQueue.contains(url);
}
}
VisitedUrlQueue.java 主要是保存已访问过的URL,使用HashSet来保存,主要是考虑到每个访问过的URL是不同。HashSet刚好符合这个要求
package com.sreach.spider;
import java.util.HashSet;
public class VisitedUrlQueue {
public static HashSet<String> visitedUrlQueue = new HashSet<String>();
public synchronized static void addElem(String url) {
visitedUrlQueue.add(url);
}
public synchronized static boolean isContains(String url) {
return visitedUrlQueue.contains(url);
}
public synchronized static int size() {
return visitedUrlQueue.size();
}
}
Test.java 此类为测试类
import java.sql.SQLException;
import com.sreach.spider.UrlDataHanding;
import com.sreach.spider.UrlQueue;
public class Test {
public static void main(String[] args) throws SQLException {
String url = "http://www.oschina.net/code/explore/achartengine/client/AndroidManifest.xml";
String url1 = "http://www.oschina.net/code/explore";
String url2 = "http://www.oschina.net/code/explore/achartengine";
String url3 = "http://www.oschina.net/code/explore/achartengine/client";
UrlQueue.addElem(url);
UrlQueue.addElem(url1);
UrlQueue.addElem(url2);
UrlQueue.addElem(url3);
UrlDataHanding[] url_Handings = new UrlDataHanding[10];
for (int i = 0; i < 10; i++) {
url_Handings[i] = new UrlDataHanding();
new Thread(url_Handings[i]).start();
}
}
}
说明一下:由于我抓取的是针对oschina的,所以里面的url正则表达式不适合其他网站,需要自己修改一下。你也可以写成xml来配置。
以上就是Java 实现网络爬虫框架详细代码的详细内容,更多关于Java 实现网络爬虫框架的资料请关注编程网其它相关文章!
免责声明:
① 本站未注明“稿件来源”的信息均来自网络整理。其文字、图片和音视频稿件的所属权归原作者所有。本站收集整理出于非商业性的教育和科研之目的,并不意味着本站赞同其观点或证实其内容的真实性。仅作为临时的测试数据,供内部测试之用。本站并未授权任何人以任何方式主动获取本站任何信息。
② 本站未注明“稿件来源”的临时测试数据将在测试完成后最终做删除处理。有问题或投稿请发送至: 邮箱/279061341@qq.com QQ/279061341