import java.io.IOException;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;
public class Snippet {
public static void main(String[] args) throws IOException{
String baseUrl = "http://www.wwenglish.com";
Document listDoc = Jsoup.connect("http://www.wwenglish.com/en/club/cnntv/").get();
Elements dd = listDoc.select("td.category td.category_main a.list");
for(Element element: dd){
String mp3PageUrl = baseUrl + element.attr("href");
//System.out.println(mp3PageUrl);
Document mp3Doc = Jsoup.connect(mp3PageUrl).get();
Elements mp3Elements = mp3Doc.select("a.wwmp3");
if(null != mp3Elements && mp3Elements.size()>0){
String mp3Url = baseUrl + mp3Elements.get(0).attr("href");
String fileName = mp3Url.substring(mp3Url.lastIndexOf("/"));
//System.out.println(fileName);
DownLoad thread = new DownLoad(mp3Url, "F:/wwenglish"+fileName);
thread.start();
}
}
}
}
import java.io.BufferedOutputStream;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.InputStream;
import java.io.OutputStream;
import java.net.URL;
public class DownLoad extends Thread {
public DownLoad(String mp3Url, String filepath) {
// Open a URL Stream
try {
URL url = new URL(mp3Url);
InputStream in = url.openStream();
OutputStream out = new BufferedOutputStream(new FileOutputStream(
filepath));
for (int b; (b = in.read()) != -1;) {
out.write(b);
}
out.close();
in.close();
} catch (IOException e) {
e.printStackTrace();
}
}
}
实现了如下链接中所描述的功能, 原文代码不完整. 这里不使用 HttpClient, 单单使用 Jsoup 就达到了目的.
简单 使用 httpclient jsoup 做的 提取 旺旺英语
库依赖如下:
<?xml version="1.0" encoding="UTF-8"?>
<classpath>
<classpathentry kind="src" path="src"/>
<classpathentry kind="con" path="org.eclipse.jdt.launching.JRE_CONTAINER/org.eclipse.jdt.internal.debug.ui.launcher.StandardVMType/JavaSE-1.8"/>
<classpathentry kind="lib" path="H:/MavenRepository/org/jsoup/1.8.1/jsoup-1.8.1.jar"/>
<classpathentry kind="lib" path="H:/MavenRepository/org/apache/httpcomponents/httpclient/4.0/httpclient-4.0.jar"/>
<classpathentry kind="lib" path="H:/MavenRepository/org/apache/httpcomponents/httpcore/4.3.2/httpcore-4.3.2.jar"/>
<classpathentry kind="output" path="bin"/>
</classpath>