java : jsoup 网页 table 解析范例

import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;
import java.io.IOException;

public class SoupTest {
private String url ;
// 构造方法
public SoupTest(String url){
this.url = url;
}

public static void main(String[] args) {
String url;
if (args.length==1){
url = args[0];
} else {
System.out.println(" usage: java SoupTest http:// ");
return;
}
SoupTest app = new SoupTest(url);
app.run();
}

private static int table1(Document doc){
Elements trs = doc.select("table").select("tr");
int i;
for ( i=0; i<trs.size(); i++){
Elements tds = trs.get(i).select("td");
for (int j=0; j<tds.size(); j++){
String txt = tds.get(j).text();
System.out.print(txt+" ");
}
System.out.println("");
}
return i;
}

// 运行过程
public void run(){
Document doc;
int rows;
try {
doc = Jsoup.connect(url).get();
// Page: 1
rows = this.table1(doc);
System.out.println(" rows: "+rows);
} catch(IOException e) {
e.printStackTrace();
}
}

}