package appgamerank;
import java.io.File;
import java.io.FileOutputStream;
import java.io.FileWriter;
import java.io.IOException;
import java.net.MalformedURLException;
import org.apache.commons.httpclient.HttpClient;
import org.apache.commons.httpclient.HttpException;
import org.apache.commons.httpclient.HttpMethod;
import org.apache.commons.httpclient.methods.GetMethod;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;
/**
*
* @author dell
*/
public class AppGameRank {
/**
* @param args the command line arguments
*/
public static void main(String[] args) {
// TODO code application logic here
AppGameRank rh = new AppGameRank();
rh.saveHtml();
rh.getMsgfromHtml();
}
public void saveHtml(){
HttpClient client = new HttpClient();
String htmlurl = "http://www.appannie.com/top/iphone/united-states/games/";
System.out.println(htmlurl);
HttpMethod method = new GetMethod(htmlurl);
try
{
client.executeMethod(method);
System.out.println(method.getStatusLine());
String html = method.getResponseBodyAsString();
FileWriter fw = new FileWriter("D:\\Top Charts - iPhone - United States - Games App Annie.htm" );
fw.write(html);
fw.close();
} catch (HttpException e)
{
// TODO Auto-generated catch block
e.printStackTrace();
} catch (IOException e)
{
// TODO Auto-generated catch block
e.printStackTrace();
}
}
public void getMsgfromHtml(){
try
{
//URL url = new URL("http://www.appannie.com/top/iphone/united-states/games/");
//Document doc = Jsoup.parse(url, 3000000);
File f = new File("D:\\Top Charts - iPhone - United States - Games App Annie.htm");
Document doc = Jsoup.parse(f,"UTF-8");
Elements tables = doc.select("table");
Element table = tables.get(1);
Elements trs =table.getElementsByTag("tr");
for(Element tr: trs)
{
Elements tds = tr.children();
Element td = tds.get(2);//表示 Free那一列
Elements span =td.getElementsByTag("span");
String content = span.get(0).html();
if(content.contains("\u25b2"))
{
String up = content.replace("\u25b2", "");//正三角，倒三角是\u25bc
int upnum = Integer.parseInt(up);
if(upnum >=30)
{
Elements a = td.getElementsByTag("a");
System.out.println(a.get(0).html());
}
}
else if(content.contains("(new)"))
{
String up = content.replace("(new)","");
Elements a = td.getElementsByTag("a");
System.out.println(a.get(0).html());