【发布时间】：2011-06-30 11:49:06
【问题描述】：
我在编写 CSV 文件时遇到了一些问题。我制作的程序使用HTML praser 从网站获取数据。然后它将该数据保存到 .csv 文件中。
我遇到的问题是，它不会将所有数据写入文件（而是截断其中的一些数据），并且当有多个 url 时，它根本不会写入它们！
要使用该程序，首先输入一个目录，然后在顶部区域，输入这些网址。
http://www.freddiemac.com/debt/data/cgi-bin/cusipdetail.cgi?cusip=04541GEL2
http://www.freddiemac.com/debt/data/cgi-bin/cusipdetail.cgi?cusip=31359T8L5
http://www.freddiemac.com/debt/data/cgi-bin/cusipdetail.cgi?cusip=31395RGT9
http://www.freddiemac.com/debt/data/cgi-bin/cusipdetail.cgi?cusip=57643LJU1
http://www.freddiemac.com/debt/data/cgi-bin/cusipdetail.cgi?cusip=31358RRC9
http://www.freddiemac.com/debt/data/cgi-bin/cusipdetail.cgi?cusip=31392V6H0
按下发送信息并按下开始。它应该在底部框中记录所有内容。
这是程序的代码：
package com.js.extract;
import java.io.*;
import java.util.*;
import javax.swing.*;
import java.awt.*;
import java.awt.event.*;
import org.htmlparser.beans.StringBean;
import org.htmlparser.util.ParserException;
public class Extraction_GUI extends JFrame {
/**
*
*/
private static final long serialVersionUID = 1L;
protected JButton start;
protected JButton sendInfo;
protected JTextArea infoArea;
protected static JTextArea log;
protected JScrollPane sp;
protected JScrollPane sp2;
protected JSplitPane pane;
protected JPanel mainPanel;
protected JPanel aPanel;
protected JPanel lPanel;
protected int areaStatus = 0;
static protected Calendar cal = Calendar.getInstance();
protected static ArrayList<String> urls = new ArrayList<String>();
public Extraction_GUI(){
super("Extraction by Jeel Shah");
setSize(660,520);
setDefaultCloseOperation(JFrame.EXIT_ON_CLOSE);
setLocationRelativeTo(null);
setResizable(false);
mainPanel = new JPanel();
mainPanel.setLayout(new FlowLayout());
aPanel = new JPanel();
aPanel.setLayout(new FlowLayout());
lPanel = new JPanel();
lPanel.setLayout(new FlowLayout());
start = new JButton("start");
sendInfo = new JButton("send info");
infoArea = new JTextArea("http://www.freddiemac.com/debt/data/cgi-bin/cusipdetail.cgi?cusip=3133F0GM5"
,13,55);
log = new JTextArea(10,55);
log.setEditable(false);
sp = new JScrollPane(infoArea);
sp.setHorizontalScrollBarPolicy(JScrollPane.HORIZONTAL_SCROLLBAR_ALWAYS);
sp.setVerticalScrollBarPolicy(JScrollPane.VERTICAL_SCROLLBAR_ALWAYS);
sp2 = new JScrollPane(log);
sp2.setHorizontalScrollBarPolicy(JScrollPane.HORIZONTAL_SCROLLBAR_ALWAYS);
sp2.setVerticalScrollBarPolicy(JScrollPane.VERTICAL_SCROLLBAR_ALWAYS);
aPanel.add(sp);
lPanel.add(sp2);
pane = new JSplitPane(JSplitPane.VERTICAL_SPLIT,aPanel,lPanel);
mainPanel.add(pane);
mainPanel.add(start);
mainPanel.add(sendInfo);
add(mainPanel);
setVisible(true);
final String toSave = JOptionPane.showInputDialog(null, "Please enter where you would like to save your files: ");
log.append("Data will be saved to: "+toSave+"\n");
sendInfo.addActionListener(new infoListener());
start.addActionListener(new ActionListener() {
public void actionPerformed(ActionEvent e) {
try {
start(toSave);
} catch (ParserException e1) {
e1.printStackTrace();
} catch (IOException e2) {
e2.printStackTrace();
}
}
});
}
// start
public static void start(String file) throws ParserException, IOException {
for(int i = 0; i < urls.size();i++) {
BufferedWriter writer = new BufferedWriter(new FileWriter(file+"CUSIP"+i+".csv"));
StringBean sb = new StringBean ();
sb.setLinks(false);
sb.setReplaceNonBreakingSpaces(true);
sb.setCollapse(true);
sb.setURL (urls.get(i));
String toReduce = sb.getStrings ();
StringBuffer buffer = new StringBuffer(toReduce);
if(toReduce.contains("*CUSIP Detail information will be available when this issue settles.")) {
log.append("CUSIP Detail not available.For "+urls.get(i)+"\n");
}else {
buffer.delete(0, toReduce.indexOf("Cusip/ISIN")-1);
buffer.delete(buffer.indexOf("Underwriters:"), buffer.length());
String[] data = new String[13];
data[0] = buffer.substring(0, buffer.indexOf("Instrument Type:"));
data[1] = buffer.substring(buffer.indexOf("Instrument Type:"),buffer.indexOf("Call Type:"));
data[2] = buffer.substring(buffer.indexOf("Call Type:"),buffer.indexOf("Issue Date:"));
data[3] = buffer.substring(buffer.indexOf("Issue Date:"),buffer.indexOf("Issue Price:"));
data[4] = buffer.substring(buffer.indexOf("Issue Price:"),buffer.indexOf("Amount Issued:"));
data[5] = buffer.substring(buffer.indexOf("Amount Issued:"),buffer.indexOf("Lockout Period:"));
data[6] = buffer.substring(buffer.indexOf("Lockout Period:"),buffer.indexOf("Currency"));
data[7] = buffer.substring(buffer.indexOf("Currency"),buffer.indexOf("Denomination:"));
data[8] = buffer.substring(buffer.indexOf("Denomination:"),buffer.indexOf("First Payment"));
data[9] = buffer.substring(buffer.indexOf("First Payment"),buffer.indexOf("Maturity Date"));
data[10] = buffer.substring(buffer.indexOf("Maturity Date"),buffer.indexOf("Original Coupon:"));
data[11] = buffer.substring(buffer.indexOf("Original Coupon:"),buffer.indexOf("Current Coupon:"));
data[12] = buffer.substring(buffer.indexOf("Current Coupon:"),buffer.length());
for(String s : data) {
writer.write(s);
writer.write(",");
writer.newLine();
}
}
writer.flush();
writer.close();
log.append("Harvested: "+urls.get(i)+" successfully"+" \n");
}
log.append("Completed at: "+cal.get(Calendar.HOUR)+":"+cal.get(Calendar.MINUTE)+":"+cal.get(Calendar.SECOND) + "\n");
}
class infoListener implements ActionListener{
public void actionPerformed(ActionEvent arg0) {
String url = infoArea.getText();
StringTokenizer st = new StringTokenizer(url,",");
while(st.hasMoreTokens()) {
urls.add(st.nextToken());
}
log.append("Data Recieved at: "+cal.get(Calendar.HOUR)+":"+cal.get(Calendar.MINUTE)+":"+cal.get(Calendar.SECOND)+"\n");
}
}
public static void main(String[]args) {
javax.swing.SwingUtilities.invokeLater(new Runnable() {
public void run() {
new Extraction_GUI();
}
});
}
}
注意：您需要下载 HTML Parser 并将其添加到您的构建路径中。
【问题讨论】：
-
截断多少？ 1个字符有机会吗？而且我假设即使您没有用逗号分隔示例 URL 列表，当您将它们输入到您的应用程序时，您也会这样做？否则在 StringTokenizer 构造函数中将 ',' 更改为 ' '
-
它有时会截断大约 2-3 个字符，我还没有注意到一个模式。
-
我认为你的意思是“csv”而不是“cvs”
标签： java csv html-parsing