Question

我创建了一个网络剪贴簿，它从网站上删除数据并将其存储在CSV文件中。但是，问题是网站上有一个列具有货币格式值，其值大于 7,100 或 85,210 。当我的代码执行并废弃数据时，这些值分为两列，如一列中的7列和其他列中的100列。请检查附带的屏幕截图。代码如下。

public class ComMarket_summary {

boolean writeCSVToConsole = true;
boolean writeCSVToFile = true;
boolean sortTheList = true;
boolean writeToConsole;
boolean writeToFile;
public static Document doc = null;
public static Elements tbodyElements = null;
public static Elements elements = null;
public static Elements tdElements = null;
public static Elements trElement2 = null;
public static String Dcomma = ",";
public static String line = "";
public static ArrayList<Elements> sampleList = new ArrayList<Elements>();

public static void createConnection() throws IOException {
    System.setProperty("http.proxyHost", "191.1.1.202");
    System.setProperty("http.proxyPort", "8080");
    String tempUrl = "http://www.psx.com.pk/phps/mktSummary.php";
    doc = Jsoup.parse(new URL(tempUrl), 1000);
    System.out.println("Successfully Connected");
}

public static void parsingHTML() throws Exception {

    for (Element table : doc.select("table.marketData")) {
        Elements tables = doc.select("table.marketData");
        table = tables.get(2);
        File fold = new File("C:\\market_smry.csv");
        fold.delete();
        File fnew = new File("C:\\market_smry.csv");
        for (Element trElement : table.getElementsByTag("tr")) {

            trElement2 = trElement.getElementsByTag("tr");
            tdElements = trElement.getElementsByTag("td");
            FileWriter sb = new FileWriter(fnew, true);

            //if (table.hasClass("marketData")) { //&&(tdElements.hasClass("tableHead")&&tdElements.hasClass("tableSubHead"))
            for (Iterator<Element> it = tdElements.iterator(); it.hasNext();) {
                if (it.hasNext()) {
                    sb.append(" , ");
                    sb.append(" \r\n ");
                }

                for (Iterator<Element> it2 = tdElements.iterator(); it.hasNext();) {
                    Element tdElement2 = it.next();
                    final String content = tdElement2.text();
                    if (it2.hasNext()) {

                        sb.append(formatData(content));
                        sb.append("   ,   ");


                    }
                }

                System.out.println(sb.toString());
                sb.flush();
                sb.close();
            }

            System.out.println(sampleList.add(tdElements));

        }
    }
}
private static final SimpleDateFormat FORMATTER_MMM_d_yyyy = new SimpleDateFormat("MMM d, yyyy", Locale.US);
private static final SimpleDateFormat FORMATTER_dd_MMM_yyyy = new SimpleDateFormat("d-MMM-yy", Locale.US);

public static String formatData(String text) {
    String tmp = null;

    try {
        Date d = FORMATTER_MMM_d_yyyy.parse(text);
        tmp = FORMATTER_dd_MMM_yyyy.format(d);
    } catch (ParseException pe) {
        tmp = text;
    }

    return tmp;
}

public static void main(String[] args) throws IOException, Exception {
    createConnection();
    parsingHTML();

}

注意：我使用的是Windows 8，java版本1.8，jsoup 1.8

Answer 1

在保存值之前，请使用String.replace

删除逗号

value = value.replace (",", "");

Answer 2

String.replace将删除您的逗号。虽然还有其他几个类似的功能（replaceAll，replaceFirst），但replace会稍快一些，通常是单个字符的最佳选择。

请参阅：https://docs.oracle.com/javase/6/docs/api/java/lang/String.html

还有：Difference between String replace() and replaceAll()

如何通过Java在CSV文件中刮取货币格式的数字

2 个答案: