我有一个程序,可以从网站上抓取表格并将其放入xls表中。但是,大多数数据必须是数字,某些单元格可能包含257,2x,ȻC,KL1等。我无法找出一种简单的方法用“”替换多余的字符,因为显然Apache POI并没有允许这个吗? 那么,您如何建议我这样做? 预先感谢。
int kansio = 1;
Document doc3 = Jsoup.connect("https://ravit.is.fi/paivanravit/").get();
Element table2 = doc3.select("table").get(5);
Elements links2 = table2.select("a[href]"); // a with href
for (Element link3 : links2) {
int asd1 = 1;
new File("C:\\sheets\\lahto-" + kansio).mkdir();
Document doc2 = Jsoup.connect("https://ravit.is.fi/paivanravit/" + link3.attr("href")).get();
Elements links = doc2.select("[href*=hevoset]");
for (Element link2 : links) {
try {
Document doc = Jsoup.connect("https://ravit.is.fi/" + link2.attr("href")).get();
String filename = "C:\\sheets\\lahto-" + kansio + "/" + asd1 + ".xls";
HSSFWorkbook workbook = new HSSFWorkbook();
HSSFSheet sheet = workbook.createSheet("FirstSheet");
for (Element asd : doc.select("#valittu_public > table > tbody > tr > td > form > table > tbody")) {
int rownum = 0;
for (Element row : asd.select("tr")) {
HSSFRow exlrow = sheet.createRow(rownum++);
int cellnum = 0;
for (Element tds : row.select("td")) {
StringUtils.isNumeric("");
HSSFCell cell = exlrow.createCell(cellnum++);
cell.setCellValue(tds.text());
}
}
}
sheet.shiftRows(2 ,500 ,-1);
int ttt = 1;
while (ttt < 500) {
sheet.shiftRows(ttt ,500 ,-1);
ttt++;
}
FileOutputStream fileOut = new FileOutputStream(filename);
workbook.write(fileOut);
fileOut.close();
workbook.close();
asd1++;
} catch ( Exception ex ) {
System.out.println(ex);
}
}
kansio++;
}