运用正则表达式提取数字的方法:
result = Pattern.compile("[^0-9]").matcher(result).replaceAll("");
public static String rules2(String html){
String result = "";
String xpath="//*[@id=\"detail\"]/div[2]/div/div[2]/div/div[3]/div/text()[2]";
JXDocument jxDocument = new JXDocument(html);
List<Object> rs = jxDocument.sel(xpath);
for (Object o:rs){
if (o instanceof Element){
int index = ((Element) o).siblingIndex();
}
result = o.toString();
}
if(result.contains("采购人:")){
try {
result = result.split("采购代理机构:")[1].split("地址:")[1].split("联系方式:")[1].split("二、采购项目名称:")[0];
}catch (Exception e){
result = "";
}
}
if ( SNRules.extractChinese(result)){
result = "";
}
if (result.length()>30 || result.length()<9){
result="";
}
// result=result.replace("二、","");
result = Pattern.compile("[^0-9]").matcher(result).replaceAll("");
return result;
}