讓JAVA讀取html文件表的內容!
public class read html 2 { public static void main(String【】args)拋出io exception {//String strUrl =“/?reg&TPL = Mn“;///URL URL =新URL(strUrl);File f =新文件(“fortest . htm“);//輸入流//inputstreamreader ISR = new inputstreamreader(URL . openstream());InputStreamReader ISR 1 = new InputStreamReader(new file inputstream(f));BufferedReader br =新的buffered reader(ISR 1);//獲取html並將其轉換為字符串String s;string all content =““;while((s = br . readline())= null){ all content = all content+s;}//使用HTML解析器控件解析器myParser後;NodeList nodeList = nullmy parser = parser . create parser(all content,“utf-8“);node filter table filter = newNodeClassFilter(tabletag . class);or filter last filter = new or filter();last filter . set predictes(new node filter【】{ table filter });嘗試{//獲取標記為table nodelist = myparser的節點列表。解析(最後壹個過濾器);//讀取每個表的for(int I = 0;我& lt= nodelist . size();i++){ if(nodelist . element at(I)TableTag的instance){ TableTag tag =(TableTag)nodelist . element at(I);TableRow【】rows = tag . getrows();system . out . println(“-table“+I+“-“);//讀取每行for(int j = 0;j & ltrows.lengthj++){ TableRow tr =(TableRow)rows【j】;table column【】TD = tr . get columns();//讀取每行的單元格內容for(int k = 0;k & lttd .長度;k++){ system . out . println(TD【k】)。getstring text());//(根據需要的格式輸出)}}} catch(解析器異常){ e . printstacktrace();}}}