我的程序在craws了前2个url的“exception in thread”awt-eventqueue-0“java.lang.stringindexoutofboundsexception:字符串索引超出范围:0”之后,一直出现错误。前两个url的craw是我想要的,我使用另一个类中的方法从它们那里获取文本。另一节课可能是我不知道的问题。请看一下我的代码,看看发生了什么。
package WebCrawler;
import java.util.Scanner;
import java.util.ArrayList;
import static TextAnalyser.Textanalyser.analyse;
public class Crawler {
public static void main(String[] args) {
// java.util.Scanner input = new java.util.Scanner(System.in);
// System.out.print("Enter a URL: ");
// String url = input.nextLine();
crawler("http://www.port.ac.uk/"); // Traverse the Web from the a starting url
}
public static void crawler(String startingURL) {
ArrayList<String> listOfPendingURLs = new ArrayList<String>();
ArrayList<String> listOfTraversedURLs = new ArrayList<String>();
listOfPendingURLs.add(startingURL);
while (!listOfPendingURLs.isEmpty() && listOfTraversedURLs.size() <= 100) {
String urlString = listOfPendingURLs.remove(0);
if (!listOfTraversedURLs.contains(urlString)) {
listOfTraversedURLs.add(urlString);
String text = urlString;
text = ReadTextfromURL.gettext(text);
text = analyse(text);
System.out.println("text : " + text);
System.out.println("Craw " + urlString);
for (String s: getSubURLs(urlString)) {
if (!listOfTraversedURLs.contains(s)) {
listOfPendingURLs.add(s);
}
}
}
}
}
public static ArrayList<String> getSubURLs(String urlString) {
ArrayList <String> list = new ArrayList<String>();
try {
java.net.URL url = new java.net.URL(urlString);
Scanner input = new Scanner(url.openStream());
int current = 0;
while (input.hasNext()) {
String line = input.nextLine();
current = line.indexOf("http:", current);
while (current > 0) {
int endIndex = line.indexOf("\"", current);
if (endIndex > 0) { // Ensure that a correct URL is found
list.add(line.substring(current, endIndex));
current = line.indexOf("http:", endIndex);
} else {
current = -1;
}
}
}
} catch (Exception ex) {
System.out.println("Error: " + ex.getMessage());
}
return list;
}
}
暂无答案!
目前还没有任何答案,快来回答吧!