我一直在努力製作一個簡單的程序,該程序運行通過頁面中的所有鏈接,然後訪問它們,然後遞歸。但似乎作爲其運行,一旦停止與錯誤java.net.MalformedURLException:無協議:/ intl/en/policies/GET請求
java.net.MalformedURLException: no protocol: /intl/en/policies/
at java.net.URL.<init>(Unknown Source)
at java.net.URL.<init>(Unknown Source)
at java.net.URL.<init>(Unknown Source)
at me.dylan.WebCrawler.WebC.sendGetRequest(WebC.java:67)
at me.dylan.WebCrawler.WebC.<init>(WebC.java:27)
at me.dylan.WebCrawler.WebC.main(WebC.java:36)
我的代碼:
package me.dylan.WebCrawler;
import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStreamReader;
import java.net.HttpURLConnection;
import java.net.MalformedURLException;
import java.net.URL;
import java.util.ArrayList;
import javax.swing.text.BadLocationException;
import javax.swing.text.EditorKit;
import javax.swing.text.MutableAttributeSet;
import javax.swing.text.html.HTML;
import javax.swing.text.html.HTMLDocument;
import javax.swing.text.html.HTMLEditorKit;
public class WebC {
// FileUtil f;
int linkamount=0;
ArrayList<URL> visited = new ArrayList<URL>();
ArrayList<String> urls = new ArrayList<String>();
public WebC() {
try {
// f= new FileUtil();
sendGetRequest("http://www.google.com");
} catch (IOException e) {
e.printStackTrace();
}
catch (BadLocationException e) {
e.printStackTrace();
}
}
public static void main(String[] args) {
new WebC();
}
public void sendGetRequest(String path) throws IOException, BadLocationException, MalformedURLException {
URL url = new URL(path);
HttpURLConnection con = (HttpURLConnection) url.openConnection();
con.setRequestMethod("GET");
con.setRequestProperty("Content-Language", "en-US");
BufferedReader rd = new BufferedReader(new InputStreamReader(con.getInputStream()));
EditorKit kit = new HTMLEditorKit();
HTMLDocument doc = (HTMLDocument)kit.createDefaultDocument();
doc.putProperty("IgnoreCharsetDirective", new Boolean(true));
kit.read(rd, doc, 0);
//Get all <a> tags (hyperlinks)
HTMLDocument.Iterator it = doc.getIterator(HTML.Tag.A);
while (it.isValid())
{
MutableAttributeSet mas = (MutableAttributeSet)it.getAttributes();
//get the HREF attribute value in the <a> tag
String link = (String)mas.getAttribute(HTML.Attribute.HREF);
if(link!=null && link!="") {
urls.add(link);
}
it.next();
}
for(int i=urls.size()-1;i>=0;i--) {
if(urls.get(i)!=null) {
if(/*f.searchforString(urls.get(i)) ||*/ visited.contains(new URL(urls.get(i)))) {
urls.remove(i);
continue;
} else {
System.out.println(linkamount++);
System.out.println(path);
visited.add(new URL(path));
//f.write(urls.get(i));
sendGetRequest(urls.get(i));
}
try {
Thread.sleep(100);
} catch (InterruptedException e) {
e.printStackTrace();
}
}
}
}
}
老實說,我不知道如何解決這個問題。顯然谷歌有一個href標籤是不是一個有效的網址,我將如何解決這個問題?
感謝,得到它現在的工作! –
另一個問題彈出,與此代碼: http://pastie.org/7164939 我得到: http://pastie.org/7164948 –
問題是「..」在www的結尾處.google.com。您希望在打開連接前檢查這種邊界情況。在這種特殊情況下,您想檢查HREF是否包含「。」在追加到鏈接之前。 –