Question

我正在尝试创建一个程序，用于在文本文件中查找任何类型的URL，例如hxxp：//www.testsite.com/images/logo.png。下面的代码是我尝试增加在线教程，（主要是在我的代码之上引用。）但是我无法捕获任何/所有URL，包括嵌入在html标记内的URL。我会感谢任何有关我可以尝试的帮助或建议。谢谢。

/* Reference: http://www.vogella.com/tutorials/JavaRegularExpressions/article.html 
*/
package de.vogella.regex.weblinks;

import java.io.BufferedReader;
import java.io.FileReader; 
import java.io.IOException;
import java.net.MalformedURLException;
import java.util.ArrayList;
import java.util.List;
import java.util.regex.Matcher;  
import java.util.regex.Pattern;

public class LinkGetter {

//variables 
private Pattern htmltag;
private Pattern link;

public LinkGetter() {
    //Patterns. 
    htmltag = Pattern.compile("<a\\b[^>]*href=\"[^>]*>(.*?)</a>");
    link = Pattern.compile(
"((https?|ftp|gopher|telnet|file):((//)|(\\\\))+[\\w\\d:#@%/;$()~_?\\+-=\\\\\\.&]*)");  

}

public static void main(String[] args){

    String filepath ="TestFile.rtf";

    System.out.println(new LinkGetter().getLinks(filepath));

} 


public List<String> getLinks(String filepath) { 
    List<String> links = new ArrayList<String>();
    try {
        FileReader FR = new FileReader("TestFile.rtf");
        BufferedReader bufferedReader = new BufferedReader(FR);

        String A;
        StringBuilder builder = new StringBuilder();
        while ((A = bufferedReader.readLine()) != null) {
            builder.append(A);
        }

        Matcher tagmatch = htmltag.matcher(builder.toString());
        while (tagmatch.find()) {
            Matcher matcher = link.matcher(tagmatch.group());
            matcher.find(); 
            String link = matcher.group().replaceFirst("href=\"", "")
                    .replaceFirst("\">", "")
                    .replaceFirst("\"[\\s]?target=\"[a-zA-Z_0-9]*", "");


            if (valid(link)) {
                links.add(makeAbsolute(filepath, link));

            }

            bufferedReader.close();
        }

    } catch (MalformedURLException e) {
        e.printStackTrace();
    } catch (IOException e) {
        e.printStackTrace();
    }
    return links;

}

private boolean valid(String A) {
    if (A.matches("javascript:.*|mailto:.*")) {
        return false;
    }
    return true;
}

private String makeAbsolute(String filepath, String link) {
    if (link.matches("http://.*")) {
        return link;
    }
    else if (link.matches("/.*") || link.matches(".*$[^/]")) {
        return "/" + link;

    throw new RuntimeException("Cannot make absolute. File: " + filepath
            + " Link " + link);
}


}

Answer 1

您可以尝试：

(https?|ftp|gopher|telnet|file):\/\/([\w\-_]+(?:(?:\.[\w\-_]+)+))([\w\-\.,@?^=%&amp;:/~\+#]*[\w\-\@?^=%&amp;/~\+#])?

Answer 2

我在我的一个旧项目中使用过这个。应该工作。

 String regex="\\s*(?i)href\\s*=\\s*(\"([^\"]*\")|'[^']*'|([^'\">\\s]+))";
 Pattern pattern = Pattern.compile(regex);

用于查找URL的正则表达式

2 个答案: