java 从字符串中提取url_使用Java正则表达式从文本文档中提取URL

如果你想确保你真的匹配一个url地址,而不仅仅是一个以’www’开头的单词.您可以使用DVK之前提到的表达式.我修改了一点,并写了一个小代码段作为您的起点：

import java.util.*;

import java.util.regex.*;

class FindUrls

{

public static List extractUrls(String input) {

List result = new ArrayList();

Pattern pattern = Pattern.compile(

"\\b(((ht|f)tp(s?)\\:\\/\\/|~\\/|\\/)|www.)" +

"(\\w+:\\w+@)?(([-\\w]+\\.)+(com|org|net|gov" +

"|mil|biz|info|mobi|name|aero|jobs|museum" +

"|travel|[a-z]{2}))(:[\\d]{1,5})?" +

"(((\\/([-\\w~!$+|.,=]|%[a-f\\d]{2})+)+|\\/)+|\\?|#)?" +

"((\\?([-\\w~!$+|.,*:]|%[a-f\\d{2}])+=?" +

"([-\\w~!$+|.,*:=]|%[a-f\\d]{2})*)" +

"(&(?:[-\\w~!$+|.,*:]|%[a-f\\d{2}])+=?" +

"([-\\w~!$+|.,*:=]|%[a-f\\d]{2})*)*)*" +

"(#([-\\w~!$+|.,*:=]|%[a-f\\d]{2})*)?\\b");

Matcher matcher = pattern.matcher(input);

while (matcher.find()) {

result.add(matcher.group());

}

return result;

}

}