Java regex для извлечения ссылки из текста

// this is not working

Потому что ваше регулярное выражение чувствительно к регистру.

Пытаться:-

Pattern p = Pattern.compile("href=\"(.*?)\"", Pattern.CASE_INSENSITIVE);

Редактировать1:
Чтобы получить этикетку, используйте Pattern.compile("(?<=>).*?(?=</a>)", Pattern.CASE_INSENSITIVE) и m.group(0).

Редактировать2:
Чтобы заменить тег (включая метку) последней строкой, используйте: -

text.replaceAll("(?i)<a href=\"(.*?)</a>", "new substring here")

Вы можете использовать текст общего доступа apacheStringEscapeUtils для декодирования html-сущностей, а затем replaceAll, то есть:

import org.apache.commons.text.StringEscapeUtils;

String text = "Some content which contains link as <A HREF=\"/relative-path/fruit.cgi?param1=abc&param2=xyz\">URL Label</A> and some text after it";
String output = StringEscapeUtils.unescapeHtml4(text).replaceAll("([^<]+).+\"(.*?)\">(.*?)<[^>]+>(.*)", "$1https://google.com$2&your_param ($3)$4");
System.out.print(output);
// Some content which contains link as https://google.com/relative-path/fruit.cgi?param1=abc&param2=xyz&your_param (URL Label) and some text after it

Демо:

1. jdoodle
2. Regex Объяснение

public static void main(String args[]) {
    String text = "Some content which contains link as <A HREF=\"/relative-path/fruit.cgi?param1=abc&param2=xyz\">URL Label</A> and some text after it and another link <A HREF=\"/relative-path/vegetables.cgi?param1=abc&param2=xyz\">URL2 Label</A> and some more text";
    text = StringEscapeUtils.unescapeHtml4(text);
    Pattern p = Pattern.compile("<a href=\"(.*?)\">(.*?)</a>", Pattern.CASE_INSENSITIVE);
    Matcher m = p.matcher(text);
    while (m.find()) {
        text = text.replace(m.group(0), cleanUrlPart(m.group(1), m.group(2)));
    }
    System.out.println(text);
}

private static String cleanUrlPart(String url, String label) {
    if (!url.startsWith("http") && !url.startsWith("www")) {
        if (url.startsWith("/")) {
            url = "http://www.google.com" + url;
        } else {
            url = "http://www.google.com/" + url;
        }
    }
    url = appendQueryParams(url, "myParam=pqr").toString();
    if (label != null && !label.isEmpty()) url += " (" + label + ")";
    return url;
}

Вывод

Some content which contains link as http://www.google.com/relative-path/fruit.cgi?param1=abc&param2=xyz&myParam=pqr (URL Label) and some text after it and another link http://www.google.com/relative-path/vegetables.cgi?param1=abc&param2=xyz&myParam=pqr (URL2 Label) and some more text

Почти готово:

public static void main(String[] args) throws URISyntaxException {
        String text = "Some content which contains link as <A HREF=\"/relative-path/fruit.cgi?param1=abc&param2=xyz\">URL Label</A> and some text after it and another link <A HREF=\"/relative-path/vegetables.cgi?param1=abc&param2=xyz\">URL2 Label</A> and some more text";
        text = StringEscapeUtils.unescapeHtml4(text);
        System.out.println(text);
        System.out.println("**************************************");
        Pattern patternTag = Pattern.compile("<a([^>]+)>(.+?)</a>", Pattern.CASE_INSENSITIVE);
        Pattern patternLink = Pattern.compile("href=\"(.*?)\"", Pattern.CASE_INSENSITIVE);
        Matcher matcherTag = patternTag.matcher(text);

        while (matcherTag.find()) {
            String href = matcherTag.group(1); // href
            String linkText = matcherTag.group(2); // link text
            System.out.println("Href: " + href);
            System.out.println("Label: " + linkText);
            Matcher matcherLink = patternLink.matcher(href);
            String finalText = null;
            while (matcherLink.find()) {
                String link = matcherLink.group(1);
                System.out.println("Link: " + link);
                finalText = getFinalText(link, linkText);
                break;
            }
            System.out.println("***************************************");
            // replacing logic goes here
        }
        System.out.println(text);
    }

    public static String getFinalText(String link, String label) throws URISyntaxException {
        link = appendBaseURI(link);
        link = appendQueryParams(link, "myParam=ABCXYZ");
        return link + " (" + label + ")";
    }

    public static String appendQueryParams(String uriToUpdate, String queryParamsToAppend) throws URISyntaxException {
        URI oldUri = new URI(uriToUpdate);
        String newQueryParams = oldUri.getQuery();
        if (newQueryParams == null) {
            newQueryParams = queryParamsToAppend;
        } else {
            newQueryParams += "&" + queryParamsToAppend;  
        }
        URI newUri = new URI(oldUri.getScheme(), oldUri.getAuthority(),
                oldUri.getPath(), newQueryParams, oldUri.getFragment());
        return newUri.toString();
    }

    public static String appendBaseURI(String url) {
        String baseURI = "http://www.google.com/";
        if (url.startsWith("/")) {
            url = url.substring(1, url.length());
        }
        if (url.startsWith(baseURI)) {
            return url;
        } else {
            return baseURI + url;
        }
    }