How to extract URLs (href property) from HTML

05 Jan 2008

protected ArrayList getURL(string txtIn)
{
    ArrayList outURL = new ArrayList();
    Regex r = new Regex("href\\s*=\\s*(?:(?:\\\"(?[^\\\"]*)\\\")|(?[^\\s]* ))"</span>);
    MatchCollection mc1 = r.Matches(txtIn);

    foreach (Match m1 in mc1)
    {
        foreach (Group g in m1.Groups)
        {
            outURL.Add(g.Value);
        }
    }

    return outURL;
}</pre>

If you liked this post, 🗞 subscribe to my newsletter and follow me on 𝕏!