Get valid URLs from sitemap (no spidering because I'm lazy)

SitemapService.cs

public IEnumerable<Uri> GetSitemapUrls(Uri sitemapUrl)
{
    var sitemapText = GetSitemapText(sitemapUrl);

    if (string.IsNullOrWhiteSpace(sitemapText))
        yield break;

    var urlRegex = new Regex(@"\b(?:https?://|www\.)[^ \f\n\r\t\v\]]+\b", RegexOptions.Compiled | RegexOptions.IgnoreCase);

    foreach (Match m in urlRegex.Matches(sitemapText))
        yield return new Uri(CleanUriString(m.Value));
}

string GetSitemapText(Uri sitemapUri)
{
    var wc = new WebClient
    {
        Encoding = System.Text.Encoding.UTF8
    };

    return wc.DownloadString(sitemapUri);
}

string CleanUriString(string dirtyUriString)
{
    var legalCharacters = @"ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-._~:/?#[]@!$&'()*+,;=".ToCharArray();

    var cleanedString = dirtyUriString;

    foreach (var character in dirtyUriString)
    {
        var matchIndex = dirtyUriString.IndexOf(character);

        if (!legalCharacters.Any(x => x.Equals(character)) && matchIndex > 0)
            cleanedString = dirtyUriString.Substring(0, matchIndex);
    }

    return cleanedString;
}