Question

I want to extract the http link from inside the anchor tags? The extension that should be extracted should be WMV files only.

Answer 1

Regex:

<a\\s*href\\s*=\\s*(?:(\"|\')(?<link>[^\"]*.wmv)(\"|\'))\\s*>(?<name>.*)\\s*</a>

[Note: \s* is used in several places to match the extra white space characters that can occur in the html.]

Sample C# code:

/// <summary>
/// Assigns proper values to link and name, if the htmlId matches the pattern
/// Matches only for .wmv files
/// </summary>
/// <returns>true if success, false otherwise</returns>
public static bool TryGetHrefDetailsWMV(string htmlATag, out string wmvLink, out string name)
{
    wmvLink = null;
    name = null;

    string pattern = "<a\\s*href\\s*=\\s*(?:(\"|\')(?<link>[^\"]*.wmv)(\"|\'))\\s*>(?<name>.*)\\s*</a>";

    if (Regex.IsMatch(htmlATag, pattern))
    {
        Regex r = new Regex(pattern, RegexOptions.IgnoreCase | RegexOptions.Compiled);
        wmvLink = r.Match(htmlATag).Result("${link}");
        name = r.Match(htmlATag).Result("${name}");
        return true;
    }
    else
        return false;
}

MyRegEx.TryGetHrefDetailsWMV("<td><a href='/path/to/file'>Name of File</a></td>", 
                out wmvLink, out name); // No match
MyRegEx.TryGetHrefDetailsWMV("<td><a href='/path/to/file.wmv'>Name of File</a></td>",
                out wmvLink, out name); // Match
MyRegEx.TryGetHrefDetailsWMV("<td><a    href='/path/to/file.wmv'   >Name of File</a></td>", out wmvLink, out name); // Match