/// <summary>
/// using a regular expression, find all of the href or urls
/// in the content of the page
/// </summary>
/// <param name="content"></param>
private void GetAllImagesUrls( string content )
{
//regular expression Responsible for finding all images on html document.
string Pattern = @"(http://)[A-Za-z0-9\-\.]+\.[A-Za-z]{2,3}(:[a-zA-Z0-9]*)?/?([a-zA-Z0-9\-\._\?\,\'/\\\+&%\$#\=~])*[^\.\,\)\(\s].(jpg|.png|.gif|.tiff)";
Regex Regex = new Regex(Pattern, RegexOptions.Compiled | RegexOptions.IgnoreCase);
Matches = Regex.Matches(content);
ListOfDistinctMatches = Matches.Cast<Match>().Select(m => m.Value).Distinct().ToList();
}
private static string formatMsoftMatches(Msoft.MatchCollection matches)
{
Msoft.Match[] matchArr = matches.Cast <Msoft.Match>().ToArray();
return(string.Format("{0} matches: [{1}]",
matchArr.Length,
matchArr.Select(m => formatMsoftMatch(m))
.JoinStrings()));
}
public static Match2[] CreateMatches(Msoft.MatchCollection msoftMatches)
{
return(msoftMatches.Cast <Msoft.Match>()
.Select(m => CreateMatch(m))
.ToArray());
}
public static List<string> PreProcessPacket(MatchCollection matches)
{
var list = (matches.Cast<Match>().Select(line => line.Value.Trim())).ToList();
return list;
}
/// <summary>
/// Returns the input typed as a generic IEnumerable of the matches
/// </summary>
/// <param name="mc"></param>
/// <returns></returns>
public static IEnumerable <System.Text.RegularExpressions.Match> AsEnumerable(
this System.Text.RegularExpressions.MatchCollection mc)
{
return(mc.Cast <Match>());
}