public static List <HtmlTag> GetElementsByTagName(this HtmlDocument document, string tagName, EndTag endTag)
{
string html = document.InnerDocument.Replace('\n', ' ').Replace('\0', ' ');
MatchCollection matches = Regex.Matches(html, string.Format(@"(<{0}\s.*?>)|(<{0}>)", tagName), RegexOptions.IgnoreCase | RegexOptions.Compiled);
List <HtmlTag> tags = new List <HtmlTag>();
foreach (Match match in matches)
{
HtmlTag tag = new HtmlTag();
tag.EndTagType = endTag;
tag.Name = tagName.ToUpper();
if (endTag == EndTag.EndTag)
{
var s = Regex.Matches(match.Value, @"\w+");
if (s.Count > 0)
{
tag.Html = TagReader.ReadToEndTag(html, tagName, match);
}
}
else
{
tag.Html = match.Value;
}
tags.Add(tag);
}
return(tags);
}
private List <HtmlTag> GetChildNodes()
{
List <HtmlTag> nodes = new List <HtmlTag>();
if (EndTagType != EndTag.EndTag)
{
return(nodes);
}
string tempInner = InnerHtml.Replace('\n', ' ').Replace('\0', ' ');
var temp = Regex.Matches(tempInner, @"(?!</)(<(\w+).*?>)", RegexOptions.Compiled | RegexOptions.IgnoreCase);
while (temp.Count > 0)
{
EndTag endType = EndTag.SelfEnd;
var node = new HtmlTag();
node.Name = temp[0].Groups[2].Value.ToUpper();
var s = Regex.Matches(temp[0].Value, @"\w+");
if (s.Count > 0)
{
node.Html = TagReader.ReadToEndTag(tempInner, node.Name, temp[0], out endType);
}
tempInner = tempInner.Substring(node.Html.Length);
temp = Regex.Matches(tempInner, @"(?!</)(<(\w+).*?>)", RegexOptions.Compiled | RegexOptions.IgnoreCase);
node.EndTagType = endType;
nodes.Add(node);
}
return(nodes);
}