public htmlTag(string strTag, string strHTML, int iLineNr, htmlTag pParentTag, htmlTag pPreviousTag)
{
_tag = strTag.Trim().ToUpper();
_html = strHTML.Trim();
_lineNr = iLineNr;
_attributes = new System.Collections.Generic.Dictionary <string, string>();
_parentTag = pParentTag;
_previousTag = pPreviousTag;
_nextTag = null;
_innerTags = new List <htmlTag>();
}
public htmlTag()
{
_tag = "";
_html = "";
_lineNr = 0;
_attributes = new System.Collections.Generic.Dictionary <string, string>();
_parentTag = null;
_previousTag = null;
_nextTag = null;
_innerTags = new List <htmlTag>();
}
/// <summary>
/// Returns the first tag from InnerTags that matches HTML expression.
/// Takes a case-insensitive regular expression as search string.
/// </summary>
public htmlTag FirstHtml(string strHTML)
{
foreach (htmlTag t in this.InnerTags)
{
if (Regex.IsMatch(t.Html, strHTML, RegexOptions.IgnoreCase))
{
return(t);
}
htmlTag t2 = t.FirstHtml(strHTML);
if (t2 != null)
{
return(t2);
}
}
//return null if nothing is found
return(null);
}
/// <summary>
/// Parses the given HTML code.
/// If Tag is given it will match tags with that name.
/// If attribute is given it will match tags having that attribute.
/// If value is given it will match tags with any attribute having that value.
/// If both attribute and value is given it will match attributes with that value.
/// </summary>
public void Parse(string strHTML)
{
#region Init/Clear local variables
htmlTag lastTag = null;
Int32 currLineNr = 1;
htmlTag currParent = null;
this.AllTags.Clear();
this.InnerTags.Clear();
#endregion
do
{
Match mCurrHtml;
// Process comments
if ((mCurrHtml = Regex.Match(strHTML, @"^\s*(<!--((?!-->).)*-->|<![^<>]+>|<!\[[^\s/<>]+\[((?!\]\]>).)*\]\]>)\s*", RegexOptions.IgnoreCase | RegexOptions.Singleline)).Success)
{
htmlTag t = new htmlTag("<COMMENT>", mCurrHtml.Groups[0].Value, currLineNr, currParent, lastTag);
if (currParent == null)
{
this.InnerTags.Add(t);
}
else
{
t.ParentTag.InnerTags.Add(t);
}
if (lastTag != null)
{
lastTag.NextTag = t;
}
lastTag = t;
this.AllTags.Add(t);
currLineNr += mCurrHtml.Groups[0].Value.Split('\n').Length - 1;
strHTML = Regex.Replace(strHTML, @"^\s*(<!--((?!-->).)*-->|<![^<>]+>|<!\[[^\s/<>]+\[((?!\]\]>).)*\]\]>)\s*", "", RegexOptions.IgnoreCase | RegexOptions.Singleline);
}
// Process scripts
else if ((mCurrHtml = Regex.Match(strHTML, @"^\s*(<script(?<a>\s+[^>]*)?>(?<s>((?!</script>).)*)</script>)\s*", RegexOptions.IgnoreCase | RegexOptions.Singleline)).Success)
{
htmlTag t = new htmlTag("<SCRIPT>", mCurrHtml.Groups[0].Value, currLineNr, currParent, lastTag);
if (currParent == null)
{
this.InnerTags.Add(t);
}
else
{
t.ParentTag.InnerTags.Add(t);
}
if (lastTag != null)
{
lastTag.NextTag = t;
}
lastTag = t;
this.AllTags.Add(t);
// Process tag attributes
MatchCollection mAttributeCollection = Regex.Matches(mCurrHtml.Groups["a"].Value, "\\s+(?<a>[^\\n/>\"'’=]+)\\s*=\\s*([\"'])(?<v>[^\"']*)[\"']|\\s+(?<a>[^\\n/>\"'’=]+)", RegexOptions.IgnoreCase | RegexOptions.Singleline);
foreach (Match mAttribute in mAttributeCollection)
{
if (t.Attributes.ContainsKey(mAttribute.Groups["a"].Value.Trim()))
{
t.Attributes[mAttribute.Groups["a"].Value.Trim()] = mAttribute.Groups["v"].Value.Trim();
}
else
{
t.Attributes.Add(mAttribute.Groups["a"].Value.Trim(), mAttribute.Groups["v"].Value.Trim());
}
}
currLineNr += mCurrHtml.Groups[0].Value.Split('\n').Length - 1;
strHTML = Regex.Replace(strHTML, @"^\s*(<script(?<a>\s+[^>]*)?>(?<s>((?!</script>).)*)</script>)\s*", "", RegexOptions.IgnoreCase | RegexOptions.Singleline);
}
// Process tags
else if ((mCurrHtml = Regex.Match(strHTML, @"^\s*<(?<t>[^\s/<>]+)(?<a>\s+[^>]*?)?\s*(?<c>/)?>\s*", RegexOptions.IgnoreCase | RegexOptions.Singleline)).Success)
{
htmlTag t = new htmlTag("<" + mCurrHtml.Groups["t"].Value + ">", mCurrHtml.Groups[0].Value, currLineNr, currParent, lastTag);
if (currParent == null)
{
this.InnerTags.Add(t);
}
else
{
t.ParentTag.InnerTags.Add(t);
}
if (lastTag != null)
{
lastTag.NextTag = t;
}
lastTag = t;
this.AllTags.Add(t);
// Process tag attributes
MatchCollection mAttributeCollection = Regex.Matches(mCurrHtml.Groups["a"].Value, "\\s+(?<a>[^\\n/>\"'’=]+)\\s*=\\s*([\"'])(?<v>[^\"']*)[\"']|\\s+(?<a>[^\\n/>\"'’=]+)", RegexOptions.IgnoreCase | RegexOptions.Singleline);
foreach (Match mAttribute in mAttributeCollection)
{
if (t.Attributes.ContainsKey(mAttribute.Groups["a"].Value.Trim()))
{
t.Attributes[mAttribute.Groups["a"].Value.Trim()] = mAttribute.Groups["v"].Value.Trim();
}
else
{
t.Attributes.Add(mAttribute.Groups["a"].Value.Trim(), mAttribute.Groups["v"].Value.Trim());
}
}
// Treat tag as parent if it does not have /> ending
if (mCurrHtml.Groups["c"].Value == "")
{
currParent = t;
}
currLineNr += mCurrHtml.Groups[0].Value.Split('\n').Length - 1;
strHTML = Regex.Replace(strHTML, @"^\s*<(?<t>[^\s/<>]+)(?<a>\s+[^>]*?)?\s*(?<c>/)?>\s*", "", RegexOptions.IgnoreCase | RegexOptions.Singleline);
}
// Process closing tags
else if ((mCurrHtml = Regex.Match(strHTML, @"^\s*</(?<t>[^\s/<>]+)( /)?>\s*", RegexOptions.IgnoreCase | RegexOptions.Singleline)).Success)
{
if (currParent != null)
{
currParent = currParent.ParentTag;
}
currLineNr += mCurrHtml.Groups[0].Value.Split('\n').Length - 1;
strHTML = Regex.Replace(strHTML, @"^\s*</(?<t>[^\s/<>]+)( /)?>\s*", "", RegexOptions.IgnoreCase | RegexOptions.Singleline);
}
// Process text in between tags
else if ((mCurrHtml = Regex.Match(strHTML, @"^\s*([^<]+)(?=<)", RegexOptions.IgnoreCase | RegexOptions.Singleline)).Success)
{
htmlTag t = new htmlTag("<TEXT>", mCurrHtml.Groups[0].Value, currLineNr, currParent, lastTag);
if (currParent == null)
{
this.InnerTags.Add(t);
}
else
{
t.ParentTag.InnerTags.Add(t);
}
if (lastTag != null)
{
lastTag.NextTag = t;
}
lastTag = t;
this.AllTags.Add(t);
currLineNr += mCurrHtml.Groups[0].Value.Split('\n').Length - 1;
strHTML = Regex.Replace(strHTML, @"^\s*([^<]+)(?=<)", "", RegexOptions.IgnoreCase | RegexOptions.Singleline);
}
else
{
// Remove unrecognized stuff and just keep on going. May of course cause missing elements so if you find it skipping something important please let me know.
strHTML = Regex.Replace(strHTML, "^.+?(?=<)", "", RegexOptions.IgnoreCase | RegexOptions.Singleline);
}
// Generate an error if number of html tags exceed 10.000.000
if (this.AllTags.Count > 10000000)
{
throw new Exception("Number of tags in document have exceeded 10.000.000 entries! Surely something must be wrong!");
}
} while (!Regex.IsMatch(strHTML, @"^\s*$", RegexOptions.Singleline));
}
/// <summary>
/// Returns the first tag from InnerTags that matches all given search expressions.
/// If Tag is given it will return tags with names that match.
/// If attribute is given it return tags with attributes that match.
/// If value is given it will return tags with any attribute having values that match.
/// If both attribute and value is given it will return tags with any attributes that match having a value that match.
/// All parameters take a case-insensitive regular expression as search string.
/// </summary>
public htmlTag FirstTag(string strTag, string strAttribute, string strValue)
{
foreach (htmlTag t in this.InnerTags)
{
bool bFound = true;
// Check if current Tag matches criteria
if (!string.IsNullOrEmpty(strTag) && !Regex.IsMatch(t.Tag, strTag, RegexOptions.IgnoreCase))
{
bFound = false;
}
if (!string.IsNullOrEmpty(strAttribute) && !string.IsNullOrEmpty(strValue))
{
bool bAttVal = false;
foreach (string s in t.Attributes.Keys)
{
if (Regex.IsMatch(s, strAttribute, RegexOptions.IgnoreCase) && Regex.IsMatch(t.Attributes[s], strValue, RegexOptions.IgnoreCase))
{
bAttVal = true;
}
}
if (!bAttVal)
{
bFound = false;
}
;
}
else if (!string.IsNullOrEmpty(strAttribute))
{
bool bAttVal = false;
foreach (string s in t.Attributes.Keys)
{
if (Regex.IsMatch(s, strAttribute, RegexOptions.IgnoreCase))
{
bAttVal = true;
}
}
if (!bAttVal)
{
bFound = false;
}
;
}
else if (!string.IsNullOrEmpty(strValue))
{
bool bAttVal = false;
foreach (string s in t.Attributes.Values)
{
if (Regex.IsMatch(s, strValue, RegexOptions.IgnoreCase))
{
bAttVal = true;
}
}
if (!bAttVal)
{
bFound = false;
}
;
}
// Return current Tag if it matches criteria
if (bFound)
{
return(t);
}
// Search InnerTags
htmlTag t2 = t.FirstTag(strTag, strAttribute, strValue);
if (t2 != null)
{
return(t2);
}
}
//return null if nothing is found
return(null);
}
