/// <summary>
/// Converts HTML to plain text.
/// </summary>
class HtmlToText
{
// Static data tables
protected static Dictionary<string, string> _tags;
protected static HashSet<string> _ignoreTags;
// Instance variables
protected TextBuilder _text;
protected string _html;
protected int _pos;
// Static constructor (one time only)
static HtmlToText()
{
_tags = new Dictionary<string, string>();
_tags.Add("address", " ");
_tags.Add("blockquote", " ");
_tags.Add("p", " ");
_tags.Add("dl", " ");
_tags.Add("fieldset", " ");
_tags.Add("form", " ");
_tags.Add("h1", " ");
_tags.Add("/h1", " ");
_tags.Add("h2", " ");
_tags.Add("/h2", " ");
_tags.Add("h3", " ");
_tags.Add("/h3", " ");
_tags.Add("h4", " ");
_tags.Add("/h4", " ");
_tags.Add("h5", " ");
_tags.Add("/h5", " ");
_tags.Add("h6", " ");
_tags.Add("/h6", " ");
_tags.Add("p", " ");
_tags.Add("/p", " ");
_tags.Add("table", " ");
_tags.Add("/table", " ");
_tags.Add("ul", " ");
_tags.Add("/ul", " ");
_tags.Add("ol", " ");
_tags.Add("/ol", " ");
_tags.Add("/li", " ");
_tags.Add("br", " ");
_tags.Add("/td", " ");
_tags.Add("/tr", " ");
_tags.Add("/pre", " ");
_ignoreTags = new HashSet<string>();
_ignoreTags.Add("script");
_ignoreTags.Add("noscript");
_ignoreTags.Add("style");
_ignoreTags.Add("object");
}
/// <summary>
/// Converts the given HTML to plain text and returns the result.
/// </summary>
/// <param name="html">HTML to be converted
/// <returns>Resulting plain text</returns>
public string Convert(string html)
{
// Initialize state variables
_text = new TextBuilder();
_html = html;
_pos = 0;
// Process input
while (!EndOfText)
{
if (Peek() == '<')
{
// HTML tag
bool selfClosing;
string tag = ParseTag(out selfClosing);
// Handle special tag cases
if (tag == "body")
{
// Discard content before
_text.Clear();
}
else if (tag == "/body")
{
// Discard content after
_pos = _html.Length;
}
else if (tag == "pre")
{
// Enter preformatted mode
_text.Preformatted = true;
EatWhitespaceToNextLine();
}
else if (tag == "/pre")
{
// Exit preformatted mode
_text.Preformatted = false;
}
string value;
if (_tags.TryGetValue(tag, out value))
_text.Write(value);
if (_ignoreTags.Contains(tag))
EatInnerContent(tag);
}
else if (Char.IsWhiteSpace(Peek()))
{
// Whitespace (treat all as space)
_text.Write(_text.Preformatted ? Peek() : ' ');
MoveAhead();
}
else
{
// Other text
_text.Write(Peek());
MoveAhead();
}
}
// Return result
return HttpUtility.HtmlDecode(_text.ToString());
}
// Eats all characters that are part of the current tag
// and returns information about that tag
protected string ParseTag(out bool selfClosing)
{
string tag = String.Empty;
selfClosing = false;
if (Peek() == '<')
{
MoveAhead();
// Parse tag name
EatWhitespace();
int start = _pos;
if (Peek() == '/')
MoveAhead();
while (!EndOfText && !Char.IsWhiteSpace(Peek()) &&
Peek() != '/' && Peek() != '>')
MoveAhead();
tag = _html.Substring(start, _pos - start).ToLower();
// Parse rest of tag
while (!EndOfText && Peek() != '>')
{
if (Peek() == '"' || Peek() == ''')
EatQuotedValue();
else
{
if (Peek() == '/')
selfClosing = true;
MoveAhead();
}
}
MoveAhead();
}
return tag;
}
// Consumes inner content from the current tag
protected void EatInnerContent(string tag)
{
string endTag = "/" + tag;
while (!EndOfText)
{
if (Peek() == '<')
{
// Consume a tag
bool selfClosing;
if (ParseTag(out selfClosing) == endTag)
return;
// Use recursion to consume nested tags
if (!selfClosing && !tag.StartsWith("/"))
EatInnerContent(tag);
}
else MoveAhead();
}
}
// Returns true if the current position is at the end of
// the string
protected bool EndOfText
{
get { return (_pos >= _html.Length); }
}
// Safely returns the character at the current position
protected char Peek()
{
return (_pos < _html.Length) ? _html[_pos] : (char)0;
}
// Safely advances to current position to the next character
protected void MoveAhead()
{
_pos = Math.Min(_pos + 1, _html.Length);
}
// Moves the current position to the next non-whitespace
// character.
protected void EatWhitespace()
{
while (Char.IsWhiteSpace(Peek()))
MoveAhead();
}
// Moves the current position to the next non-whitespace
// character or the start of the next line, whichever
// comes first
protected void EatWhitespaceToNextLine()
{
while (Char.IsWhiteSpace(Peek()))
{
char c = Peek();
MoveAhead();
if (c == ' ')
break;
}
}
// Moves the current position past a quoted value
protected void EatQuotedValue()
{
char c = Peek();
if (c == '"' || c == ''')
{
// Opening quote
MoveAhead();
// Find end of value
int start = _pos;
_pos = _html.IndexOfAny(new char[] { c, ' ', ' ' }, _pos);
if (_pos < 0)
_pos = _html.Length;
else
MoveAhead(); // Closing quote
}
}
/// <summary>
/// A StringBuilder class that helps eliminate excess whitespace.
/// </summary>
protected class TextBuilder
{
private StringBuilder _text;
private StringBuilder _currLine;
private int _emptyLines;
private bool _preformatted;
// Construction
public TextBuilder()
{
_text = new StringBuilder();
_currLine = new StringBuilder();
_emptyLines = 0;
_preformatted = false;
}
/// <summary>
/// Normally, extra whitespace characters are discarded.
/// If this property is set to true, they are passed
/// through unchanged.
/// </summary>
public bool Preformatted
{
get
{
return _preformatted;
}
set
{
if (value)
{
// Clear line buffer if changing to
// preformatted mode
if (_currLine.Length > 0)
FlushCurrLine();
_emptyLines = 0;
}
_preformatted = value;
}
}
/// <summary>
/// Clears all current text.
/// </summary>
public void Clear()
{
_text.Length = 0;
_currLine.Length = 0;
_emptyLines = 0;
}
/// <summary>
/// Writes the given string to the output buffer.
/// </summary>
/// <param name="s">
public void Write(string s)
{
foreach (char c in s)
Write(c);
}
/// <summary>
/// Writes the given character to the output buffer.
/// </summary>
/// <param name="c">Character to write
public void Write(char c)
{
if (_preformatted)
{
// Write preformatted character
_text.Append(c);
}
else
{
if (c == ' ')
{
// Ignore carriage returns. We'll process
// ' ' if it comes next
}
else if (c == ' ')
{
// Flush current line
FlushCurrLine();
}
else if (Char.IsWhiteSpace(c))
{
// Write single space character
int len = _currLine.Length;
if (len == 0 || !Char.IsWhiteSpace(_currLine[len - 1]))
_currLine.Append(' ');
}
else
{
// Add character to current line
_currLine.Append(c);
}
}
}
// Appends the current line to output buffer
protected void FlushCurrLine()
{
// Get current line
string line = _currLine.ToString().Trim();
// Determine if line contains non-space characters
string tmp = line.Replace(" ", String.Empty);
if (tmp.Length == 0)
{
// An empty line
_emptyLines++;
if (_emptyLines < 2 && _text.Length > 0)
_text.AppendLine(line);
}
else
{
// A non-empty line
_emptyLines = 0;
_text.AppendLine(line);
}
// Reset current line
_currLine.Length = 0;
}
/// <summary>
/// Returns the current output as a string.
/// </summary>
public override string ToString()
{
if (_currLine.Length > 0)
FlushCurrLine();
return _text.ToString();
}
}
}</param name="c"></param name="s"></param name="html"></string></string, string></string></string, string>
