C# Convert HTML to plain text
/// <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", "\n"); _tags.Add("blockquote", "\n"); _tags.Add("div", "\n"); _tags.Add("dl", "\n"); _tags.Add("fieldset", "\n"); _tags.Add("form", "\n"); _tags.Add("h1", "\n"); _tags.Add("/h1", "\n"); _tags.Add("h2", "\n"); _tags.Add("/h2", "\n"); _tags.Add("h3", "\n"); _tags.Add("/h3", "\n"); _tags.Add("h4", "\n"); _tags.Add("/h4", "\n"); _tags.Add("h5", "\n"); _tags.Add("/h5", "\n"); _tags.Add("h6", "\n"); _tags.Add("/h6", "\n"); _tags.Add("p", "\n"); _tags.Add("/p", "\n"); _tags.Add("table", "\n"); _tags.Add("/table", "\n"); _tags.Add("ul", "\n"); _tags.Add("/ul", "\n"); _tags.Add("ol", "\n"); _tags.Add("/ol", "\n"); _tags.Add("/li", "\n"); _tags.Add("br", "\n"); _tags.Add("/td", "\t"); _tags.Add("/tr", "\n"); _tags.Add("/pre", "\n"); _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</param> /// <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 <body> _text.Clear(); } else if (tag == "/body") { // Discard content after </body> _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 == '\n') 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, '\r', '\n' }, _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"></param> 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</param> public void Write(char c) { if (_preformatted) { // Write preformatted character _text.Append(c); } else { if (c == '\r') { // Ignore carriage returns. We'll process // '\n' if it comes next } else if (c == '\n') { // 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(); } } }

Hot AI Tools

Undresser.AI Undress
AI-powered app for creating realistic nude photos

AI Clothes Remover
Online AI tool for removing clothes from photos.

Undress AI Tool
Undress images for free

Clothoff.io
AI clothes remover

AI Hentai Generator
Generate AI Hentai for free.

Hot Article

Hot Tools

Notepad++7.3.1
Easy-to-use and free code editor

SublimeText3 Chinese version
Chinese version, very easy to use

Zend Studio 13.0.1
Powerful PHP integrated development environment

Dreamweaver CS6
Visual web development tools

SublimeText3 Mac version
God-level code editing software (SublimeText3)

Hot Topics



In C language, special characters are processed through escape sequences, such as: \n represents line breaks. \t means tab character. Use escape sequences or character constants to represent special characters, such as char c = '\n'. Note that the backslash needs to be escaped twice. Different platforms and compilers may have different escape sequences, please consult the documentation.

In C, the char type is used in strings: 1. Store a single character; 2. Use an array to represent a string and end with a null terminator; 3. Operate through a string operation function; 4. Read or output a string from the keyboard.

In C language, the main difference between char and wchar_t is character encoding: char uses ASCII or extends ASCII, wchar_t uses Unicode; char takes up 1-2 bytes, wchar_t takes up 2-4 bytes; char is suitable for English text, wchar_t is suitable for multilingual text; char is widely supported, wchar_t depends on whether the compiler and operating system support Unicode; char is limited in character range, wchar_t has a larger character range, and special functions are used for arithmetic operations.

The usage methods of symbols in C language cover arithmetic, assignment, conditions, logic, bit operators, etc. Arithmetic operators are used for basic mathematical operations, assignment operators are used for assignment and addition, subtraction, multiplication and division assignment, condition operators are used for different operations according to conditions, logical operators are used for logical operations, bit operators are used for bit-level operations, and special constants are used to represent null pointers, end-of-file markers, and non-numeric values.

The difference between multithreading and asynchronous is that multithreading executes multiple threads at the same time, while asynchronously performs operations without blocking the current thread. Multithreading is used for compute-intensive tasks, while asynchronously is used for user interaction. The advantage of multi-threading is to improve computing performance, while the advantage of asynchronous is to not block UI threads. Choosing multithreading or asynchronous depends on the nature of the task: Computation-intensive tasks use multithreading, tasks that interact with external resources and need to keep UI responsiveness use asynchronous.

In C language, char type conversion can be directly converted to another type by: casting: using casting characters. Automatic type conversion: When one type of data can accommodate another type of value, the compiler automatically converts it.

There is no built-in sum function in C language, so it needs to be written by yourself. Sum can be achieved by traversing the array and accumulating elements: Loop version: Sum is calculated using for loop and array length. Pointer version: Use pointers to point to array elements, and efficient summing is achieved through self-increment pointers. Dynamically allocate array version: Dynamically allocate arrays and manage memory yourself, ensuring that allocated memory is freed to prevent memory leaks.

The char array stores character sequences in C language and is declared as char array_name[size]. The access element is passed through the subscript operator, and the element ends with the null terminator '\0', which represents the end point of the string. The C language provides a variety of string manipulation functions, such as strlen(), strcpy(), strcat() and strcmp().
