登录  /  注册

C# 将 HTML 转成纯文本

大家讲道理
发布: 2016-11-10 10:15:47
原创
1124人浏览过

/// <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() == &#39;<&#39;)
            {
                // 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() : &#39; &#39;);
                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() == &#39;<&#39;)
        {
            MoveAhead();
 
            // Parse tag name
            EatWhitespace();
            int start = _pos;
            if (Peek() == &#39;/&#39;)
                MoveAhead();
            while (!EndOfText && !Char.IsWhiteSpace(Peek()) &&
                Peek() != &#39;/&#39; && Peek() != &#39;>&#39;)
                MoveAhead();
            tag = _html.Substring(start, _pos - start).ToLower();
 
            // Parse rest of tag
            while (!EndOfText && Peek() != &#39;>&#39;)
            {
                if (Peek() == &#39;"&#39; || Peek() == &#39;\&#39;&#39;)
                    EatQuotedValue();
                else
                {
                    if (Peek() == &#39;/&#39;)
                        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() == &#39;<&#39;)
            {
                // 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 == &#39;\n&#39;)
                break;
        }
    }
 
    // Moves the current position past a quoted value
    protected void EatQuotedValue()
    {
        char c = Peek();
        if (c == &#39;"&#39; || c == &#39;\&#39;&#39;)
        {
            // Opening quote
            MoveAhead();
            // Find end of value
            int start = _pos;
            _pos = _html.IndexOfAny(new char[] { c, &#39;\r&#39;, &#39;\n&#39; }, _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 == &#39;\r&#39;)
                {
                    // Ignore carriage returns. We&#39;ll process
                    // &#39;\n&#39; if it comes next
                }
                else if (c == &#39;\n&#39;)
                {
                    // 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(&#39; &#39;);
                }
                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();
        }
    }
}
登录后复制

智能AI问答
PHP中文网智能助手能迅速回答你的编程问题,提供实时的代码和解决方案,帮助你解决各种难题。不仅如此,它还能提供编程资源和学习指导,帮助你快速提升编程技能。无论你是初学者还是专业人士,AI智能助手都能成为你的可靠助手,助力你在编程领域取得更大的成就。
来源:php中文网
本文内容由网友自发贡献,版权归原作者所有,本站不承担相应法律责任。如您发现有涉嫌抄袭侵权的内容,请联系admin@php.cn
作者最新文章
最新问题
热门教程
更多>
最新下载
更多>
网站特效
网站源码
网站素材
前端模板
关于我们 免责申明 意见反馈 讲师合作 广告合作 最新更新
php中文网:公益在线php培训,帮助PHP学习者快速成长!
关注服务号 技术交流群
PHP中文网订阅号
每天精选资源文章推送
PHP中文网APP
随时随地碎片化学习
PHP中文网抖音号
发现有趣的

Copyright 2014-2024 https://www.php.cn/ All Rights Reserved | php.cn | 湘ICP备2023035733号