C# substring完美截取HTML字符

注：此函数是在网上搜索得来，因此无法注明作者名，莫怪莫怪。嘿。

 /// <summary> /// 按字节长度截取字符串(支持截取带HTML代码样式的字符串) /// </summary> /// <param name="content">将要截取的字符串参数</param> /// <param name="length">截取的字节长度</param> /// <param name="StripHTML">截取的结果是否为html代码</param> /// <returns>截取的字符串</returns> public static string GetContentSummary(string content, int length, bool StripHTML) { if (string.IsNullOrEmpty(content) || length == 0) return ""; if (StripHTML) { System.Text.RegularExpressions.Regex re = new System.Text.RegularExpressions.Regex("<[^>]*>"); content = re.Replace(content, ""); content = content.Replace("　", "").Replace(" ", "").Replace(" ", ""); if (content.Length <= length) return content; else return content.Substring(0, length) + "..."; } else { if (content.Length <= length) return content; int pos = 0, npos = 0, size = 0; bool firststop = false, notr = false, noli = false; System.Text.StringBuilder sb = new System.Text.StringBuilder(); while (true) { if (pos >= content.Length) break; string cur = content.Substring(pos, 1); if (cur == "<") { string next = content.Substring(pos + 1, 3).ToLower(); if (next.IndexOf("p") == 0 && next.IndexOf("pre") != 0) { npos = content.IndexOf(">", pos) + 1; } else if (next.IndexOf("/p") == 0 && next.IndexOf("/pr") != 0) { npos = content.IndexOf(">", pos) + 1; if (size < length) sb.Append("<br />"); } else if (next.IndexOf("br") == 0) { npos = content.IndexOf(">", pos) + 1; if (size < length) sb.Append("<br />"); } else if (next.IndexOf("img") == 0) { npos = content.IndexOf(">", pos) + 1; if (size < length) { sb.Append(content.Substring(pos, npos - pos)); size += npos - pos + 1; } } else if (next.IndexOf("li") == 0 || next.IndexOf("/li") == 0) { npos = content.IndexOf(">", pos) + 1; if (size < length) { sb.Append(content.Substring(pos, npos - pos)); } else { if (!noli && next.IndexOf("/li") == 0) { sb.Append(content.Substring(pos, npos - pos)); noli = true; } } } else if (next.IndexOf("tr") == 0 || next.IndexOf("/tr") == 0) { npos = content.IndexOf(">", pos) + 1; if (size < length) { sb.Append(content.Substring(pos, npos - pos)); } else { if (!notr && next.IndexOf("/tr") == 0) { sb.Append(content.Substring(pos, npos - pos)); notr = true; } } } else if (next.IndexOf("td") == 0 || next.IndexOf("/td") == 0) { npos = content.IndexOf(">", pos) + 1; if (size < length) { sb.Append(content.Substring(pos, npos - pos)); } else { if (!notr) { sb.Append(content.Substring(pos, npos - pos)); } } } else { npos = content.IndexOf(">", pos) + 1; sb.Append(content.Substring(pos, npos - pos)); } if (npos <= pos) npos = pos + 1; pos = npos; } else { if (size < length) { sb.Append(cur); size++; } else { if (!firststop) { sb.Append("..."); firststop = true; } } pos++; } } return sb.ToString(); } }

 

本文来自CSDN博客，转载请标明出处：http://blog.csdn.net/LeiJuan903/archive/2009/03/05/3959102.aspx