C# Replace替换问题 和 除去HTML标签
1、看到好多人遇到字符串Replace替换不成功的问题，大家要注意了
string aa = "亲爱的$name，感谢您选择该网站，您在该网站上的订单$no已经提交成功，请您在2小时内完成支付，以便我们尽快为您发货，如有问题请电：4007-336-337";
aa.Replace("$name", "ceshi000");
aa.Replace("$no", "2012090400032");
Response.Write(aa);
上面的代码看吧，看不出问题，但是替换的时候没成功，为什么呢？
原因是替换的时候要从新给字符串aa再次赋值，如下：
string aa = "亲爱的$name，感谢您选择该网站，您在该网站上的订单$no已经提交成功，请您在2小时内完成支付，以便我们尽快为您发货，如有问题请电：4007-336-337";
aa=aa.Replace("$name", "ceshi000");
aa=aa.Replace("$no", "2012090400032");
Response.Write(aa);
这样就能替换成功了。
2、大家做开发的时候，碰到一些内容是含有HTML标签的，有的时候是不需要的，怎么去除？如下：
string Smes= System.Text.RegularExpressions.Regex.Replace(message, "<.*?>", "").Replace(" ", "");
注：message就是含有HTML标签的内容。
3、上面的那个全部去除了
protected string gHtml(string Htmlstring)
{
try
{
if (HTMLTagsCheck.Check(Htmlstring))
{
Htmlstring = HTMLTagsCheck.Fix(Htmlstring);
}
}
catch
{ }
Htmlstring = Regex.Replace(Htmlstring, @"<script[^>]*?>.*?</script>", "", RegexOptions.IgnoreCase);
//删除HTML
//Htmlstring = Regex.Replace(Htmlstring, @"<(.[^>]*)>", "", RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"([\r\n])[\s]+", "", RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"<div", "<p", RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"</div>", "</p>", RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"-->", "", RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"<!--.*", "", RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"&(quot|#34);", "\"", RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"&(amp|#38);", "&", RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"&(lt|#60);", "<", RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"&(gt|#62);", ">", RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"&(nbsp|#160);", " ", RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"&(iexcl|#161);", "\xa1", RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"&(cent|#162);", "\xa2", RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"&(pound|#163);", "\xa3", RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"&(copy|#169);", "\xa9", RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"&#(\d+);", "", RegexOptions.IgnoreCase);
Htmlstring.Replace("\r\n", "");
// Htmlstring = HttpContext.Current.Server.HtmlEncode(Htmlstring).Trim();
if(Htmlstring.IndexOf("img.cdaily.1qfa.com/FY")==-1)
{
Htmlstring=Htmlstring.Replace("img.cdaily.1qfa.com","img.cdaily.1qfa.com/FY");
}
return Htmlstring;
}
/// <summary>
/// 检查HTML是否存在未闭合的标签
/// </summary>
/// <param name="str"></param>
/// <returns></returns>
public static bool Check(String str)
{
TagsList[] unclosedTags = getUnclosedTags(str);
if (unclosedTags[0].Size() != 0)
{
return false;
}
for (int i = 0; i < unclosedTags[1].Size(); i++)
{
if (unclosedTags[1].get(i) != null)
return false;
}
return true;
}
/// <summary>
/// 修复HTML未闭合的标签
/// </summary>
/// <param name="str">要进行修复的标签</param>
/// <returns></returns>
public static String Fix(String str)
{
try
{
StringBuilder sfixed = new StringBuilder(); // 存放修复后的字符串
TagsList[] unclosedTags = getUnclosedTags(str);
// 生成新字符串
for (int i = unclosedTags[0].Size() - 1; i > -1; i--)
{
sfixed.Append("<" + unclosedTags[0].get(i) + ">");
}
sfixed.Append(str);
for (int i = unclosedTags[1].Size() - 1; i > -1; i--)
{
String s = null;
if ((s = unclosedTags[1].get(i)) != null)
{
sfixed.Append("</" + s + ">");
}
}
return sfixed.ToString();
}
catch
{
return str;
}
}
private static TagsList[] getUnclosedTags(string _str)
{
StringBuilder temp = new StringBuilder(); // 存放标签
TagsList[] unclosedTags = new TagsList[2];
unclosedTags[0] = new TagsList(); // 前不闭合，如有</div>而前面没有<div>
unclosedTags[1] = new TagsList(); // 后不闭合，如有<div>而后面没有</div>
bool flag = false; // 记录双引号"或单引号'
char currentJump = ' '; // 记录需要跳过''还是""
char current = ' ', last = ' '; // 当前 & 上一个
// 开始判断
char[] str = _str.ToCharArray();
for (int i = 0; i < _str.Length; )
{
current = str[i++]; // 读取一个字符
if (current == '"' || current == '\'')
{
flag = flag ? false : true; // 若为引号，flag翻转
currentJump = current;
if (flag)
{
while (i < _str.Length && str[i++] != currentJump)
; // 跳过引号之间的部分
flag = false;
}
}
else if (current == '<')
{
if (i >= _str.Length)
break;
// 开始提取标签
current = str[i++];
if (current == '/')
{ // 标签的闭合部分，如</div>
current = str[i++];
// 读取标签
while (i < _str.Length && current != '>')
{
temp.Append(current);
current = str[i++];
}
// 从tags_bottom移除一个闭合的标签
if (!unclosedTags[1].remove(temp.ToString()))
{ // 若移除失败，说明前面没有需要闭合的标签
unclosedTags[0].add(temp.ToString()); // 此标签需要前闭合
}
temp.Remove(0, temp.Length); // 清空temp
}
else
{ // 标签的前部分，如<div>
last = current;
while (i < _str.Length && current != ' '
&& current != ' ' && current != '>')
{
temp.Append(current);
last = current;
current = str[i++];
}
// 已经读取到标签，跳过其他内容，如<div id=test>跳过id=test
while (i < _str.Length && current != '>')
{
last = current;
current = str[i++];
if (current == '"' || current == '\'')
{ // 判断双引号
flag = flag ? false : true;
currentJump = current;
if (flag)
{ // 若引号不闭合，跳过到下一个引号之间的内容
while (i < _str.Length
&& str[i++] != currentJump)
;
current = str[i++];
flag = false;
}
}
}
if (last != '/' && current == '>') // 判断这种类型：<TagName />
unclosedTags[1].add(temp.ToString());
temp.Remove(0, temp.Length);
}
}
}
return unclosedTags;
}
}
public class TagsList
{
private String[] data;
private int size = 0;
public TagsList(int size)
{
data = new String[size];
}
public TagsList()
: this(10)
{
}
public void add(String str)
{
ensureCapacity(size + 1);
data[size++] = str;
}
public String get(int index)
{
if (index < size)
return data[index];
else
return null;
}
//为了提高效率，只将其置为null
public bool remove(String str)
{
for (int index = size - 1; index >= 0; index--)
{
if (str.Equals(data[index]))
{
data[index] = null;
return true;
}
}
return false;
}
public bool remove(int index)
{
if (index < data.Length)
{
data[index] = null;
return true;
}
return false;
}
public int Size()
{
return this.size;
}
//扩展容量
public void ensureCapacity(int minSize)
{
int oldCapacity = data.Length;
if (minSize > oldCapacity)
{
int newCapacity = (oldCapacity * 3 / 2 + 1) > minSize ?
oldCapacity * 3 / 2 + 1 : minSize;
string[] newarr = new string[newCapacity];
Array.Copy(data, newarr, oldCapacity);
data = newarr;
}
}
}