|
/// <summary>
/// 得到分页后的数据
/// </summary>
/// <param name="param">文章内容</param>
/// <param name="size">文章字数（不包含HTML）</param>
/// <returns></returns>
public static List<string> SubstringTo(string param, int size)
{
param = NoHTML(param);//过滤一些有Wap上面不能显示的HTML标签，你也不可不过滤
var length = param.ToCharArray().Length;
var being = 0;
var list = new List<string>();
while (true)
{
string str = SubstringToHTML(param, being, size, "", out being);
list.Add(str);
if (length <= being)
{
break;
}
}
return list;
}
/// <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="param">将要截取的字符串参数</param>
/// <param name="length">截取的字节长度</param>
/// <param name="end">字符串末尾补上的字符串</param>
/// <returns>返回截取后的字符串</returns>
public static string SubstringToHTML(string param, int being, int length, string end, out int index)
{
string Pattern = null;
MatchCollection m = null;
StringBuilder result = new StringBuilder();
int n = 0;
char temp;
bool isCode = false; //是不是HTML代码
bool isHTML = false; //是不是HTML特殊字符,如
char[] pchar = param.ToCharArray();
int i = 0;
for (i = being; i < pchar.Length; i++)
{
temp = pchar[i];
if (temp == '<')
{
isCode = true;
}
else if (temp == '&')
{
isHTML = true;
}
else if (temp == '>' && isCode)
{
//n = n - 1;
isCode = false;
}
else if (isHTML)
{
isHTML = false;
}
if (!isCode && !isHTML)
{
n = n + 1;
//UNICODE码字符占两个字节
if (System.Text.Encoding.Default.GetBytes(temp + "").Length > 1)
{
n = n + 1;
}
}
result.Append(temp);
if (n >= length)
{
break;
}
}
index = i + 1;
result.Append(end);
//去掉成对的HTML标记,我的正则表达式不好，所以这里写得不好，大家可以写个正则直接去掉所有的
temp_result = Regex.Replace(temp_result, @"(?is)<p[^>]*?>.*?</p>", "$2", RegexOptions.IgnoreCase);
temp_result = Regex.Replace(temp_result, @"(?is)<a[^>]*?>.*?</a>", "$2", RegexOptions.IgnoreCase);
temp_result = Regex.Replace(temp_result, @"(?is)<img[^>]*>", "$2", RegexOptions.IgnoreCase);
temp_result = Regex.Replace(temp_result, @"(?is)<br[^>]*>", "$2", RegexOptions.IgnoreCase);
//用正则表达式取出标记
Pattern = ("</([a-zA-Z]+)*>");
m = Regex.Matches(temp_result, Pattern);
ArrayList bengHTML = new ArrayList();
foreach (Match mt in m)
{
bengHTML.Add(mt.Result("$1"));
}
//补全前面不成对的HTML标记
for (int nn = bengHTML.Count - 1; nn >= 0; nn--)
{
result.Insert(0, "<" + bengHTML[nn] + ">");
}
//用正则表达式取出标记
Pattern = ("<([a-zA-Z]+)[^<>]*>");
m = Regex.Matches(temp_result, Pattern);
ArrayList endHTML = new ArrayList();
foreach (Match mt in m)
{
endHTML.Add(mt.Result("$1"));
}
//补全后面不成对的HTML标记
for (int nn = endHTML.Count - 1; nn >= 0; nn--)
{
result.Append("</");
result.Append(endHTML[nn]);
result.Append(">");
}
return result.ToString();
}
|
