private void GetElementsStringList(string html, ref List <string> eleList)
{
var info = new HtmlInfo
{
TagName =
System.Text.RegularExpressions.Regex.Match(html, @"(?<=\<\s{0,5}|\<)([a-z,A-Z]+|h\d{1})(?=\>|\s)",
RegexOptions.IgnoreCase).Value
};
var currentTagBeginReg = @"<\s{0,10}" + info.TagName + @".*?>"; //获取当前标签元素开始标签正则
var currentTagEndReg = @"\<\/" + info.TagName + @"\>"; //获取当前标签元素收尾标签正则
if (string.IsNullOrEmpty(info.TagName))
{
return;
}
string eleHtml;
//情况1 <a/>
//情况2 <a></a>
//情况3 <a> 错误格式
//情况4endif
if (Regex.IsMatch(html, @"<\s{0,10}" + info.TagName + "[^<].*?/>"))//单标签
{
eleHtml = Regex.Match(html, @"<\s{0,10}" + info.TagName + "[^<].*?/>").Value;
}
else if (!Regex.IsMatch(html, currentTagEndReg))//没有收尾
{
if (Regex.IsMatch(html, @"\s{0,10}\<\!\-\-\[if"))
{
eleHtml = GetElementString(html, @"\s{0,10}\<\!\-\-\[if", @"\[endif\]\-\-\>", 1);
}
else
{
eleHtml = Regex.Match(html, currentTagBeginReg, RegexOptions.Singleline).Value;
}
}
else
{
eleHtml = GetElementString(html, currentTagBeginReg, currentTagEndReg, 1);
}
try
{
eleList.Add(eleHtml);
html = html.Replace(eleHtml, "");
html = Regex.Replace(html, @"<\!DOCTYPE.*?>", "");
if (!Regex.IsMatch(html, @"^\s*$"))
{
GetElementsStringList(html, ref eleList);
}
}
catch (Exception ex)
{
throw new Exception("SORRY,您的HTML格式不能解析！！！");
}
}
