网站开发技术手记－读取html标签内容
private string GetSingleTagValueByAttr(string inputstring,string tagName,string attrname,string key)
{
Regex reg = new Regex("<" + tagName + " [^<>]*>",RegexOptions.IgnoreCase);
MatchCollection matchs = reg.Matches(inputstring);
string result = "";
foreach (Match match in matchs)
{
string matchValue = match.Value;
Regex regValue = new Regex("content=\".*\"",RegexOptions.IgnoreCase);
if (matchValue.ToLower().IndexOf(attrname + "=\"" + key + "\"") != -1)
{
if(regValue.IsMatch(matchValue))
{
result = regValue.Match(matchValue).Value;
if (!string.IsNullOrEmpty(result))
{
result =result.ToLower().Replace("content=","").Replace("\"","");
}
}
return result;
}
}
return "";
}
使用举例：
string description=GetSingleTagValueByAttr(sourceHTML,“meta”,"name","description");
string keywords =GetSingleTagValueByAttr(sourceHTML,“meta”,"name","keywords");
改进：添加读取属性参数，目前只限定了读取的是meta的congtent的内容。
2。读取封闭标签的内容：
private string GetFixTagContent(string inputstring,string tagName)
{
string leftTag = "<" + tagName + ">";
string rightTag="</"+tagName+">";
Regex reg = new Regex("<" +tagName+"[^<>]*>(.|\n)*" + rightTag,RegexOptions.IgnoreCase);
return reg.Match(inputstring).Value.Replace(leftTag, "").Replace(rightTag, "");
}
使用举例：
string title=GetFixTagContent(sourceHTML,"title");
