asp.net 获取HTML meta标记中的内容

 

public   static   string  GetSingleTagValueByAttr( string  inputstring,  string  tagName,  string  attrname,  string  key)
         ... {
            Regex reg = new Regex("<" + tagName + " [^<>]*>", RegexOptions.IgnoreCase);
            MatchCollection matchs = reg.Matches(inputstring);
            string result = string.Empty;
            foreach (Match match in matchs)
            ...{
                string matchValue = match.Value;
                Regex regValue = new Regex("content=".*"", RegexOptions.IgnoreCase);
                if (matchValue.ToLower().IndexOf(attrname.ToLower() + "="" + key.ToLower() + """) != -1)
                ...{
                    if (regValue.IsMatch(matchValue))
                    ...{
                        result = regValue.Match(matchValue).Value;
                        if (!string.IsNullOrEmpty(result))
                        ...{
                            result = result.Replace("CONTENT=", "").Replace("content=","").Replace(""", "");
                        }
                    }
                    return result;
                }
            }
            return null;
        }

 

使用举例：

获取关键词 GetSingleTagValueByAttr(data, "meta", "name", "Keywords");   data是HTML源代码
获取描述GetSingleTagValueByAttr(data, "meta", "name", "Discription");