C#基于正则表达式抓取a标签链接和innerhtml的方法

//读取网页htmlstring text = File.ReadAllText(Environment.CurrentDirectory + "//test.txt", Encoding.GetEncoding("gb2312"));string prttern = "<a(//s+(href=/"(?<url>([^/"])*)/"|'([^'])*'|//w+=/"(([^/"])*)/"|'([^'])*'))+>(?<text>(.*?))</a>";var maths = Regex.Matches(text, prttern);//抓取出来写入的文件using (FileStream w = new FileStream(Environment.CurrentDirectory + "//wirter.txt", FileMode.Create)){    for (int i = 0; i < maths.Count; i++)    {      byte[] bs = Encoding.UTF8.GetBytes(string.Format("链接地址:{0},  innerhtml：{1}", maths[i].Groups["url"].Value,        maths[i].Groups["text"].Value) + "/r/n");      w.Write(bs, 0, bs.Length);      Console.WriteLine();    }}Console.ReadKey();

string text =File.ReadAllText(Environment.CurrentDirectory + "//test.txt", Encoding.GetEncoding("gb2312"));string prttern = "<img(//s*(src=/"(?<src>[^/"]*?)/"|data-url=/"(?<dataurl>[^/"]*?)/"|[-//w]+=/"[^/"]*?/"))*//s*/>";var maths = Regex.Matches(text, prttern);//抓取出来写入的文件using (FileStream w = new FileStream(Environment.CurrentDirectory + "//wirter.txt", FileMode.Create)){    for (int i = 0; i < maths.Count; i++)    {      byte[] bs = Encoding.UTF8.GetBytes(string.Format("图片src:{0},  图片data-url：{1}", maths[i].Groups["src"].Value,        maths[i].Groups["dataurl"].Value) + "/r/n");      w.Write(bs, 0, bs.Length);      Console.WriteLine();    }}