c#使用正则表达式抓取a标签的链接和innerhtml

  //读取网页html
            string 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();

图解正则

 

朋友需要截取img标签的src 和data-url   跟上面差不多。。顺便附上

?

1 2 3 4 5 6 7 8 9 10 11 12 13 14 15

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();                }            }