国产精彩视频,噜啊噜在线,成人精品视频在线观看

本文實例講述了C#基于正則表達式抓取a標簽鏈接和innerhtml的方法。分享給大家供大家參考，具體如下：

				?

									//讀取網頁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);

									//抓取出來寫入的文件

									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("鏈接地址:{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();

圖解正則

C#基于正則表達式抓取a標簽鏈接和innerhtml的方法

朋友需要截取img標簽的src 和data-url 跟上面差不多。。順便附上

				?

									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);

									//抓取出來寫入的文件

									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("圖片src:{0},  圖片data-url：{1}", maths[i].Groups["src"].Value,

									        maths[i].Groups["dataurl"].Value) + "\r\n");

									      w.Write(bs, 0, bs.Length);

									      Console.WriteLine();

									    }

									}