【学习】爬糗事百科，可自动翻页。

namespace HTML
{
    class Program
    {
        const string qsbkMainUrl = "http://www.qiushibaike.com";

        private static string GetWBJokeUrl(int pageIndex)
        {

            StringBuilder url = new StringBuilder();

            url.Append(qsbkMainUrl);

            url.Append("/textnew/page/");

            url.Append(pageIndex.ToString());

            url.Append("/?s=4869039");

            return url.ToString();

        }

        //根据网页的url获取网页的html源码


        private static string GetUrlContent(string url)
        {
            try
            {

                HttpWebRequest request = (HttpWebRequest)WebRequest.Create(url);

                request.UserAgent = "Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Maxthon/4.4.8.1000 Chrome/30.0.1599.101 Safari/537.36";

                request.Method = "GET";

                request.ContentType = "text/html;charset=UTF-8";

                HttpWebResponse response = (HttpWebResponse)request.GetResponse();

                Stream myResponseStream = response.GetResponseStream();

                StreamReader myStreamReader = new StreamReader(myResponseStream, Encoding.GetEncoding("utf-8"));//因为知道糗百网页的编码方式为utf-8

                string retString = myStreamReader.ReadToEnd();

                myStreamReader.Close();

                myResponseStream.Close();

                return retString;

            }

            catch { return null; }

        }
        static void Main(string[] args)
        {
            System.Threading.Timer threadTimer = new System.Threading.Timer(new System.Threading.TimerCallback(Method3), null, 0, 5000);
            while (true)
            {
                Thread.Sleep(1000);
            }
        }

       static int first = 1;
       static int curNum=1;
       static void Method3(Object state)
        {
            List<JokeItem> a = GetJokeList(first == 1 ? curNum : first);
            int i = 1;
            Console.Clear();
            foreach (JokeItem item in a)
            {
                Console.WriteLine("笑话" + i + ":" + item.JokeContent + "
");
                i++;
            }
            curNum++;
        }
        public class JokeItem
        {

            private string nickName;

            /// <summary>

            /// 昵称

            /// </summary>

            public string NickName
            {

                get { return nickName; }

                set { nickName = value; }

            }



            private Image headImage;

            /// <summary>

            /// 头像

            /// </summary>

            public Image HeadImage
            {

                get { return headImage; }

                set { headImage = value; }

            }

            private string jokeContent;

            /// <summary>

            /// 笑话内容

            /// </summary>

            public string JokeContent
            {

                get { return jokeContent; }

                set { jokeContent = value; }

            }



            private string jokeUrl;

            /// <summary>

            /// 笑话地址

            /// </summary>

            public string JokeUrl
            {

                get { return jokeUrl; }

                set { jokeUrl = value; }

            }

        }

        /// <summary>

        /// 获取笑话列表

        /// </summary>

        /// <param name="htmlContent"></param>

        public static List<JokeItem> GetJokeList(int pageIndex)
        {

            string htmlContent = GetUrlContent(GetWBJokeUrl(pageIndex));
            List<JokeItem> jokeList = new List<JokeItem>();
            Regex rg = new Regex("<div class="content">\s*((.*|<br/>)*)", RegexOptions.IgnoreCase);

            JokeItem joke;

            MatchCollection matchResults = rg.Matches(htmlContent);



            foreach (Match result in matchResults)
            {
                joke = new JokeItem();
                joke.JokeContent = result.Groups[0].Value.Replace("<div class="content">", "").Replace("</span>", "").Replace("<span>", "").Replace("<br/>","");
                joke.JokeContent = Regex.Replace(joke.JokeContent, @"(
)+|(
)+", "");//去掉多余的空行
                joke.JokeContent = Regex.Replace(joke.JokeContent, @"(
)+", "
");
                jokeList.Add(joke);
            }

            return jokeList;

        }



 
    }
}