C# 采集页面数据

using HtmlAgilityPack;
using Nito.AsyncEx;
using System;
using System.Diagnostics;
using System.IO;
using System.IO.Compression;
using System.Net;
using System.Text;
using System.Threading;
using System.Threading.Tasks;

namespace test1
{
    class Program
    {
        static void Main(string[] args)
        {
            var uri = new Uri("https://www.baidu.com/");
            string pageHtml=AsyncContext.Run(() => GetHttpDomByUrl(uri));
            HtmlDocument thisnode = new HtmlDocument();
            thisnode.LoadHtml(pageHtml);
            var tnode = thisnode.DocumentNode;
            if (tnode.SelectSingleNode("//*/a[@name=\"tj_login\"]") != null)
            {
                Console.WriteLine("获取到的数据为:"+tnode.SelectSingleNode("//*/a[@name=\"tj_login\"]").Attributes["href"].Value);
            }
            Console.WriteLine("测试成功");
            Console.ReadKey();
        }
        public static CookieContainer CookiesContainer = new CookieContainer();//定义Cookie容器
        static CookieContainer cookie = new CookieContainer();//设置为全局，这样可以方便每个函数直接调用
        public static async Task<string> GetHttpDomByUrl(Uri uri, string proxy = null)
        {
            Thread.Sleep(1000);
            return await Task.Run(() =>
            {
                var pageSource = string.Empty;
                try
                {
                    //模拟浏览器请求
                    //if (this.OnStart != null) this.OnStart(this, new OnStartEventArgs(uri));
                    var watch = new Stopwatch();
                    watch.Start();
                    var request = (HttpWebRequest)WebRequest.Create(uri);
                    request.Accept = "*/*";
                    request.ServicePoint.Expect100Continue = false;//加快载入速度
                    request.ServicePoint.UseNagleAlgorithm = false;//禁止Nagle算法加快载入速度
                    request.AllowWriteStreamBuffering = false;//禁止缓冲加快载入速度
                    request.Headers.Add(HttpRequestHeader.AcceptEncoding, "gzip,deflate");//定义gzip压缩页面支持
                    request.ContentType = "application/x-www-form-urlencoded";//定义文档类型及编码
                    request.AllowAutoRedirect = true;//禁止自动跳转
                    //设置User-Agent，伪装成Google Chrome浏览器
                    request.UserAgent = "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/50.0.2661.102 Safari/537.36";
                    request.Timeout = 5000;//定义请求超时时间为5秒
                    request.KeepAlive = true;//启用长连接
                    request.Method = "GET";//定义请求方式为GET     
                    request.CookieContainer = cookie;
                    if (proxy != null)
                    {
                        request.Proxy = new WebProxy(proxy);//设置代理服务器IP，伪装请求地址
                    }
                    //request.CookieContainer = this.CookiesContainer;//附加Cookie容器
                    request.ServicePoint.ConnectionLimit = int.MaxValue;//定义最大连接数
                    using (var response = (HttpWebResponse)request.GetResponse())
                    {
                       
                        //获取请求响应
                        foreach (Cookie cookie in response.Cookies)
                        {
                            CookiesContainer.Add(cookie);//将Cookie加入容器，保存登录状态
                            
                        }
                        //判断网页是否被gzip压缩 
                        if (response.ContentEncoding.ToLower().Contains("gzip"))
                        {
                            //解压
                            using (GZipStream stream = new GZipStream(response.GetResponseStream(), CompressionMode.Decompress))
                            {
                                using (StreamReader reader = new StreamReader(stream, Encoding.UTF8))
                                {
                                    pageSource = reader.ReadToEnd();
                                }
                            }
                        }
                        //判断网页http头中是否Content-Encoding:deflate
                        else if (response.ContentEncoding.ToLower().Contains("deflate"))
                        {
                            //解压
                            using (DeflateStream stream = new DeflateStream(response.GetResponseStream(), CompressionMode.Decompress))
                            {
                                using (StreamReader reader = new StreamReader(stream, Encoding.UTF8))
                                {
                                    pageSource = reader.ReadToEnd();
                                }

                            }
                        }
                        //正常流获取网页
                        else
                        {
                            using (Stream stream = response.GetResponseStream())//原始
                            {
                                using (StreamReader reader = new StreamReader(stream, Encoding.UTF8))
                                {

                                    pageSource = reader.ReadToEnd();
                                }
                            }
                        }
                    }
                    request.Abort();
                    watch.Stop();
                    var threadId = System.Threading.Thread.CurrentThread.ManagedThreadId;//获取当前任务线程ID
                    var milliseconds = watch.ElapsedMilliseconds;//获取请求执行时间
                    //if (this.OnCompleted != null)
                    //{
                    //    this.OnCompleted(this, new OnCompletedEventArgs(uri, threadId, milliseconds, pageSource));
                    //    // Console.WriteLine("程序执行完成");
                    //}
                }
                catch (Exception ex)
                {
                    Console.WriteLine($"hello, task的线程ID为{Thread.CurrentThread.ManagedThreadId}");
                    Console.WriteLine(uri + $"请求页面失败正在重新请求,当前线程{Thread.CurrentThread.ManagedThreadId}:" + ex.Message.ToString());
                    Thread.Sleep(1000);
                    return AsyncContext.Run(() => GetHttpDomByUrl(uri));
                }
                return pageSource;
            });
        }
    }
}