c#基于Titanium爬取微信公众号历史文章列表

using System;
using System.Collections.Generic;
using System.Linq;
using System.Net;
using System.Text.RegularExpressions;
using System.Threading;
using System.Threading.Tasks;
using System.Web;
using Newtonsoft.Json.Linq;
using Titanium.Web.Proxy;
using Titanium.Web.Proxy.Http;
using Titanium.Web.Proxy.Models;


namespace WechatArticleSpider
{
 public class SpiderProxy
 {
  private readonly SemaphoreSlim @lock = new SemaphoreSlim(1);
  private readonly ProxyServer proxyServer;
  private readonly ExplicitProxyEndPoint explicitEndPoint;


  public SpiderProxy()
  {
   proxyServer = new ProxyServer();
   //在响应之前事件
   proxyServer.BeforeResponse += ProxyServer_BeforeResponse;


   //绑定监听端口
   explicitEndPoint = new ExplicitProxyEndPoint(IPAddress.Any, 8000, true);
   Console.WriteLine("监听地址127.0.0.1:8000");
   //隧道请求连接前事件，HTTPS用
   explicitEndPoint.BeforeTunnelConnectRequest += ExplicitEndPoint_BeforeTunnelConnectRequest; ;


   //代理服务器注册监听地址
   proxyServer.AddEndPoint(explicitEndPoint);
  }


  public void Start()
  {
   Console.WriteLine("开始监听");
   //Start方法会检测证书，若为空会调用CertificateManager.EnsureRootCertificate();为我们自动生成根证书。
   proxyServer.Start();
  }


  public void Stop()
  {
   // Unsubscribe & Quit
   explicitEndPoint.BeforeTunnelConnectRequest -= ExplicitEndPoint_BeforeTunnelConnectRequest;
   proxyServer.BeforeResponse -= ProxyServer_BeforeResponse;


   Console.WriteLine("结束监听");
   proxyServer.Stop();
  }


  private async Task ExplicitEndPoint_BeforeTunnelConnectRequest(object sender, Titanium.Web.Proxy.EventArguments.TunnelConnectSessionEventArgs e)
  {
   string hostname = e.HttpClient.Request.RequestUri.Host;
   await WriteToConsole("Tunnel to: " + hostname);


   if (!hostname.StartsWith("mp.weixin.qq.com"))
   {
    //是否要解析SSL，不解析就直接转发
    e.DecryptSsl = false;
   }
  }


  private async Task ProxyServer_BeforeResponse(object sender, Titanium.Web.Proxy.EventArguments.SessionEventArgs e)
  {
   var request = e.HttpClient.Request;


   //判断是否是微信文章页。
   if (request.Host.Contains("mp.weixin.qq.com")&&(request.RequestUriString.StartsWith("/s&＃63;") || request.RequestUriString.StartsWith("/s/")))
   {
    byte[] bytes = await e.GetResponseBody();
    string body = System.Text.Encoding.UTF8.GetString(bytes);
    ThreadPool.QueueUserWorkItem((stateInfo) => { CrawlAsync(body, e.HttpClient.Request); }); 
   }
  }


  private async Task CrawlAsync(string body,Request request)
  {
   //采用正则表达式匹配数据
   Match match = Regex.Match(body, @"(.+)");
   Match matchGhid = Regex.Match(body, @"var user_name = ""(.+)"";");
   if (!match.Success || !matchGhid.Success)
   {
    return;
   }


   MatchCollection matches = Regex.Matches(body, @"(.+)");
   if (match.Groups.Count == 0)
   {
    return;
   }
   await WriteToConsole("检测到微信文章页: " + match.Groups[1].Value + " " + matches[0].Groups[1].Value + " " + matches[1].Groups[1].Value + " ");


   var queryString = HttpUtility.ParseQueryString(request.RequestUriString.Substring(3));
   var httpClient = new HttpClient(request.Headers);
   await WriteToConsole("Client实例化，已获取header，COOKIE");


   //获取历史页信息
   string result = httpClient.Get(string.Format("https://mp.weixin.qq.com/mp/profile_ext&＃63;action=home&__biz={0}&scene=124#wechat_redirect", queryString["__biz"]));
   //封接口检测
   if (result.Contains("操作频繁，请稍后再试"))
   {
    await WriteToConsole("操作频繁，请稍后再试 限制24小时 请更换微信");
    await WriteToConsole("已停止爬虫任务，请更换之后重启助手。");
   }


   //是否抓取完
   bool end = false;
   //下标
   int offset = 0;


   do
   {
    //获取历史消息
    string jsOnResult= httpClient.Get(string.Format("https://mp.weixin.qq.com/mp/profile_ext&＃63;action=getmsg&__biz={0}&f=json&offset={1}&count=10&is_ok=1&scene=124&uin={2}&key={3}&pass_ticket={4}&wxtoken=&x5=0&f=json", queryString["__biz"], offset, queryString["uin"], queryString["key"], queryString["pass_ticket"]));
    JObject jobject = JObject.Parse(jsonResult);
    if (Convert.ToInt32(jobject["ret"]) == 0)
    {
     if (Convert.ToInt32(jobject["can_msg_continue"]) == 0)
     {
      end = true;
     }
     offset = Convert.ToInt32(jobject["next_offset"]);
     string strList = jobject["general_msg_list"].ToString();
     JObject temp = JObject.Parse(strList);
     List list = temp["list"].ToList();
     foreach (var item in list)
     {
      JToken comm_msg_info = item["comm_msg_info"];
      JToken app_msg_ext_info = item["app_msg_ext_info"];
      if (app_msg_ext_info == null)
      {
       continue;
      }
      //发布时间
      string publicTime = comm_msg_info["datetime"].ToString();
      //文章标题
      string title = app_msg_ext_info["title"].ToString();
      //文章摘要
      string digest = app_msg_ext_info["digest"].ToString();
      //文章地址
      string content_url = app_msg_ext_info["content_url"].ToString();
      //文章封面
      string cover = app_msg_ext_info["cover"].ToString();
      //作者
      string author = app_msg_ext_info["author"].ToString();


      await WriteToConsole(String.Format("{0},{1},{2},{3},{4},{5}", publicTime, title, digest, content_url, cover, author));


      //今天发布了多条消息
      if (app_msg_ext_info["is_multi"].ToString() == "1")
      {
       foreach (var multiItem in app_msg_ext_info["multi_app_msg_item_list"].ToList())
       {
        title = multiItem["title"].ToString();
        digest = multiItem["digest"].ToString();
        content_url = multiItem["content_url"].ToString();
        cover = multiItem["cover"].ToString();
        author = multiItem["author"].ToString();
        await WriteToConsole(String.Format("{0},{1},{2},{3},{4},{5}", publicTime, title, digest, content_url, cover, author));
       }
      }
     }
    }
    else
    {
     end = true;
    }
    //每5秒翻页一次
    await Task.Delay(5000);
   } while (!end);


   await WriteToConsole("历史文章抓取完成");


  }


  private async Task WriteToConsole(string message, ConsoleColor&＃63; cOnsoleColor= null)
  {
   await @lock.WaitAsync();


   if (consoleColor.HasValue)
   {
    ConsoleColor existing = Console.ForegroundColor;
    Console.ForegroundColor = consoleColor.Value;
    Console.WriteLine(message);
    Console.ForegroundColor = existing;
   }
   else
   {
    Console.WriteLine(message);
   }


   @lock.Release();
  }
 }
}

using System;
using System.IO;
using System.Net;
using System.Threading;
using Titanium.Web.Proxy.Http;


namespace WechatArticleSpider
{
 class HttpClient
 {
  private readonly HeaderCollection headerCollection;
  private readonly COOKIEContainer COOKIECOntainer= new COOKIEContainer();


  /// 

  /// 微信请求客户端
  /// 
  /// 拦截微信请求头集合
  public HttpClient(HeaderCollection headerCollection)
  {
   COOKIECOntainer= new COOKIEContainer();
   ServicePointManager.DefaultCOnnectionLimit= 512;
   ServicePointManager.SecurityProtocol = SecurityProtocolType.Tls12 | SecurityProtocolType.Tls11;
   this.headerCollection = headerCollection;
  }


  /// 

  /// 带微信参数的GET请求
  /// 
  /// 请求地址
  /// 请求结果
  public string Get(string url)
  {
   string ret = Retry(() =>
   {
    HttpWebRequest webRequest = WebRequest.CreateHttp(url);
    webRequest = PretendWechat(webRequest);
    HttpWebResponse respOnse= webRequest.GetResponse() as HttpWebResponse;
    string result = new StreamReader(response.GetResponseStream()).ReadToEnd();
    return result;
   });
   return ret;
  }


  /// 

  /// 伪造微信请求
  /// 
  /// 需要伪造的request
  /// 
  public HttpWebRequest PretendWechat(HttpWebRequest request)
  {
   try
   {
    request.Host = headerCollection.Headers["Host"].Value;
    request.UserAgent = headerCollection.Headers["User-Agent"].Value;
    request.Headers.Set(headerCollection.Headers["Accept-Language"].Name, headerCollection.Headers["Accept-Language"].Value);
    request.Headers.Set(headerCollection.Headers["Accept-Encoding"].Name, headerCollection.Headers["Accept-Encoding"].Value);
    COOKIEContainer.SetCOOKIEs(new Uri("https://mp.weixin.qq.com"), headerCollection.Headers["COOKIE"].Value.Replace(";", ","));
    request.KeepAlive = true;
    request.Accept = headerCollection.Headers["Accept"].Value;
    request.AutomaticDecompression = DecompressionMethods.Deflate | DecompressionMethods.GZip;
    request.COOKIECOntainer= COOKIEContainer;
    request.AllowAutoRedirect = true;
    request.ServicePoint.Expect100COntinue= false;
    request.Timeout = 35000;
    return request;
   }
   catch (Exception e)
   {
    Console.WriteLine(e.Message);
    throw;
   }
  }


  /// 

  /// 三次重试机制
  /// 
  /// 参数类型
  /// 方法
  /// 
  private static T Retry(Func func)
  {
   int err = 0;
   while (err <3)
   {
    try
    {
     return func();
    }
    catch (WebException webExp)
    {
     err++;
     Thread.Sleep(5000);
     if (err > 2)
     {
      throw webExp;
     }
    }
   }
   return func();
  }
 }
}