特色栏目： python 批处理 net编程 Javascript Php Asp Css Html5 Android seo centos

.NET Core 实现定时抓取网站文章并发送到邮箱

来源：互联网收集：自由互联发布时间：2021-07-08

前言大家好，我是晓晨。许久没有更新博客了，今天给大家带来一篇干货型文章，一个每隔5分钟抓取博客园首页文章信息并在第二天的上午9点发送到你的邮箱的小工具。比如我在201

前言

大家好，我是晓晨。许久没有更新博客了，今天给大家带来一篇干货型文章，一个每隔5分钟抓取博客园首页文章信息并在第二天的上午9点发送到你的邮箱的小工具。比如我在2018年2月14日，9点来到公司我就会收到一封邮件，是2018年2月13日的博客园首页的文章信息。写这个小工具的初衷是，一直有看博客的习惯，但是最近由于各种原因吧，可能几天都不会看一下博客，要是中途错过了什么好文可是十分心疼的哈哈。所以做了个工具，每天归档发到邮箱，妈妈再也不会担心我错过好的文章了。为什么只抓取首页？因为博客园首页文章的质量相对来说高一些。

准备

作为一个持续运行的工具，没有日志记录怎么行，我准备使用的是NLog来记录日志，它有个日志归档功能非常不错。在http请求中，由于网络问题吧可能会出现失败的情况，这里我使用Polly来进行Retry。使用HtmlAgilityPack来解析网页，需要对xpath有一定了解。下面是详细说明：

组件名用途 github NLog 记录日志 https://github.com/NLog/NLog Polly 当http请求失败，进行重试 https://github.com/App-vNext/Polly HtmlAgilityPack 网页解析 https://github.com/zzzprojects/html-agility-pack MailKit 发送邮件 https://github.com/jstedfast/MailKit

有不了解的组件，可以通过访问github获取资料。

参考文章

https://www.jb51.net/article/112595.htm

获取&解析博客园首页数据

我是用的是HttpWebRequest来进行http请求，下面分享一下我简单封装的类库：

using System;
using System.IO;
using System.Net;
using System.Text;

namespace CnBlogSubscribeTool
{
 /// <summary>
 /// Simple Http Request Class
 /// .NET Framework >= 4.0
 /// Author:stulzq
 /// CreatedTime:2017-12-12 15:54:47
 /// </summary>
 public class HttpUtil
 {
 static HttpUtil()
 {
  //Set connection limit ,Default limit is 2
  ServicePointManager.DefaultConnectionLimit = 1024;
 }

 /// <summary>
 /// Default Timeout 20s
 /// </summary>
 public static int DefaultTimeout = 20000;

 /// <summary>
 /// Is Auto Redirect
 /// </summary>
 public static bool DefalutAllowAutoRedirect = true;

 /// <summary>
 /// Default Encoding
 /// </summary>
 public static Encoding DefaultEncoding = Encoding.UTF8;

 /// <summary>
 /// Default UserAgent
 /// </summary>
 public static string DefaultUserAgent =
  "Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/62.0.3202.94 Safari/537.36"
  ;

 /// <summary>
 /// Default Referer
 /// </summary>
 public static string DefaultReferer = "";

 /// <summary>
 /// httpget request
 /// </summary>
 /// <param name="url">Internet Address</param>
 /// <returns>string</returns>
 public static string GetString(string url)
 {
  var stream = GetStream(url);
  string result;
  using (StreamReader sr = new StreamReader(stream))
  {
  result = sr.ReadToEnd();
  }
  return result;

 }

 /// <summary>
 /// httppost request
 /// </summary>
 /// <param name="url">Internet Address</param>
 /// <param name="postData">Post request data</param>
 /// <returns>string</returns>
 public static string PostString(string url, string postData)
 {
  var stream = PostStream(url, postData);
  string result;
  using (StreamReader sr = new StreamReader(stream))
  {
  result = sr.ReadToEnd();
  }
  return result;

 }

 /// <summary>
 /// Create Response
 /// </summary>
 /// <param name="url"></param>
 /// <param name="post">Is post Request</param>
 /// <param name="postData">Post request data</param>
 /// <returns></returns>
 public static WebResponse CreateResponse(string url, bool post, string postData = "")
 {
  var httpWebRequest = WebRequest.CreateHttp(url);
  httpWebRequest.Timeout = DefaultTimeout;
  httpWebRequest.AllowAutoRedirect = DefalutAllowAutoRedirect;
  httpWebRequest.UserAgent = DefaultUserAgent;
  httpWebRequest.Referer = DefaultReferer;
  if (post)
  {

  var data = DefaultEncoding.GetBytes(postData);
  httpWebRequest.Method = "POST";
  httpWebRequest.ContentType = "application/x-www-form-urlencoded;charset=utf-8";
  httpWebRequest.ContentLength = data.Length;
  using (var stream = httpWebRequest.GetRequestStream())
  {
   stream.Write(data, 0, data.Length);
  }
  }

  try
  {
  var response = httpWebRequest.GetResponse();
  return response;
  }
  catch (Exception e)
  {
  throw new Exception(string.Format("Request error,url:{0},IsPost:{1},Data:{2},Message:{3}", url, post, postData, e.Message), e);
  }
 }

 /// <summary>
 /// http get request
 /// </summary>
 /// <param name="url"></param>
 /// <returns>Response Stream</returns>
 public static Stream GetStream(string url)
 {
  var stream = CreateResponse(url, false).GetResponseStream();
  if (stream == null)
  {

  throw new Exception("Response error,the response stream is null");
  }
  else
  {
  return stream;

  }
 }

 /// <summary>
 /// http post request
 /// </summary>
 /// <param name="url"></param>
 /// <param name="postData">post data</param>
 /// <returns>Response Stream</returns>
 public static Stream PostStream(string url, string postData)
 {
  var stream = CreateResponse(url, true, postData).GetResponseStream();
  if (stream == null)
  {

  throw new Exception("Response error,the response stream is null");
  }
  else
  {
  return stream;

  }
 }


 }
}

获取首页数据

string res = HttpUtil.GetString(https://www.cnblogs.com);

解析数据

我们成功获取到了html，但是怎么提取我们需要的信息（文章标题、地址、摘要、作者、发布时间）呢。这里就亮出了我们的利剑HtmlAgilityPack，他是一个可以根据xpath来解析网页的组件。

载入我们前面获取的html：

HtmlDocument doc = new HtmlDocument();
doc.LoadHtml(html);

从上图中，我们可以看出，每条文章所有信息都在一个class为post_item的div里，我们先获取所有的class=post_item的div

//获取所有文章数据项
var itemBodys = doc.DocumentNode.SelectNodes("//div[@class='post_item_body']");

我们继续分析，可以看出文章的标题在class=post_item_body的div下面的h3标签下的a标签，摘要信息在class=post_item_summary的p标签里面，发布时间和作者在class=post_item_foot的div里，分析完毕，我们可以取出我们想要的数据了：

foreach (var itemBody in itemBodys)
{
 //标题元素
 var titleElem = itemBody.SelectSingleNode("h3/a");
 //获取标题
 var title = titleElem?.InnerText;
 //获取url
 var url = titleElem?.Attributes["href"]?.Value;

 //摘要元素
 var summaryElem = itemBody.SelectSingleNode("p[@class='post_item_summary']");
 //获取摘要
 var summary = summaryElem?.InnerText.Replace("\r\n", "").Trim();

 //数据项底部元素
 var footElem = itemBody.SelectSingleNode("div[@class='post_item_foot']");
 //获取作者
 var author = footElem?.SelectSingleNode("a")?.InnerText;
 //获取文章发布时间
 var publishTime = Regex.Match(footElem?.InnerText, "\\d+-\\d+-\\d+ \\d+:\\d+").Value;
 Console.WriteLine($"标题：{title}");
 Console.WriteLine($"网址：{url}");
 Console.WriteLine($"摘要：{summary}");
 Console.WriteLine($"作者：{author}");
 Console.WriteLine($"发布时间：{publishTime}");
 Console.WriteLine("--------------华丽的分割线---------------");
}

运行一下：

我们成功的获取了我们想要的信息。现在我们定义一个Blog对象将它们装起来。

public class Blog
{
 /// <summary>
 /// 标题
 /// </summary>
 public string Title { get; set; }

 /// <summary>
 /// 博文url
 /// </summary>
 public string Url { get; set; }

 /// <summary>
 /// 摘要
 /// </summary>
 public string Summary { get; set; }

 /// <summary>
 /// 作者
 /// </summary>
 public string Author { get; set; }

 /// <summary>
 /// 发布时间
 /// </summary>
 public DateTime PublishTime { get; set; }
}

http请求失败重试

我们使用Polly在我们的http请求失败时进行重试，设置为重试3次。

//初始化重试器
_retryTwoTimesPolicy =
 Policy
 .Handle<Exception>()
 .Retry(3, (ex, count) =>
 {
  _logger.Error("Excuted Failed! Retry {0}", count);
  _logger.Error("Exeption from {0}", ex.GetType().Name);
 });

测试一下：

可以看到当遇到exception是Polly会帮我们重试三次，如果三次重试都失败了那么会放弃。

发送邮件

使用MailKit来进行邮件发送，它支持IMAP，POP3和SMTP协议，并且是跨平台的十分优秀。下面是根据前面园友的分享自己封装的一个类库：

using System.Collections.Generic;
using CnBlogSubscribeTool.Config;
using MailKit.Net.Smtp;
using MimeKit;

namespace CnBlogSubscribeTool
{
 /// <summary>
 /// send email
 /// </summary>
 public class MailUtil
 {
 private static bool SendMail(MimeMessage mailMessage,MailConfig config)
 {
  try
  {
  var smtpClient = new SmtpClient();
  smtpClient.Timeout = 10 * 1000; //设置超时时间
  smtpClient.Connect(config.Host, config.Port, MailKit.Security.SecureSocketOptions.None);//连接到远程smtp服务器
  smtpClient.Authenticate(config.Address, config.Password);
  smtpClient.Send(mailMessage);//发送邮件
  smtpClient.Disconnect(true);
  return true;

  }
  catch
  {
  throw;
  }

 }

 /// <summary>
 ///发送邮件
 /// </summary>
 /// <param name="config">配置</param>
 /// <param name="receives">接收人</param>
 /// <param name="sender">发送人</param>
 /// <param name="subject">标题</param>
 /// <param name="body">内容</param>
 /// <param name="attachments">附件</param>
 /// <param name="fileName">附件名</param>
 /// <returns></returns>
 public static bool SendMail(MailConfig config,List<string> receives, string sender, string subject, string body, byte[] attachments = null,string fileName="")
 {
  var fromMailAddress = new MailboxAddress(config.Name, config.Address);
  
  var mailMessage = new MimeMessage();
  mailMessage.From.Add(fromMailAddress);
  
  foreach (var add in receives)
  {
  var toMailAddress = new MailboxAddress(add);
  mailMessage.To.Add(toMailAddress);
  }
  if (!string.IsNullOrEmpty(sender))
  {
  var replyTo = new MailboxAddress(config.Name, sender);
  mailMessage.ReplyTo.Add(replyTo);
  }
  var bodyBuilder = new BodyBuilder() { HtmlBody = body };

  //附件
  if (attachments != null)
  {
  if (string.IsNullOrEmpty(fileName))
  {
   fileName = "未命名文件.txt";
  }
  var attachment = bodyBuilder.Attachments.Add(fileName, attachments);

  //解决中文文件名乱码
  var charset = "GB18030";
  attachment.ContentType.Parameters.Clear();
  attachment.ContentDisposition.Parameters.Clear();
  attachment.ContentType.Parameters.Add(charset, "name", fileName);
  attachment.ContentDisposition.Parameters.Add(charset, "filename", fileName);

  //解决文件名不能超过41字符
  foreach (var param in attachment.ContentDisposition.Parameters)
   param.EncodingMethod = ParameterEncodingMethod.Rfc2047;
  foreach (var param in attachment.ContentType.Parameters)
   param.EncodingMethod = ParameterEncodingMethod.Rfc2047;
  }

  mailMessage.Body = bodyBuilder.ToMessageBody();
  mailMessage.Subject = subject;

  return SendMail(mailMessage, config);

 }
 }
}

测试一下：