最近我要做一个爬虫。这个爬虫需要如下几个步骤:
1 填写注册内容(需要邮箱注册)
2 过拖拽验证码(geetest)
3 注册成功会给邮箱发一封确认邮箱
4 点击确认邮箱中的链接 完成注册
我这里就采用163邮箱注册。
邮箱协议有 pop3 和 imap 和 smtp
我试了pop3 不能够筛选邮件 例如筛选未读 和 发件人这2个条件 所以放弃用pop3
imap协议是支持的。
我就找了一个开源的第三方lib:S22.Imap
用法很简单:
public void Test163() { var imapServer = "imap.163.com"; var port = 993; using (ImapClient client = new ImapClient(imapServer, port, "xxxx@163.com", "pwd", AuthMethod.Login, true)) { // Returns a collection of identifiers of all mails matching the specified search criteria. IEnumerable<uint> uids = client.Search(SearchCondition.Unseen()); // Download mail messages from the default mailbox. IEnumerable<MailMessage> messages = client.GetMessages(uids,FetchOptions.HtmlOnly); Console.WriteLine("We are connected!"); } }
发现 在login的时候 报错了:
提示“NO Select Unsafe Login. Please contact kefu@188.com for help”。
163邮箱也会收到一个告警邮件
经过查证 发现得需要在发送 login 命令之前 得先发送 id 命令
至于为什么要这么做 我的理解是得先伪装成普通的客户端吧(有理解错误请指出谢谢)
我fork了一份SS2.imap的代码 打算兼容163的这个特殊情况改掉源码
然后走Login方法就不会报错了
Github地址:https://github.com/yuzd/S22.Imap
http://www.mimekit.net/docs/html/M_MailKit_Net_Imap_ImapClient_Identify.htm
public static void Capabilities ()
{
using (var client = new ImapClient ()) {
client.Connect ("imap.gmail.com", 993, SecureSocketOptions.SslOnConnect);
var mechanisms = string.Join (", ", client.AuthenticationMechanisms);
Console.WriteLine ("The IMAP server supports the following SASL authentication mechanisms: {0}", mechanisms);
client.Authenticate ("username", "password");
if (client.Capabilities.HasFlag (ImapCapabilities.Id)) {
var clientImplementation = new ImapImplementation { Name = "MailKit", Version = "1.0" };
var serverImplementation = client.Identify (clientImplementation);
Console.WriteLine ("Server implementation details:");
foreach (var property in serverImplementation.Properties)
Console.WriteLine (" {0} = {1}", property.Key, property.Value);
}
if (client.Capabilities.HasFlag (ImapCapabilities.Acl)) {
Console.WriteLine ("The IMAP server supports Access Control Lists.");
Console.WriteLine ("The IMAP server supports the following access rights: {0}", client.Rights);
Console.WriteLine ("The Inbox has the following access controls:");
var acl = client.Inbox.GetAccessControlList ();
foreach (var ac in acl)
Console.WriteLine (" {0} = {1}", ac.Name, ac.Rights);
var myRights = client.Inbox.GetMyAccessRights ();
Console.WriteLine ("Your current rights for the Inbox folder are: {0}", myRights);
}
if (client.Capabilities.HasFlag (ImapCapabilities.Quota)) {
Console.WriteLine ("The IMAP server supports quotas.");
Console.WriteLine ("The current quota for the Inbox is:");
var quota = client.Inbox.GetQuota ();
if (quota.StorageLimit.HasValue && quota.StorageLimit.Value)
Console.WriteLine (" Limited by storage space. Using {0} out of {1} bytes.", quota.CurrentStorageSize.Value, quota.StorageLimit.Value);
if (quota.MessageLimit.HasValue && quota.MessageLimit.Value)
Console.WriteLine (" Limited by the number of messages. Using {0} out of {1} bytes.", quota.CurrentMessageCount.Value, quota.MessageLimit.Value);
Console.WriteLine ("The quota root is: {0}", quota.QuotaRoot);
}
if (client.Capabilities.HasFlag (ImapCapabilities.Thread)) {
if (client.ThreadingAlgorithms.Contains (ThreadingAlgorithm.OrderedSubject))
Console.WriteLine ("The IMAP server supports threading by subject.");
if (client.ThreadingAlgorithms.Contains (ThreadingAlgorithm.References))
Console.WriteLine ("The IMAP server supports threading by references.");
}
client.Disconnect (true);
}
}