代码笔记:使用C#转移WordPress博客到为知笔记或Evernote

  • 代码
    using System; using System.Linq; using System.Net.Mail; using System.Text; using System.Text.RegularExpressions; using System.Threading.Tasks; using System.Xml.Linq; using System.Xml.XPath; namespace WordPressExport { class Program { static SmtpClient smtpClient; static MailMessage mailMessage; static IOrderedEnumerable<post> list; static bool smtpConnected; static bool triedAfterEx = false; readonly static string CONFIG_smtp_addr = System.Configuration.ConfigurationSettings.AppSettings["smtp_addr"]; readonly static string CONFIG_smtp_acct_name = System.Configuration.ConfigurationSettings.AppSettings["smtp_acct_name"]; readonly static string CONFIG_smtp_acct_pwd = System.Configuration.ConfigurationSettings.AppSettings["smtp_acct_pwd"]; readonly static string CONFIG_xml_path = System.Configuration.ConfigurationSettings.AppSettings["xml_path"]; readonly static string CONFIG_evernote_folder = System.Configuration.ConfigurationSettings.AppSettings["evernote_folder"]; readonly static string CONFIG_post_scope_start_date = System.Configuration.ConfigurationSettings.AppSettings["post_scope_start_date"]; readonly static string CONFIG_post_scope_end_date = System.Configuration.ConfigurationSettings.AppSettings["post_scope_end_date"]; readonly static string CONFIG_notebook_email = System.Configuration.ConfigurationSettings.AppSettings["notebook_email"]; readonly static string CONFIG_blog_addr = System.Configuration.ConfigurationSettings.AppSettings["blog_addr"]; static void SendMail(post post) { bool isSuccess = true; if (post == null) return; DateTime post_date; if (!DateTime.TryParse(post.post_date, out post_date)) { post_date = System.DateTime.MinValue; } string str_post_date = post_date == System.DateTime.MinValue ? "" : post_date.ToString("yyyy-MM-dd"); mailMessage.SubjectEncoding = Encoding.UTF8; mailMessage.Subject = string.Format("[{0}] {1} {2}", str_post_date, post.post_title, CONFIG_evernote_folder);//主題 mailMessage.Body = "<b>创建时间:</b>" + post.post_date + "<br/>";//內容 mailMessage.Body += "<b>原目录或tag</b>:" + post.post_tagcat + "<br/>";//內容 mailMessage.Body += string.Format("<b>原文见</b>:<a href={0}?p={1}>{0}?p={1}</a></a><br/><br/><br/>", CONFIG_blog_addr, post.ID);//內容 mailMessage.Body += post.post_content; try { mailMessage.BodyEncoding = Encoding.UTF8;//正文編碼 mailMessage.Priority = MailPriority.High;//優先級 mailMessage.IsBodyHtml = true; Regex reg = new Regex(@"\n"); mailMessage.Body = reg.Replace(mailMessage.Body, "<br/>"); Console.WriteLine(System.DateTime.Now + " sending mail... id = " + post.ID + " " + post.post_title); // 你也可以使用异步发送,不过会导致发到邮箱的时间很乱,我们还是希望导入到笔记后的笔记自然顺序(即ID)是按时间顺序的 // smtpClient.Send(mailMessage);// 發送郵件 } catch (SmtpException ex) { Console.WriteLine("failed in SMTP connection, try again..."); // System.IO.IOException: Unable to write data to the transport connection: An established connection was aborted by the // software in your host machine. // ---> System.Net.Sockets.SocketException: An established connection was aborted by the software in your host machine if (triedAfterEx) { isSuccess = false; Console.WriteLine(ex.Message); } // again, create another smtp instance for reconnecting SMTP // Parallel.Invoke(() => connectSmtp(), () => SendMail (post)); isSuccess = false; Console.WriteLine(ex.Message); triedAfterEx = true; } catch (Exception ex2) { isSuccess = false; Console.WriteLine(ex2.Message); } Console.WriteLine(System.DateTime.Now.ToString() + (isSuccess ? " completed" : " completed with error(s): log's date" + post.post_date));//下次从这个时间戳开始导入 } static void Main(string[] args) { smtpConnected = false; Console.WriteLine(System.DateTime.Now + " start..."); Parallel.Invoke(() => connectSmtp(), () => HandleWPExport()); if (list.Count() == 0) { throw new Exception("ooops.."); } int cnt = 0; while (1 == 1) { if (smtpConnected = true || cnt > 10000) break; cnt++; } Console.WriteLine(cnt); foreach (var p in list) { triedAfterEx = false; SendMail(p); } } private static void connectSmtp() { smtpClient = new SmtpClient(); smtpClient.DeliveryMethod = SmtpDeliveryMethod.Network; //指定電子郵件發送方式 smtpClient.Host = CONFIG_smtp_addr; //指定SMTP服務器 smtpClient.EnableSsl = true; smtpClient.Credentials = new System.Net.NetworkCredential(CONFIG_smtp_acct_name, CONFIG_smtp_acct_pwd); smtpClient.Timeout = 100000; mailMessage = new MailMessage(CONFIG_smtp_acct_name, CONFIG_notebook_email); } private static void HandleWPExport() { Console.WriteLine(System.DateTime.Now + " starting to read wp_posts.xml..."); XDocument xmlDoc = XDocument.Load(CONFIG_xml_path); var queryTax = (from tax in xmlDoc.XPathSelectElements(@".//table[@name='wp_term_taxonomy']") where tax.XPathSelectElement("column[@name='taxonomy']").Value.Trim("\n".ToCharArray()) == TaxonomyEnum.category.ToString() || tax.XPathSelectElement("column[@name='taxonomy']").Value.Trim("\n".ToCharArray()) == TaxonomyEnum.link_category.ToString() || tax.XPathSelectElement("column[@name='taxonomy']").Value.Trim("\n".ToCharArray()) == TaxonomyEnum.post_tag.ToString() select new { term_id = tax.XPathSelectElement("column[@name='term_id']").Value.Trim("\n".ToCharArray()), tax_id = tax.XPathSelectElement("column[@name='term_taxonomy_id']").Value.Trim("\n".ToCharArray()) }).ToList(); var queryCat = (from cat in xmlDoc.XPathSelectElements(@".//table[@name='wp_terms']") select new { term_id = cat.XPathSelectElement("column[@name='term_id']").Value.Trim("\n".ToCharArray()), name = cat.XPathSelectElement("column[@name='name']").Value.Trim("\n".ToCharArray()), }).ToList(); var queryRel = (from rel in xmlDoc.XPathSelectElements(@".//table[@name='wp_term_relationships']") select new { object_id = rel.XPathSelectElement("column[@name='object_id']").Value.Trim("\n".ToCharArray()), tax_id = rel.XPathSelectElement("column[@name='term_taxonomy_id']").Value.Trim("\n".ToCharArray()), }).ToList(); Console.WriteLine(System.DateTime.Now + " continuing ... "); var queryTagCat = (from tax in queryTax from cat in queryCat from rel in queryRel where cat.term_id == tax.term_id && tax.tax_id == rel.tax_id select new { name = cat.name, id = rel.object_id }).ToList(); var query = from p in xmlDoc.XPathSelectElements(@".//table[@name='wp_posts' ]") where p.XPathSelectElement("column[@name='post_type']").Value.Trim("\n".ToCharArray()) == "post" // there're two types - post, attachment, we don't want attachment type of posts select new post { ID = p.XPathSelectElement("column[@name='ID']").Value.Trim("\n".ToCharArray()), post_author = p.XPathSelectElement("column[@name='post_author']").Value.Trim("\n".ToCharArray()), post_date = p.XPathSelectElement("column[@name='post_date']").Value.Trim("\n".ToCharArray()), post_date_gmt = p.XPathSelectElement("column[@name='post_date_gmt']").Value.Trim("\n".ToCharArray()), post_content = p.XPathSelectElement("column[@name='post_content']").Value.Trim("\n".ToCharArray()), post_title = p.XPathSelectElement("column[@name='post_title']").Value.Trim("\n".ToCharArray()), post_excerpt = p.XPathSelectElement("column[@name='post_excerpt']").Value.Trim("\n".ToCharArray()), post_status = p.XPathSelectElement("column[@name='post_status']").Value.Trim("\n".ToCharArray()), comment_status = p.XPathSelectElement("column[@name='comment_status']").Value.Trim("\n".ToCharArray()), ping_status = p.XPathSelectElement("column[@name='ping_status']").Value.Trim("\n".ToCharArray()), post_password = p.XPathSelectElement("column[@name='post_password']").Value.Trim("\n".ToCharArray()), post_name = p.XPathSelectElement("column[@name='post_name']").Value.Trim("\n".ToCharArray()), to_ping = p.XPathSelectElement("column[@name='to_ping']").Value.Trim("\n".ToCharArray()), pinged = p.XPathSelectElement("column[@name='pinged']").Value.Trim("\n".ToCharArray()), post_modified = p.XPathSelectElement("column[@name='post_modified']").Value.Trim("\n".ToCharArray()), post_modified_gmt = p.XPathSelectElement("column[@name='post_modified_gmt']").Value.Trim("\n".ToCharArray()), post_content_filtered = p.XPathSelectElement("column[@name='post_content_filtered']").Value.Trim("\n".ToCharArray()), post_parent = p.XPathSelectElement("column[@name='post_parent']").Value.Trim("\n".ToCharArray()), guid = p.XPathSelectElement("column[@name='guid']").Value.Trim("\n".ToCharArray()), menu_order = p.XPathSelectElement("column[@name='menu_order']").Value.Trim("\n".ToCharArray()), post_type = p.XPathSelectElement("column[@name='post_type']").Value.Trim("\n".ToCharArray()), post_mime_type = p.XPathSelectElement("column[@name='post_mime_type']").Value.Trim("\n".ToCharArray()), comment_count = p.XPathSelectElement("column[@name='comment_count']").Value.Trim("\n".ToCharArray()), post_tagcat = string.Join(" ", (from t in queryTagCat where t.id == p.XPathSelectElement("column[@name='ID']").Value.Trim("\n".ToCharArray()) select t.name).ToList()) }; Console.WriteLine(System.DateTime.Now + " done with reading the xml... "); // PredicateBuilder if (!string.IsNullOrEmpty(CONFIG_post_scope_start_date)) query = query.Where(o => Convert.ToDateTime(o.post_date) >= DateTime.Parse(CONFIG_post_scope_start_date)); if (!string.IsNullOrEmpty(CONFIG_post_scope_end_date)) query = query.Where(o => Convert.ToDateTime(o.post_date) <= DateTime.Parse(CONFIG_post_scope_end_date)); list = query.ToList().OrderBy(o => o.post_date); } } }

    DTO类

    using System; using System.Collections.Generic; using System.Linq; using System.Text; using System.Xml.Serialization; namespace WordPressExport { [Serializable] public class column { public string name { get; set; } public string text { get; set; } } [Serializable] public class database { [XmlElement(ElementName = "database")] public List<table> tables { get; set; } } [Serializable] public class table { public string name { get; set; } public column column { get; set; } } [Serializable] public class post { public string ID { get; set; } public string post_author { get; set; } public string post_date { get; set; } public string post_date_gmt { get; set; } public string post_content { get; set; } public string post_title { get; set; } public string post_excerpt { get; set; } public string post_status { get; set; } public string comment_status { get; set; } public string ping_status { get; set; } public string post_password { get; set; } public string post_name { get; set; } public string to_ping { get; set; } public string pinged { get; set; } public string post_modified { get; set; } public string post_modified_gmt { get; set; } public string post_content_filtered { get; set; } public string post_parent { get; set; } public string guid { get; set; } public string menu_order { get; set; } public string post_type { get; set; } public string post_mime_type { get; set; } public string comment_count { get; set; } public string post_tagcat { get; set; } } public enum TaxonomyEnum { category, link_category, post_format, post_tag, series } }

    app.config

    <?xml version="1.0"?> <configuration> <startup><supportedRuntime version="v4.0" sku=".NETFramework,Version=v4.0"/></startup> <appSettings> <add key="smtp_addr" value="smtp.gmail.com"/> <add key="smtp_acct_name" value="@gmail.com"/> <add key="smtp_acct_pwd" value=""/> <add key="evernote_folder" value="@folder..."/> <add key="xml_path" value="xxxxx\wp_posts.xml"/> <add key="notebook_email" value="xxxx@mywiz.cn"/> <add key="post_scope_start_date" value="2013-04-11 22:25:50"/> <add key="post_scope_end_date" value=""/> <add key="blog_addr" value="http://www.xxxx.com/"/> </appSettings> </configuration>
  • 原文链接:https://www.cnblogs.com/syveen/archive/2013/05/11/3073300.html