using System;
using System.Collections.Generic;
using System.Linq;
using System.Text;
using System.Xml;
using System.IO;
using System.Net;
using System.Web;
using System.Diagnostics;
using System.Threading;

namespace WordPressTools.ConsoleTest {
class Program {
static void Main(string[] args) {
CollectedDocumentInfo docInfo = new CollectedDocumentInfo();
docInfo.Posts = new List();
PostInfo currentPost = null;
using (XmlTextReader loader = new XmlTextReader(File.Open(@”path-to-wordpress-export.xml”, FileMode.Open))) {
if (loader.ReadToDescendant(“channel”)) {
while (loader.Read()) {

if (!loader.IsStartElement()) {
continue;
}

if (loader.Name == “title” && loader.Depth == 2) {
docInfo.Title = loader.ReadString();
}

if (loader.Name == “description” && loader.Depth == 2) {
docInfo.SubTitle = loader.ReadString();
}

if (loader.Name == “wp:author_display_name” && loader.Depth == 3) {
docInfo.Author = loader.ReadString();
}

if (loader.Name == “item” && loader.Depth == 2) {
if (currentPost != null && String.IsNullOrWhiteSpace(currentPost.Content)) {
docInfo.Posts.Remove(currentPost);
}
currentPost = new PostInfo();
docInfo.Posts.Add(currentPost);
}

if (loader.Name == “title” && loader.Depth == 3) {
currentPost.Title = loader.ReadString();
}

if (loader.Name == “content:encoded” && loader.Depth == 3) {
currentPost.Content = loader.ReadString();
}

if (loader.Name == “wp:post_date” && loader.Depth == 3) {
currentPost.Date = DateTime.Parse(loader.ReadString());
}

if (loader.Name == “wp:status” && loader.Depth == 3) {
string status = loader.ReadString();
if (status != “publish”) {
currentPost.Content = null;
}
}
}
}
}

Console.WriteLine(String.Empty);
using (StreamWriter sw = new StreamWriter(@”c:\fftex\ff.tex”, false)) {
sw.WriteLine(@”\documentclass[11pt]{article}
\usepackage{graphicx}
\usepackage{hyperref}
\usepackage[normalem]{ulem}
% Default margins are too wide all the way around. I reset them here
\setlength{\topmargin}{-.5in}
\setlength{\textheight}{9in}
\setlength{\oddsidemargin}{.125in}
\setlength{\textwidth}{6.25in}
\begin{document}
\title{God’s Faithfulness Through Infertility}
\author{Part 1 – (Some name for Part 1)\\Elaine Sheldon}
\maketitle
“”‘For I know the plans I have for you,’ declares the LORD, ‘plans to prosper you and not to harm you, plans to give you hope and a future.”" Jeremiah 29:11

“);
foreach (PostInfo post in docInfo.Posts) {
Console.WriteLine(post.Title + ” – ” + post.Date.ToShortDateString());

// ok, I need to go through this post and process the content…

post.Title = System.Web.HttpUtility.HtmlDecode(post.Title).Replace(“&”, “\\&”).Replace(“#”, “\\#”);
string contentHtml = post.Content;

if (File.Exists(panDocInputPath)) {
File.Delete(panDocInputPath);
}

if (File.Exists(panDocOutputPath)) {
File.Delete(panDocOutputPath);
}

File.WriteAllText(panDocInputPath, contentHtml);

ProcessStartInfo psiPanDoc = new ProcessStartInfo(panDocPath, panDocInputPath + ” -f html -t latex -o ” + panDocOutputPath);
psiPanDoc.WindowStyle = ProcessWindowStyle.Hidden;

Process pPanDoc = Process.Start(psiPanDoc);

while (pPanDoc.HasExited) {
Thread.Sleep(50);
}
Thread.Sleep(100);
#region remove those image links and download html images to local folder
string searchString = @”\includegraphics{“;
using (StreamReader texIn = new StreamReader(panDocOutputPath)) {
using (StreamWriter texOut = new StreamWriter(fixedOutputPath)) {
int line = 0;
while (texIn.EndOfStream == false) {
string myLine = texIn.ReadLine();

string[] linesDerived = myLine.Split(new string[] { “\\\\” }, StringSplitOptions.None);
foreach (string lineFound in linesDerived) {
myLine = lineFound;

line++;

if (myLine.StartsWith(“\\href{“) && myLine.EndsWith(“}}”)) {
myLine = myLine.Substring(myLine.IndexOf(‘}’) + 2);
myLine = myLine.Substring(0, myLine.Length – 1);
}

int indexOfGraphics = myLine.IndexOf(searchString);
if (indexOfGraphics > -1) {
int indexToStart = indexOfGraphics + searchString.Length;

string webFile = myLine.Substring(indexToStart);
webFile = webFile.Substring(0, webFile.IndexOf(‘}’));
string localFile = “./” + webFile.Substring(webFile.LastIndexOf(‘/’) + 1).Replace(“?imgmax=800″, “”).Replace(“%”,”");

string downloadFile = @”c:\fftex\” + localFile.Substring(2);
try {
if (!File.Exists(downloadFile)) {
WebClient downloader = new WebClient();
downloader.DownloadFile(webFile, downloadFile);
}
}
catch (Exception ex) {
continue;
}
myLine = myLine.Replace(webFile, localFile);
}
texOut.WriteLine(myLine);
}
}
}
}
#endregion remove those image links

string contentLatex = File.ReadAllText(fixedOutputPath);

sw.WriteLine(String.Format(@”\section{{{0} – {1}}}

{2}”, post.Title, post.Date.ToShortDateString(), contentLatex));
}
sw.Write(@”\end{document}”);
}

Console.WriteLine(String.Empty);
Console.WriteLine(“Press enter to exit…”);

Console.ReadLine();
}
static string panDocInputPath = @”c:\pan-in.txt”;
static string panDocOutputPath = @”c:\pan-out.txt”;
static string fixedOutputPath = @”c:\pan-out-fixed.txt”;
static string panDocPath = @”c:\program files (x86)\pandoc\bin\pandoc.exe”;
}

class CollectedDocumentInfo {
public string Title { get; set; }
public string SubTitle { get; set; }
public string Author { get; set; }
public List Posts { get; set; }
}

class PostInfo {
public string Title { get; set; }
public DateTime Date { get; set; }
public string Content { get; set; }
}
}

Thanks for this example with PdfSharp !

So, this can be used to add a bunch of images at the end of a PDF ?
Not sure what you mean by a “Letterhead” generator.
Isn’t a letterhead something at the beginning of each page of the document ?

Any idea of putting some image description text ( above or below each image ) ?
Regards, Rich