private static void Main(string[] args)
{
if (args.Length < 3)
{
Console.WriteLine("usage: MarkdownParser input_file html_output_file text_output_file");
Environment.Exit(-1);
}
if (!File.Exists(args[0]))
{
Console.WriteLine("{0} does not exist.", args[0]);
Environment.Exit(-1);
}
//convert markdown to html
var markdownSource = File.ReadAllText(args[0]);
var htmlSource = new Markdown().Transform(markdownSource);
File.WriteAllText(args[1], htmlSource);
//convert html to txt
var html2txt = new HtmlToText();
var text = html2txt.Convert(args[1]);
//use OS newlines
text = Regex.Replace(text, "(?<!\r)\n", Environment.NewLine);
Console.WriteLine(text);
File.WriteAllText(args[2], text);
}
static void Test()
{
HtmlToText htt = new HtmlToText();
string s = htt.Convert(@"..\..\mshome.htm");
StreamWriter sw = new StreamWriter("mshome.txt");
sw.Write(s);
sw.Flush();
sw.Close();
}
public string[] Top10ContentWords(string url)
{
var proxy = new Web2StringProxy.ServiceClient();
var html = proxy.GetWebContent(url);
proxy.Close();
var htmlToText = new HtmlToText();
var content = htmlToText.ConvertHtml(html);
var contentWords = Regex.Split(content, @"[\W\d]+").Where(c => !String.IsNullOrWhiteSpace(c) && !_stopWords.Contains(c));
var topTenContentWords = (from w in contentWords
group w by w
into g
let count = g.Count()
orderby count descending
select g.Key).Take(10);
return topTenContentWords.ToArray();
}
