private void load()
{
HttpWebRequest wrq;
HttpWebResponse wr;
try
{
wrq = (HttpWebRequest)WebRequest.Create(url);
wrq.UserAgent = "LOTW UNI Crawler/computer science research project";
wrq.Timeout = 5000;
wr = (HttpWebResponse)wrq.GetResponse();
}
catch (Exception)
{
source = "";
return;
}
if (wr.ContentType.IndexOf("text/html") > -1)
{
source = new StreamReader(wr.GetResponseStream()).ReadToEnd();
title = extractTitle();
TagRemover tr = new TagRemover();
source = tr.ProcessText(new StringReader(source));
}
else
{
source = "";
}
wr.Close();
}
static void Main(string[] args)
{
string source = i.Helper.PAGES_PATH;
string target = i.Helper.DOCS_PATH;
i.TagRemover tr = new i.TagRemover(source, target);
tr.RemoveTags();
i.TitleExtractor te = new i.TitleExtractor();
te.Extract(i.Helper.PAGES_PATH);
i.LinkProcessor lp = new i.LinkProcessor();
lp.Run();
i.DataHelper dh = new i.DataHelper();
dh.AddTitleUrlTags();
i.TermParser p = new i.TermParser();
p.ExtractTerms();
i.Calculator c = new i.Calculator();
c.CalculateIdfs();
c.CalculateIdfsA();
i.AnchorTextProcessor at = new IrProject.Indexing.AnchorTextProcessor();
at.AddAnchorText();
Tester t = new Tester();
t.Run();
TextConverter tc = new TextConverter();
tc.ConvertTermDocTable();
}
