public void ProcessNewPage(Website inputwebsite)
{
try
{
string URL = inputwebsite.currentPath;
HtmlWeb htmlweb = new HtmlWeb();
HtmlDocument htmlDocument = htmlweb.Load(URL);
List <string> urls = new List <string>();
try
{
urls = htmlDocument.DocumentNode.SelectNodes("//a[@href]").Select(i => i.GetAttributeValue("href", null)).ToList();
}
catch (Exception e)
{
//Console.WriteLine(e.Message);
}
List <string> banned = new List <string>();
inputwebsite.HTMLContent = htmlDocument.Text;
//websites.Find(x => x.currentPath == URL).HTMLContent = htmlDocument.Text;
foreach (string item in urls)
{
if (item.Contains("facebook.com") || item.ToLower().Contains(".pdf"))
{
banned.Add(item);
}
}
foreach (string item in banned)
{
urls.Remove(item);
}
string url1;
string httpstring = "http";
foreach (string url in urls)
{
try
{
//Console.WriteLine(url.IndexOf('h').ToString() + url.IndexOf('t').ToString() + url.IndexOf('p').ToString());
if (!url.Contains("www"))
{
if (url.IndexOf('h') == 0 && url.IndexOf('t') == 1 && url.IndexOf('p') == 3)
{
url1 = url;
}
else if (url[0] == '/' && url[1] == '/')
{
url1 = httpstring + url;
}
else
{
url1 = URL.Remove(URL.Length - 1, 1) + url;
}
}
else
{
url1 = url;
}
Uri uri = new Uri(url1);
string domain = uri.Host;
Domain dom = domains.Find(x => x.URL == domain);
if (dom == null)
{
dom = new Domain(domain, RobotTXTHandler.FindRestrictions(domain));
domains.Add(dom);
}
Website tempwebsite = new Website(dom, url1);
if (!dom.restriction.disallow.Contains(tempwebsite.currentPath.Remove(0, tempwebsite.DomainURL.URL.Length)))
{
if (!queue.Contains(tempwebsite) && !websites.Contains(tempwebsite))
{
tempwebsite.LinkedFrom.Add(inputwebsite);
queue.Enqueue(tempwebsite);
}
else if (websites.Contains(tempwebsite))
{
websites.Find(x => x == tempwebsite).LinkedFrom.Add(inputwebsite);
}
else if (queue.Contains(tempwebsite))
{
queue.ElementAt(queue.ToArray().ToList().IndexOf(tempwebsite)).LinkedFrom.Add(inputwebsite);
}
}
}
catch (Exception e)
{
//Console.WriteLine(e.Message);
}
}
}
catch (Exception e)
{
//Console.WriteLine(e.Message);
}
}
public double Jaccard(Website input1, Website input2)
{
string text1input = input1.HTMLContent;
string text2input = input2.HTMLContent;
List <int> text1 = new List <int>();
List <int> text2 = new List <int>();
List <int> shift1 = new List <int>(84);
List <int> shift2 = new List <int>(84);
if (input1.HTMLContent == "" || input1.HTMLContent == null)
{
if (input2.HTMLContent == "" || input2.HTMLContent == null)
{
return(100);
}
else
{
return(0);
}
}
if (input2.HTMLContent == "" || input2.HTMLContent == null || input1.HTMLContent.Split(' ').Length < 4 || input2.HTMLContent.Split(' ').Length < 6)
{
return(0);
}
if (knownwebsitees.Contains(input1))
{
shift1 = input1.Hashnumber;
}
else
{
text1 = FindHashNumber(text1input);
for (int i = 0; i < randomList.Count; i++)
{
shift1.Add(BigShiftHash(text1, randomList[i]).Min());
}
input1.Hashnumber = shift1;
knownwebsitees.Add(input1);
}
if (knownwebsitees.Contains(input2) && input2.Hashnumber != null)
{
shift2 = input2.Hashnumber;
}
else
{
text2 = FindHashNumber(text2input);
for (int i = 0; i < randomList.Count; i++)
{
shift2.Add(BigShiftHash(text2, randomList[i]).Min());
}
input2.Hashnumber = shift2;
knownwebsitees.Add(input2);
}
double identicalcounter = 0;
for (int i = 0; i < shift1.Count - 1; i++)
{
if (shift1[i] == shift2[i])
{
identicalcounter++;
}
}
/*
* foreach (Int32 item in randomList)
* {
* text1Hashes = BigShiftHash(text1, item).Min();
* text2Hashes = BigShiftHash(text2, item).Min();
* if (text1Hashes == text2Hashes)
* {
* identicalcounter++;
* }
* }*/
return((identicalcounter / 84) * 100);
}
