/// <summary>
/// Constructor that creates a directory
/// </summary>
public static TXTCreating GetTXT(string URL)
{
if (creator == null)
{
creator = new TXTCreating();
}
if (creator.VerifyURL(URL))
{
TempDirectorySplit = URL.Split(':');
directoryName = TempDirectorySplit[1].Substring(2, TempDirectorySplit[1].Length - 2);
Directory.CreateDirectory(directoryName);
}
//Reset values
codeHTML = "";
nbrTooLong = 0;
return(creator);
}
/// <summary>
/// Method which returns a list of words for every links on the website
/// </summary>
/// <param name="Creator">TXTCreating object which will take the HTML and returns it to the HTMLTxtAnalyser</param>
/// <param name="URL">URL of the HTML to analyse</param>
/// <returns>List of words</returns>
public List <string> WordSearching(TXTCreating Creator, string URL)
{
//Variables
char chrOne = ' ';
char chrTwo = ' ';
char chrThree = ' ';
char chrFour = ' ';
char chrFive = ' ';
char chrSix = ' ';
char chrSeven = ' ';
bool takeChr = false;
bool scripted = false;
string word = "";
//Objects
List <string> lstWords = new List <string>();
//Taking HTML and cleaning it
string HTML = Creator.TakeHTML(URL);
if (HTML != null)
{
HTML = Regex.Replace(HTML, @"\n", " ");
HTML = Regex.Replace(HTML, @"\r", " ");
HTML = Regex.Replace(HTML, @"\t", " ");
//Loop to search for words
for (int x = 0; x < HTML.Length; ++x)
{
char currentChr = Convert.ToChar(HTML.Substring(x, 1));
chrOne = chrTwo;
chrTwo = chrThree;
chrThree = chrFour;
chrFour = chrFive;
chrFive = chrSix;
chrSix = chrSeven;
chrSeven = currentChr;
if (chrTwo == 's' && chrThree == 'c' && chrFour == 'r' && chrFive == 'i' && chrSix == 'p' && chrSeven == 't')
{
scripted = IsScript(chrOne);
}
if (currentChr == '>')
{
takeChr = true;
}
else if (currentChr == '<' && takeChr)
{
takeChr = false;
}
else if (takeChr && !scripted)
{
if (currentChr == ' ')
{
if (word != "")
{
word = word.ToLower();
lstWords.Add(word);
word = "";
}
}
else
{
word += currentChr;
}
}
}
}
else
{
lstWords = null;
}
return(lstWords);
}
/// <summary>
/// Method to search links
/// </summary>
/// <param name="Creator">TXTCreating object which will take the HTML and returns it to the HTMLLinkFinder</param>
/// <param name="URL">URL of the HTML to analyse</param>
/// <returns>Return a list of links</returns>
public List <string> Finder(TXTCreating Creator, string URL)
{
//Variables
char chrOne = ' ';
char chrTwo = ' ';
char chrThree = ' ';
char chrFour = ' ';
string Link = "";
bool takeCar = false;
bool isLink = false;
int chrRemaining = 0;
//Objects
List <string> lstLinks = new List <string>();
//Taking HTML
string HTML = Creator.TakeHTML(URL);
if (HTML != null)
{
//Loop to search for links
for (int x = 0; x < HTML.Length; ++x)
{
chrOne = chrTwo;
chrTwo = chrThree;
chrThree = chrFour;
chrFour = Convert.ToChar(HTML.Substring(x, 1));
if (chrFour == 'a' && chrThree == '<')
{
isLink = true;
}
else if (chrOne == '<' && chrTwo == '/' && chrThree == 'a' && chrFour == '>')
{
isLink = false;
}
if (isLink)
{
if (chrOne == 'h' && chrTwo == 'r' && chrThree == 'e' && chrFour == 'f')
{
takeCar = true;
chrRemaining = 2;
}
else if (chrFour == '"' && chrRemaining == 0 && takeCar)
{
takeCar = false;
lstLinks.Add(Link);
Link = "";
}
else if (takeCar)
{
if (chrRemaining != 0)
{
chrRemaining--;
}
else
{
Link += chrFour;
}
}
}
}
}
else
{
lstLinks = null;
}
return(lstLinks);
}
/// <summary>
/// Method who will start the analyse and control other methods
/// </summary>
/// <param name="URL">URL of the website to analyse</param>
public void Start(string URL)
{
//Variables
int Analysed = 0;
int Created = 0;
//Objects
List <List <string> > TempWordLst = new List <List <string> >();
List <string> lstLinks = new List <string>();
List <string> lstLinksName = new List <string>();
List <string> TempLst = new List <string>();
TXTCreating Creator = TXTCreating.GetTXT(URL);
HTMLTxtAnalyser Analyser = HTMLTxtAnalyser.GetHTMLTxt();
//Verify the link of the website
if (Creator.VerifyURL(URL))
{
//Search of links on the website
HTMLLinkFinder Finder = HTMLLinkFinder.GetHTMLLink();
lstLinks = Finder.Finder(Creator, URL);
foreach (string link in lstLinks)
{
if (link.Substring(0, 1) == "/")
{
TempLst = Finder.Finder(Creator, URL.Substring(0, URL.Length - 1) + link);
if (TempLst != null)
{
lstLinks = lstLinks.Union(TempLst).ToList();
}
}
else if (link.Length > 5)
{
if (link.Substring(link.Length - 5, 5) == ".html")
{
TempLst = Finder.Finder(Creator, URL + link);
if (TempLst != null)
{
lstLinks = lstLinks.Union(TempLst).ToList();
}
}
}
else if (link.Contains(URL))
{
TempLst = Finder.Finder(Creator, link);
if (TempLst != null)
{
lstLinks = lstLinks.Union(TempLst).ToList();
}
}
}
if (!lstLinks.Contains(URL))
{
lstLinks.Add(URL);
}
//Search of words
foreach (string link in lstLinks)
{
if (link.Substring(0, 1) == "/")
{
TempLst = Analyser.WordSearching(Creator, URL + link.Substring(1, link.Length - 1));
if (TempLst != null)
{
TempWordLst.Add(TempLst);
lstLinksName.Add(link.Substring(1, link.Length - 1));
}
}
else if (link.Length > 5)
{
if (link.Substring(link.Length - 5, 5) == ".html")
{
TempLst = Finder.Finder(Creator, URL + link);
if (TempLst != null)
{
TempWordLst.Add(TempLst);
lstLinksName.Add(link);
}
}
}
else if (link.Contains(URL))
{
TempLst = Analyser.WordSearching(Creator, link);
if (TempLst != null)
{
TempWordLst.Add(TempLst);
lstLinksName.Add("Base");
}
}
Analysed++;
Console.SetCursorPosition(0, 5);
Console.WriteLine("Analysed : " + Analysed * 100 / lstLinks.Count + "%");
}
//Text creation
for (int x = 0; x < lstLinksName.Count(); ++x)
{
Creator.CreateTXT(lstLinksName[x], TempWordLst[x]);
Created++;
Console.SetCursorPosition(0, 6);
Console.WriteLine("Created : " + Created * 100 / lstLinksName.Count + "%");
}
Console.WriteLine("\n\nWebsite analysed!!!");
}
}
