<?
/*
########################################################################                                        
Copyright 2007, Michael Schrenk                                                                                 
   This software is designed for use with the book,                                                             
   "Webbots, Spiders, and Screen Scarpers", Michael Schrenk, 2007 No Starch Press, San Francisco CA             
                                                                                                                
W3CŽ SOFTWARE NOTICE AND LICENSE                                                                                
                                                                                                                
This work (and included software, documentation such as READMEs, or other                                       
related items) is being provided by the copyright holders under the following license.                          
 By obtaining, using and/or copying this work, you (the licensee) agree that you have read,                     
 understood, and will comply with the following terms and conditions.                                           
                                                                                                                
Permission to copy, modify, and distribute this software and its documentation, with or                         
without modification, for any purpose and without fee or royalty is hereby granted, provided                    
that you include the following on ALL copies of the software and documentation or portions thereof,             
including modifications:                                                                                        
   1. The full text of this NOTICE in a location viewable to users of the redistributed                         
      or derivative work.                                                                                       
   2. Any pre-existing intellectual property disclaimers, notices, or terms and conditions.                     
      If none exist, the W3C Software Short Notice should be included (hypertext is preferred,                  
      text is permitted) within the body of any redistributed or derivative code.                               
   3. Notice of any changes or modifications to the files, including the date changes were made.                
      (We recommend you provide URIs to the location from which the code is derived.)                           
                                                                                                                
THIS SOFTWARE AND DOCUMENTATION IS PROVIDED "AS IS," AND COPYRIGHT HOLDERS MAKE NO REPRESENTATIONS OR           
WARRANTIES, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO, WARRANTIES OF MERCHANTABILITY OR FITNESS          
FOR ANY PARTICULAR PURPOSE OR THAT THE USE OF THE SOFTWARE OR DOCUMENTATION WILL NOT INFRINGE ANY THIRD         
PARTY PATENTS, COPYRIGHTS, TRADEMARKS OR OTHER RIGHTS.                                                          
                                                                                                                
COPYRIGHT HOLDERS WILL NOT BE LIABLE FOR ANY DIRECT, INDIRECT, SPECIAL OR CONSEQUENTIAL DAMAGES ARISING OUT     
OF ANY USE OF THE SOFTWARE OR DOCUMENTATION.                                                                    
                                                                                                                
The name and trademarks of copyright holders may NOT be used in advertising or publicity pertaining to the      
software without specific, written prior permission. Title to copyright in this software and any associated     
documentation will at all times remain with copyright holders.                                                  
########################################################################                                        
*/

/***********************************************************************
harvest_links($url)                                                     
-------------------------------------------------------------			
DESCRIZIONE:															
		Raccoglie tutti i link da una pagina web
                                                                        
INPUT:																    
		$url                                                            
            Indirizzo URL completo della pagina target
OUTPUT:																
		Ritorna un array di link
***********************************************************************/
function harvest_links($url)
    {
    // Inizializzazione
    global $DELAY;
    $link_array = array();
    
    // Calcola la page base di $url
    $page_base = get_base_page_address($url);
    
    // Scarica la pagina web
    sleep($DELAY);          
    $downloaded_page = http_get($url, "");
    $anchor_tags = parse_array($downloaded_page['FILE'], "<a", "</a>", EXCL);
    // Mette in un array gli attributi di tutti i tag
    for($xx=0; $xx<count($anchor_tags); $xx++)
        {
        $href = get_attribute($anchor_tags[$xx], "href");
        $resolved_addres = resolve_address($href, $page_base);
        $link_array[] = $resolved_addres;
        echo "Raccolta da: ".$resolved_addres." \n";
        }
    return $link_array;
    }

/***********************************************************************
archive_links($spider_array, $penetration_level, $temp_link_array)      
-------------------------------------------------------------			
DESCRIZIONE:															
		Archivia i link grezzi aggiungendoli ad un array
                                                                        
INPUT:																    
        $spider_array                                                   
            L'array di archivio iniziale
                                                                        
        $penetration_level                                              
            Livello di penetrazione in cui e' stato eseguito lo spider
                                                                        
        $temp_link_array                                                
            Array temporaneo di link
OUTPUT:																
		Ritorna l'array di archivio aggiornato
***********************************************************************/
function archive_links($spider_array, $penetration_level, $temp_link_array)
    {
    for($xx=0; $xx<count($temp_link_array); $xx++)
        {
        # Don't add exlcuded links to $spider_array
        if(!excluded_link($spider_array, $temp_link_array[$xx]))
            {
            $spider_array[$penetration_level][] = $temp_link_array[$xx];
            }
        }
    return $spider_array;
    }

/***********************************************************************
get_domain($url)                                                        
-------------------------------------------------------------			
DESCRIZIONE:															
        Calcola il dominio di un indirizzo web
INPUT:																    
        $url                                                            
            L'indirizzo web
                                                                        
RITURNA:																
		Ritorna il dominio per l'URL di input
***********************************************************************/
function get_domain($url)
    {
    // Rimuove il protocollo da $url
    $url = str_replace("http://", "", $url);
    $url = str_replace("https://", "", $url);
    
    // Rimuove i riferimenti alla pagina e alla directory
    if(stristr($url, "/"))
        $url = substr($url, 0, strpos($url, "/"));
    
    return $url;
    }

/***********************************************************************
excluded_link($spider_array, $link)                                     
-------------------------------------------------------------			
DESCRIZIONE:															
        Controlla se un link deve essere incluso nell'array di archivio
INPUT:																    
        $spider_array                                                   
            L'array di archivio dello spider
                                                                        
        $link                                                           
            Il link da controllare
OUTPUT:																
		Ritorna TRUE o FALSE, a secondo del fatto che il link debba essere escluso
***********************************************************************/
function excluded_link($spider_array, $link)
    {
    // Inizializzazione
    global $SEED_URL, $exclusion_array, $ALLOW_OFFISTE;
    $exclude = false;
    
    // Esclude i link che sono comandi JavaScript
    if(stristr($link, "javascript"))
        {
        echo "Ignorata funzione JavaScript: $link\n";
        $exclude=true;
        }
    
    // Esclude i link ridondanti
    for($xx=0; $xx<count($spider_array); $xx++)
        {
        $saved_link="";
        while(isset($saved_link))
            {
            $saved_link=array_pop($spider_array[$xx]);
            if($link == array_pop($spider_array[$xx]))
                {
                echo "Ignorato link ridondante: $link\n";
                $exclude=true;
                break;
                }
            }
        }
    
    // Esclude i link compresi in $exclusion_array
    for($xx=0; $xx<count($exclusion_array); $xx++)
        {
        if(stristr($link, $exclusion_array[$xx]))
            {
            echo "Ignorato link escluso: $link\n";
            $exclude=true;
            }
        }
        
    // Esclude i link su siti diversi
    if($ALLOW_OFFISTE==false)
        {
        if(get_domain($link)!=get_domain($SEED_URL))
            {
            echo "Ignorato link su sito diverso: $link\n";
            $exclude=true;
            }
        }

    return $exclude;
    }
?>