#!/usr/bin/python

import urllib
import urlparse
import sys
import re

RECURSION_LEVEL = 3

def getLinks ( start_page, page_data ) :
    url_list = []
    anchor_href_regex = '<\s*a\s*href\s*=\s*[\x27\x22]?([a-zA-Z0-9:/\\\\._-]*)[\x27\x22]?\s*'
    urls = re.findall(anchor_href_regex,page_data)
    for url in urls :
        url_list.append(urlparse.urljoin( start_page, url ))
    return url_list
    
def getPage ( url ) :
    page_data = urllib.urlopen(url).read()
    return page_data
    

    
if __name__ == '__main__' :
    end_results = []
    recursion_count = 0
    try: page_array = [sys.argv[1]]
    except IndexError: 
        print 'Please provide a valid url.'
        sys.exit()
    end_results.append(sys.argv[1])
    while recursion_count < RECURSION_LEVEL:
        results = []
        for current_page in page_array:
            page_data = getPage( current_page )
            link_list = getLinks(current_page, page_data)
            for item in link_list:
                if item.find( current_page ) != -1:
                    results.append( item )
            results = list(set(results))
        page_array = results
        end_results += results
        end_results = list(set(end_results))
        recursion_count += 1
    for item in end_results:
        print item