import urllib2
import re
import sys
import time;
from time import sleep

def getWebContent(url) :
    response = urllib2.urlopen(url)
    html = response.read()
    response.close()
    return html

r = re.compile(r"http[s]?://[a-zA-Z\.-]+")
r1 = re.compile(r"<a[^>]*href=[\"']([^\"']*)[\"']")

def extractAllLinks(html) :
    links1= map(lambda x: domain+x, filter(lambda x:  x[0]=='/', r1.findall(html)))
    links2= r.findall(html)
    return links1 + links2

start = sys.argv[1]
domain = sys.argv[2]

q = [start]

d = {}


while (len(q) > 0):
  cur_page = q.pop(0)

  if (not cur_page.startswith(domain)):
    continue
    
  if (cur_page in d):
    pass
  else:
    d[cur_page] = 1;
    print cur_page
    try:
      body = getWebContent(cur_page);
      links = extractAllLinks(body)
      q.extend(links)
    except urllib2.HTTPError:
      print "Can't find ", cur_page