'''
Created on Sep 5, 2012

@author: ola
'''
import urllib

anchor = '<a href="'
anchor_len = len(anchor)

def get_links(url):
    #print "running on", filename
    stream = urllib.urlopen(url)
    st = stream.read()
    start = 0
    while True:
        search_index = st.find('<a href="',start)
        if search_index == -1:
            break
        end = st.find('"',search_index+anchor_len)
        if end == -1: 
            break
        link = st[search_index+anchor_len:end]
        if link.startswith("http://"):
            print link
        start = search_index+anchor_len
  
    
if __name__ == "__main__":
    print get_links("http://stanford.edu")