#! usr/bin/python
#Filename: rsquery2.py

import re, urllib, time
rsnumbers = []
f = open('ancestral0624', 'a')
urltest = re.compile
prefix = "http://www.ncbi.nlm.nih.gov/projects/SNP/snp_ref.cgi?rs="
rsn = open("snplist")

for line in rsn:
    rsnumbers.append(line) 

for line in rsnumbers:	
	try:
		entrez = urllib.urlopen(prefix + line).read()
   		time.sleep(.5)
  		text = entrez.split("Ancestral Allele")[-1].split("Clinical Association")[0]
  		output = text.split('f1f1f1">')[-1].split('</td></TR>')[0]
   		final = output, line
  		finalstr = str(final)
  		f.write("%s\n" % finalstr)
	except IOError:
    		time.sleep(5)
f.close()