# -*- coding: utf-8 -*- import re, urllib, time def kn(book): url='' while not url: try: kn1 = urllib.urlopen('http://flibusta.net/' + book) url = kn1.geturl() time.sleep(1) print "get %s" % book except: print "Can't get %s" % book return url if __name__ == '__main__': conf = open('config.txt', 'r') list_url = conf.readlines() conf.close() res = open('urls.txt','w') for url in list_url: print "Getting URL's from %s" % url.strip() r = urllib.urlopen(url).read() books = re.findall('', r) books += re.findall('', r) books = map(kn, books) res.write('\n'.join(books)+'\n') res.close() raw_input('Press any key...')