1 def get_urls_list(): 2 result_list = [] 3 url_list_path = os.path.join(“http://localhost/phpmanual/”) 4 url_object = urllib.urlopen(url_list_path) 5 lines = url_object.readlines() 6 reo = re.compile(r””” 7 \” 8 (?P 9 (\S*?) 10 \.html) 11 “””, re.VERBOSE|re.IGNORECASE|re.DOTALL) 12 for line in lines: 13 result = reo.search(line) 14 if result: 15 url = result.group(‘url’) 16 full_url = urlparse.urljoin(url_list_path, url) 17 result_list.append(full_url) 18 return result_list