regex

gistfile1.py

def find_year (filename):
	file1 = open (filename, 'rU')
		
	match = re.findall (r'>Popularity in ([\d]+)<', file1.read())
		
	file1.close()
	return match

	
def find_name_and_rank (filename):
	temp_tuple_name_and_rank = {}
	file2 = open (filename, 'rU')
	
	temp_tuple_name_and_rank = re.findall (r'<tr align="right"><td>([\d+])</td><td>([\w]+)</td><td>([\w]+)</td>', file2.read())

	file2.close
	return temp_tuple_name_and_rank


	
def convert_tuple_to_unisex_list (tuple_name_and_rank):
	dict_men = {}
	dict_women = {}
	
	# Convert tuple into dictionary
	for item_tuple in tuple_name_and_rank:
		dict_men[item_tuple[1]] = item_tuple[0]
	
	for item_tuple in tuple_name_and_rank:
		dict_women[item_tuple[2]] = item_tuple[0]
	
	#convert dictionary into list
	list_men = list(dict_men.items())
	list_women = list (dict_women.items())
	
	#sort both lists into one men and women sorted list
	unisex_list = list_men
	unisex_list.extend (list_women)
	unisex_list.sort()
	
	return (unisex_list)
	

	
def extract_names(filename):
  """
	Given a file name for baby.html, returns a list starting with the year string
	followed by the name-rank strings in alphabetical order.
	['2006', 'Aaliyah 91', Aaron 57', 'Abagail 895', ' ...]
  """
  
  tuple_name_and_rank = {}
 
  
  # Looking for name and its rank and insert into a tuple
  tuple_name_and_rank = find_name_and_rank (filename)
    
  # Convert tuple into sorted list 
  list_sorted = convert_tuple_to_unisex_list (tuple_name_and_rank)
  
  return list_sorted
  


def main():
 	args = sys.argv[1:]

	if not args:
		print 'usage: [--summaryfile] file [file ...]'
		sys.exit(1)

	summary = False
	if args[0] == '--summaryfile':
		summary = True
		del args[0]
		
  # For each filename, get the names, then either print the text output (False)
  # or write it to a summary file (True)
  
	if summary == False:
		the_year_is = find_year (args[0])
		print '\n', the_year_is,
  		list_sorted = extract_names(args[0])
		print list_sorted	
	else:
		list_sorted = extract_names(args[0])
		file_output = open ('result.txt', 'a')
		print >> file_output, find_year(args[0])
		print >> file_output,list_sorted
		file_output.close
	
	
if __name__ == '__main__':
  main()