py_edu/babynames/babynames.py

#!/usr/bin/env python3
# Copyright 2010 Google Inc.
# Licensed under the Apache License, Version 2.0
# http://www.apache.org/licenses/LICENSE-2.0

# Google's Python Class
# http://code.google.com/edu/languages/google-python-class/

import sys
import re
from typing import List

"""
A. :
1) extract_names() OK
2) Если имя уже есть в списке - выдать то,
что с меньшей цифрой
3) В main распечатывать возвращаемый список
через text = '\n'.join(mylist) + '\n'
чтобы результат:

2006
Aaliyah 91
Aaron 57
Abagail 895
Abbey 695
Abbie 650
...
4) Сделать возможность принимать несколько файлов

B. :
1) Если --summaryfile записать вывод для каждого foo.html 
в соответствующий foo.html.summary
"""

def extract_names(filename: str) -> List[str]:
  """
  ['2006', 'Aaliyah 91', Aaron 57', 'Abagail 895', ' ...]
  """
  xlist = []
  tmp_list = []
  year = ""
  with open(filename, 'r') as file:
    #print("RR_F")

    for line in file:

      if 'size="4" value="' in line:
          year = re.search(r'\d{4}', line)
          #print(year.group())
          if year.group() == None:
            continue
          else:
            xlist.append(year.group())

      elif '><td>' in line:
        #rangNameList = re.findall(r'<td>\d*</td><td>\w*</td><td>\w*', line)
        names_line = re.search(r'<td>\d*</td><td>\w*</td><td>\w*', line)

        if names_line == None:
          continue

        else:
          # Без такого блока получаю broken pipe, если много в терминал плюю
          rank = None
          rank_male_name = None
          male_name_string = None
          male_name = None
          rank_fem_name = None
          fem_name_string = None
          fem_name_search = None
          fem_name = None

          #print(type(names_line.group()))

          rank = re.search(r'[0-9]{1,}', names_line.group()).group()
          #print(rank)

          male_name_string = re.search(re.escape(">") + r'[A-z]+' + re.escape("<"), names_line.group()).group()
          male_name = re.search(r'[A-z]+', male_name_string).group()

          #print("M name: ", male_name)
          #print(type(names_line.group()[::-1]))

          fem_name_string = re.search(re.escape("<") + r'[A-z]+' + re.escape(">"), names_line.group()[::-1]).group()
          fem_name = re.search(r'[A-z]+', fem_name_string).group()
          #print("F name: ", fem_name[::-1])

          rank_male_name = male_name + " " + rank
          rank_fem_name = fem_name[::-1] + " " + rank
          #print("F rank name: ", rank_fem_name)

          for namesPlusRank in tmp_list:
            fem_name_search = fem_name[::-1]

            if re.match(re.escape(male_name) + r' [0-9]+', namesPlusRank):
              #print("detected mal: ", male_name)

              if int(rank) <= int(re.search(r'[0-9]+', namesPlusRank).group()):
                tmp_list.remove(namesPlusRank)

              else:
                rank_male_name = namesPlusRank
                tmp_list.remove(namesPlusRank)

            elif re.match(re.escape(fem_name_search) + r' [0-9]+', namesPlusRank):
              #print("detected fem: ", fem_name_search)

              if int(rank) <= int(re.search(r'[0-9]+', namesPlusRank).group()):
                tmp_list.remove(namesPlusRank)

              else:
                rank_fem_name = namesPlusRank
                tmp_list.remove(namesPlusRank)

          #print("append block: ", rank_male_name)
          #tmp_list.remove(rank_male_name)
          tmp_list.append(rank_male_name)
          #male_name = None
          #tmp_list.remove(rank_fem_name)
          tmp_list.append(rank_fem_name)
          #fem_name = None
        #tmp_list.append(rangNameList[3]+" "+rangNameList[0])
        #str(list(filter(re.compile('\w{2,}').match, rangNameList))[0])+" "+
    #print(tmp_list)

    tmp_list.sort()
    #print(tmp_list)

    xlist.extend(tmp_list)
    #print(xlist)

    return xlist

def main():
  # This command-line parsing code is provided.
  # Make a list of command line arguments, omitting the [0] element
  # which is the script itself.
  args = sys.argv[1:]

  if not args:
    print('usage: [--summaryfile] file [file ...]')
    sys.exit(1)
  # Notice the summary flag and remove it from args if it is present.

  summary = False

  if args[0] == '--summaryfile':
    summary = True
    del args[0]
  #print(len(args))

  for i in args:

    if summary:
      print("summary")

    else:
      #extract_names(i)
      #print(extract_names(i))
      print('\n'.join(extract_names(i)) + '\n')
  # +++your code here+++
  # For each filename, get the names, then either print the text output
  # or write it to a summary file  

if __name__ == '__main__':
  main()