#
#this script reads a file and counts lines which appear >= 2 times
#

#open the file in Read only mode
file = open("emails_list.txt", "r")

#read lines to list called "lines"
#first line is at lines[0], second in lines[1] etc
lines = file.readlines()

#close the "connection" to the file
file.close() 

#create a new empty dictionary called emails_dict
emails_dict = {}

#loop trough the lines list. Line = current line from the list
#IF line not found from the dictionary, then add it there with the value 0
#IF line is found from the dictionary, then +1 for its value
for line in lines:
  if line not in emails_dict:
    emails_dict[line] = 0
  emails_dict[line] += 1

#lets create a new file called output_file.csv
#open it as "w" = we are able to write in it.
output_file = open("output_file.csv", "w")

#loop trough the dictionary
# i = email address
# if the email address appears 2 or more times
# then write it into the output_file
for i in emails_dict:
  if emails_dict[i] >= 2:
    # create a new variable which will include the whole writable line
    # i.rstrip() removes the whitespaces from the i
    # then we add ; delimeter (for the cvs file)
    # emails_dict[i] returns the (int) value how many times the email address
    # was found from the emails_list. We also convert it to string
    # at the end we add newline "\n"
    # example: email_count = email@address.com;3 (newline) 
    email_count = i.rstrip() + ";" + str(emails_dict[i]) + "\n"

    #write the email_count line to the output_file
    output_file.write(email_count)
    
#close the file connection.
output_file.close()