1  import random
  2  import string
  3  import os
  4  from datetime import datetime, timedelta
  5  
  6  # Path to the local file for storing names
  7  local_file_path = "first-names.txt"
  8  
  9  # Function to load names from the local file
 10  def load_names(file_path):
 11      if not os.path.exists(file_path):
 12          print(f"Error: The file '{file_path}' does not exist.")
 13          print("Please download the file from the following URL and place it in the same directory as this script:")
 14          print("https://gist.githubusercontent.com/elifiner/cc90fdd387449158829515782936a9a4/raw/fea1da1a3c4ce5c8e470f679a8e1bc741281a609/first-names.txt")
 15          exit(1)
 16      with open(file_path, "r") as file:
 17          return file.read().splitlines()
 18  
 19  # Load names from the local file
 20  first_names = load_names(local_file_path)
 21  last_names = first_names  # Assuming the same file contains both first and last names
 22  
 23  # List of U.S. states for state of birth (SOB)
 24  states = [
 25      "AL", "AK", "AZ", "AR", "CA", "CO", "CT", "DE", "FL", "GA", 
 26      "HI", "ID", "IL", "IN", "IA", "KS", "KY", "LA", "ME", "MD", 
 27      "MA", "MI", "MN", "MS", "MO", "MT", "NE", "NV", "NH", "NJ", 
 28      "NM", "NY", "NC", "ND", "OH", "OK", "OR", "PA", "RI", "SC", 
 29      "SD", "TN", "TX", "UT", "VT", "VA", "WA", "WV", "WI", "WY"
 30  ]
 31  
 32  domains = [
 33      "earthlink.net", "verizon.net", "msn.com", "yahoo.com", "aol.com", 
 34      "protonmail.com", "icloud.com", "outlook.com", "zoho.com", "mail.com", 
 35      "yandex.com", "fastmail.com", "rocketmail.com", "gmx.com", "tutanota.com", 
 36      "mail.ru", "hushmail.com", "guerrillamail.com", "inbox.com", "sendinblue.com", 
 37      "lavabit.com", "lycos.com", "aol.co.uk", "myway.com", "bluebottle.com", 
 38      "unseen.is", "chime.com", "walla.com", "mindspring.com", "gawab.com", 
 39      "openmailbox.org", "rediffmail.com", "epix.net", "gmail.com", "hotmail.com", 
 40      "live.com", "yahoo.co.uk", "icloud.co.uk", "outlook.co.uk", "mailchimp.com", 
 41      "zoho.co.uk", "aol.com.au", "msn.co.uk", "seznam.cz", "t-online.de", 
 42      "orange.fr", "bellsouth.net", "comcast.net", "btinternet.com", "charter.net", 
 43      "cox.net", "shaw.ca", "telus.net", "sbcglobal.net", "att.net", "roadrunner.com",
 44      
 45      # Government Domains
 46      "usa.gov", "gov.uk", "canada.ca", "gov.au", "gov.in", "gov.sg", 
 47      "gov.za", "gov.ph", "gov.br", "gov.de", "gov.fr", "gov.it", "gov.jp",
 48      
 49      # Military Domains
 50      "army.mil", "navy.mil", "af.mil", "usmc.mil", "uscg.mil", "spaceforce.mil",
 51      
 52      # Educational Domains
 53      "harvard.edu", "stanford.edu", "mit.edu", "ox.ac.uk", "cam.ac.uk", 
 54      "berkeley.edu", "umich.edu", "columbia.edu", "yale.edu", "princeton.edu", 
 55      "ucla.edu", "nyu.edu", "utexas.edu", "uchicago.edu", "upenn.edu",
 56      "caltech.edu", "duke.edu", "northwestern.edu", "uw.edu", "gatech.edu",
 57  ]
 58  
 59  # Function to generate a random email
 60  def generate_email(first_name, last_name):
 61      domain = random.choice(domains)
 62      email_format = random.choice([f"{first_name}.{last_name}", f"{first_name}{last_name}", f"{first_name[0]}{last_name}"])
 63      email = f"{email_format}@{domain}"
 64      return email.lower()
 65  
 66  # Function to generate a random password
 67  def generate_password():
 68      chars = string.ascii_letters + string.digits + string.punctuation
 69      password_length = random.randint(8, 16)
 70      password = "".join(random.choices(chars, k=password_length))
 71      return password
 72  
 73  # Function to generate a random reasonable DOB (between 18 and 70 years ago)
 74  def generate_dob():
 75      today = datetime.today()
 76      start_date = today - timedelta(days=70 * 365)  # 70 years ago
 77      end_date = today - timedelta(days=18 * 365)    # 18 years ago
 78      random_date = start_date + (end_date - start_date) * random.random()
 79      return random_date.strftime("%Y-%m-%d")
 80  
 81  # Function to generate a random state of birth (SOB) with a 50% chance
 82  def generate_sob():
 83      if random.random() < 0.5:  # 50% chance
 84          return random.choice(states)
 85      return "N/A"  # Return "N/A" if no SOB is generated
 86  
 87  # Function to generate a random phone number
 88  def generate_phone_number():
 89      if random.random() < 0.7:  # 70% chance
 90          return f"{random.randint(200, 999)}-{random.randint(100, 999)}-{random.randint(1000, 9999)}"
 91      return "N/A"  # Return "N/A" if no phone number is generated
 92  
 93  # Function to generate a random 9-digit number with heavy obscuration
 94  def generate_9_digit_number():
 95      if random.random() < 0.5:  # 50% chance
 96          number = f"{random.randint(100000000, 999999999)}"
 97          # Replace 6 out of 9 digits with *
 98          indices_to_obscure = random.sample(range(9), 6)  # Randomly select 6 indices to obscure
 99          number_list = list(number)
100          for index in indices_to_obscure:
101              number_list[index] = "*"
102          return "".join(number_list)
103      return "N/A"  # Return "N/A" if no 9-digit number is generated
104  
105  # Function to generate a single line of fake data
106  def generate_line():
107      first_name = random.choice(first_names)
108      last_name = random.choice(last_names)
109      email = generate_email(first_name, last_name)
110      password = generate_password()
111      dob = generate_dob()
112      sob = generate_sob()
113      phone_number = generate_phone_number()
114      nine_digit_number = generate_9_digit_number()
115      return f"{first_name} {last_name} | {email} | {password} | {dob} | {sob} | {phone_number} | {nine_digit_number}\n"
116  
117  # Function to generate a file of a specified size
118  def generate_file(filename, size_bytes):
119      with open(filename, "w") as file:
120          written_size = 0
121          while written_size < size_bytes:
122              line = generate_line()
123              file.write(line)
124              written_size += len(line.encode("utf-8"))  # Account for byte size
125              print(f"Written: {written_size / (1024 * 1024):.2f} MB", end="\r")
126  
127  # Run the script
128  if __name__ == "__main__":
129      # Ask the user for the desired file size
130      size_input = float(input("Enter the desired file size (e.g., 1 for 1GB, 0.5 for 500MB, 0.1 for 100MB): "))
131      
132      # Convert the size to bytes and determine the appropriate unit for the filename
133      if size_input >= 1:
134          size_bytes = size_input * 1024 * 1024 * 1024  # Convert GB to bytes
135          size_label = f"{int(size_input)}gb" if size_input.is_integer() else f"{size_input}gb"
136      else:
137          size_bytes = size_input * 1024 * 1024  # Convert MB to bytes
138          size_label = f"{int(size_input * 1000)}mb" if (size_input * 1000).is_integer() else f"{size_input * 1000}mb"
139      
140      # Adjust the filename based on the size
141      filename = f"fake_data_{size_label}.txt"
142      
143      print(f"Generating {size_label.upper()} of fake data in '{filename}'...")
144      generate_file(filename, size_bytes)
145      print("\nDone! File generated successfully.")