Aventri Attendee List Generator

aventri_attendee_generator.py

#!/usr/bin/env python3

import csv
import re
import sys

from faker import Faker


fake = Faker()
 
ADDRESS_RE = re.compile(r'^(.*?), ([A-Z]{2}) ([0-9]{5})$')

FIELDS = [
    'Email Address',
    'Other Identifier',
    'Prefix (Mr, Mrs, Dr etc)',
    'First Name',
    'Middle Name',
    'Last Name',
    'Suffix',
    'Job Title',
    'Company',
    'Address Line 1',
    'Address Line 2',
    'Address Line 3',
    'City',
    'US State',
    'State/County/Province (Non-US)',
    'Zip (Postal Code)',
    'Country',
    'Work Phone',
    'Extension',
    'Fax',
    'Mobile Phone',
    'cc email',
    'Skype/IM/Twitter ID'
]

US_STATES = {
    'AL': 'Alabama',
    'AK': 'Alaska',
    'AZ': 'Arizona',
    'AR': 'Arkansas',
    'CA': 'California',
    'CO': 'Colorado',
    'CT': 'Connecticut',
    'DE': 'Delaware',
    'FL': 'Florida',
    'GA': 'Georgia',
    'HI': 'Hawaii',
    'ID': 'Idaho',
    'IL': 'Illinois',
    'IN': 'Indiana',
    'IA': 'Iowa',
    'KS': 'Kansas',
    'KY': 'Kentucky',
    'LA': 'Louisiana',
    'ME': 'Maine',
    'MD': 'Maryland',
    'MA': 'Massachusetts',
    'MI': 'Michigan',
    'MN': 'Minnesota',
    'MS': 'Mississippi',
    'MO': 'Missouri',
    'MT': 'Montana',
    'NE': 'Nebraska',
    'NV': 'Nevada',
    'NH': 'New Hampshire',
    'NJ': 'New Jersey',
    'NM': 'New Mexico',
    'NY': 'New York',
    'NC': 'North Carolina',
    'ND': 'North Dakota',
    'OH': 'Ohio',
    'OK': 'Oklahoma',
    'OR': 'Oregon',
    'PA': 'Pennsylvania',
    'RI': 'Rhode Island',
    'SC': 'South Carolina',
    'SD': 'South Dakota',
    'TN': 'Tennessee',
    'TX': 'Texas',
    'UT': 'Utah',
    'VT': 'Vermont',
    'VA': 'Virginia',
    'WA': 'Washington',
    'WV': 'West Virginia',
    'WI': 'Wisconsin',
    'WY': 'Wyoming',
    'DC': 'District of Columbia',
    'MP': 'Northern Mariana Islands', 
    'PW': 'Palau', 
    'PR': 'Puerto Rico', 
    'VI': 'Virgin Islands',
}
 
FIELD_GROUPINGS = dict((
    ('Email Address', 'mail'),
    ('Prefix (Mr, Mrs, Dr etc)', 'prefix'),
    ('First Name', 'first_name'),
    ('Last Name', 'last_name'),
    ('Job Title', 'job'),
    ('Company', 'company'),
    ('Address Line 1', 'address'),
    ('City', 'city'),
    ('US State', 'state'),
    ('Zip (Postal Code)', 'zip_code'),
    ('Country', 'country'),
    ('Work Phone', 'work_phone'),
    ('Mobile Phone', 'mobile_phone'),
    ('Extension', 'extension'),
))
 
def new_profile():
    profile = fake.profile()
    prefix = 'Mrs' if profile.get('sex') == 'F' else 'Mr'
    names = profile.get('name').split(' ')
    first_name = names[0]
    last_name = names[-1]
    address, state_info = profile.get('address').split('\n')
    address_match = ADDRESS_RE.match(state_info)
    
    if address_match is None:
        return None
    
    city, state, zip_code = address_match.groups()
    
    work_phone = fake.phone_number()
    extension = ''
    
    if len(work_phone.split('x')) > 1:
        work_phone, extension = work_phone.split('x')
    
    mobile_phone = fake.phone_number()
    
    profile.update({
        'first_name': first_name,
        'last_name': last_name,
        'prefix': prefix,
        'address': address,
        'city': city,
        'state': US_STATES[state],
        'zip_code': zip_code,
        'work_phone': work_phone,
        'mobile_phone': mobile_phone,
        'country': 'United States',
        'extension': extension,
    })
    
    profile_output = {}

    for field in FIELDS:
        matching = FIELD_GROUPINGS.get(field, None)

        if matching is None:
            continue
        
        profile_output[field] = profile.get(matching)

    return profile_output


def generate_attendee_list(output_file_path, limit):
    with open(output_file_path, 'w') as csv_file:
        writer = csv.DictWriter(csv_file, fieldnames=FIELDS)
        
        writer.writeheader()

        total = 0
        
        while total < limit:
            profile = new_profile()
            
            if profile is None:
                continue
            
            writer.writerow(profile)
            
            total += 1


if __name__ == '__main__':
    if len(sys.argv) < 2:
        print("Please provide an output file path")
        sys.exit(0)

    limit = 100

    try:
        limit = int(sys.argv[2])
    except:
        pass

    print("Generating %d attendees..." % limit)

    generate_attendee_list(sys.argv[1], limit)

    print("Done!")

Fake attendee list generator for Aventri. Depends on Faker.

Usage is: ./aventri_attendee_generator.py [output_filename] [number of attendees (optional, defaults to 100)].