Make a list of random names
Sometimes you just want to build a list of random names. Here's a quick and easy way.
Sometimes you just want to build a list of random names. Here's a quick and easy way.
Code Breakdown
First we import all the libraries we will need.
import lxml.html
import requests
import yaml
import random
This function performs a critical role. First it gets a page from the internet, parses it using the LXML library, and then gets a list of names based on a supplied XPath.
def get_names(url,xpath):
page = requests.get(url)
tree = lxml.html.fromstring(page.content)
names = [item.text for item in tree.xpath(xpath)]
return names
To get a list of first names, we first visit a random web page that has a list of names and obtain the xpath for the element that we care about. By supplying the URL to the page and the XPath string, we can get back the list of first names.
xpath='/html/body/div/div/div[1]/div/div/div[4]/table/tbody/tr[*]/td[2]/a'
url = 'https://www.thenamegeek.com/most-common-first-names'
first_names = get_names(url,xpath)
We reuse this function for finding a list of last names, and then extend the initial list with the second through fifth page results as well
xpath= '/html/body/div/div/main/section[2]/div[2]/table/tbody/tr[*]/td[2]/a'
url = 'https://namecensus.com/last-names/'
last_names = get_names(url,xpath)
last_names.extend(get_names('https://namecensus.com/last-names/?page=2',xpath))
last_names.extend(get_names('https://namecensus.com/last-names/?page=3',xpath))
last_names.extend(get_names('https://namecensus.com/last-names/?page=4',xpath))
last_names.extend(get_names('https://namecensus.com/last-names/?page=5',xpath))
We create a dictionary and put the list of first names and last names in the dictionary.
my_dict = {}
my_dict['first_names'] = first_names
my_dict['last_names'] = last_names
To create arbitrary email addresses we supply a list of fun old school provider names.
providers = []
providers.append('gmail.com')
providers.append('yahoo.com')
providers.append('aol.com')
providers.append('altavista.net')
providers.append('comcast.net')
providers.append('geocities.com')
providers.append('friendster.com')
providers.append('myspace.com')
to create a full user profile, We combine a randomized first name and last name With a randomized provider to create a random full name and email. These profiles are added to a list of random profiles, Which are also added to our dictionary.
random_names = []
for ii in range(1000):
first_name = random.choice(first_names)
last_name = random.choice(last_names)
provider = random.choice(providers)
full_name = f'{first_name} {last_name}'
email = f'{first_name}_{last_name}@{provider}'
user = {}
user['first_name'] = first_name
user['last_name'] = last_name
user['full_name'] = full_name
user['email'] = email
random_names.append(user)
my_dict['random_names'] = random_names
With our dictionary completed, we save it to a file on our PC.
with open('names.yaml','w') as f:
yaml.dump(my_dict,f)
Full Code
import lxml.html
import requests
import yaml
import random
def get_names(url,xpath):
page = requests.get(url)
tree = lxml.html.fromstring(page.content)
first_names = [item.text for item in tree.xpath(xpath)]
return first_names
xpath='/html/body/div/div/div[1]/div/div/div[4]/table/tbody/tr[*]/td[2]/a'
url = 'https://www.thenamegeek.com/most-common-first-names'
first_names = get_names(url,xpath)
xpath= '/html/body/div/div/main/section[2]/div[2]/table/tbody/tr[*]/td[2]/a'
url = 'https://namecensus.com/last-names/'
last_names = get_names(url,xpath)
last_names.extend(get_names('https://namecensus.com/last-names/?page=2',xpath))
last_names.extend(get_names('https://namecensus.com/last-names/?page=3',xpath))
last_names.extend(get_names('https://namecensus.com/last-names/?page=4',xpath))
last_names.extend(get_names('https://namecensus.com/last-names/?page=5',xpath))
my_dict = {}
my_dict['first_names'] = first_names
my_dict['last_names'] = last_names
providers = []
providers.append('gmail.com')
providers.append('yahoo.com')
providers.append('aol.com')
providers.append('altavista.net')
providers.append('comcast.net')
providers.append('geocities.com')
providers.append('friendster.com')
providers.append('myspace.com')
random_names = []
for ii in range(1000):
first_name = random.choice(first_names)
last_name = random.choice(last_names)
provider = random.choice(providers)
full_name = f'{first_name} {last_name}'
email = f'{first_name}_{last_name}@{provider}'
user = {}
user['first_name'] = first_name
user['last_name'] = last_name
user['full_name'] = full_name
user['email'] = email
random_names.append(user)
my_dict['random_names'] = random_names
with open('names.yaml','w') as f:
yaml.dump(my_dict,f)
