Trying to find human names in a file using ntlk


I’d like to extract human names from a text file. I’m getting a blank line as output for some reason. Here is my code:

import nltk
import re'names')'punkt')
from nltk.corpus import names

# Create a list of male and female names from the nltk names corpus
male_names = names.words('male.txt')
female_names = names.words('female.txt')
all_names = set(male_names + female_names)

def flag_people_names(text):
    possible_names = []
    words = nltk.word_tokenize(text)
    for word in words:
        # Split the word by ' ', '.' or '_' and check each part
        parts = re.split('[ _.]', word)
        for part in parts:
            if part.lower() in all_names:
    return possible_names

# Read text file
with open('sample.txt', 'r') as file:
    text =

# Call function to flag possible names
names = flag_people_names(text)

Here is the input file called sample.txt

James is a really nice guy
Gina is a friend of james.
Gina and james like to play with Andy.

I get this as the output:


I’d like to get James, Gina and Andy.

I’m on a MAC Catalina with python3.8.5.
Any idea what’s not working here?

Asked By: Brajesh



Try removing the ".lower()" in "part.lower()" since the NLTK names list is not in all lower but proper capitalization.

Answered By: Adnan S
Categories: questions Tags: ,
Answers are sorted by their score. The answer accepted by the question owner as the best is marked with
at the top-right corner.