Basic example of using NLTK for name entity extraction.

example1.py

import nltk

with open('sample.txt', 'r') as f:
    sample = f.read()
     
sentences = nltk.sent_tokenize(sample)
tokenized_sentences = [nltk.word_tokenize(sentence) for sentence in sentences]
tagged_sentences = [nltk.pos_tag(sentence) for sentence in tokenized_sentences]
chunked_sentences = nltk.batch_ne_chunk(tagged_sentences, binary=True)

def extract_entity_names(t):
    entity_names = []
    
    if hasattr(t, 'node') and t.node:
        if t.node == 'NE':
            entity_names.append(' '.join([child[0] for child in t]))
        else:
            for child in t:
                entity_names.extend(extract_entity_names(child))
                
    return entity_names

entity_names = []
for tree in chunked_sentences:
    # Print results per sentence
    # print extract_entity_names(tree)
    
    entity_names.extend(extract_entity_names(tree))

# Print all entity names
#print entity_names

# Print unique entity names
print set(entity_names)

@rsingh2083

You have to download the package using the following command in terminal:

import nltk
nltk.donwload('batch_ne_chunk')

Hey, can you attach the sample.txt file you used with this code? I am getting an empty set

Hey, can you attach the sample.txt file you used with this code? I am getting an empty set

Sorry. I didn't understand what you asked?

Hi and thanks for the code. I tried the version 'ririw commented on 3 Jul 2015'. I got syntax error on the last line where it was converting to unique names. If I deleted set then it worked and that was actually better for me because my need was to list the names by frequency. I tried it on an Icelandic saga, Laxdæla ant it worked fine. I added a dictionary to achieve unique names and a line to sort them by value. Here is the adapted code:
import nltk
with open('laxd.txt', 'r') as f:
sample = f.read()
sentences = nltk.sent_tokenize(sample)
tokenized_sentences = [nltk.word_tokenize(sentence) for sentence in sentences]
tagged_sentences = [nltk.pos_tag(sentence) for sentence in tokenized_sentences]
chunked_sentences = nltk.ne_chunk_sents(tagged_sentences, binary=True)

def extract_entity_names(t):
entity_names = []

if hasattr(t, 'label') and t.label:
    if t.label() == 'NE':
        entity_names.append(' '.join([child[0] for child in t]))
    else:
        for child in t:
            entity_names.extend(extract_entity_names(child))

return entity_names

entity_names = []
names = {}
for tree in chunked_sentences:
# Print results per sentence
# print extract_entity_names(tree)
entity_names.extend(extract_entity_names(tree))
for w in entity_names:
names[w] = names.get(w, 0) +1

Print all entity names

print(sorted(names.items(), key=lambda x:x[1], reverse=True))