Entity Extraction using NLTK

gistfile1.py

import nltk

text =  """Barack Hussein Obama II  (born August 4, 1961) is the 44th and current President of the United States. He is the first African American to hold the office. Obama previously served as a United States Senator from Illinois, from January 2005 until he resigned after his election to the presidency in November 2008."""

sentences = nltk.sent_tokenize(text)
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:
    entity_names.extend(extract_entity_names(tree))

print entity_names