%%html
<style>
div.input {
display:none;
}
</style>
import nltk
with open('text-eng.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 = []
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(entity_names)
file = open("names-extracted.txt", "w")
for element in entity_names:
print(f"{element}", file=file)
file.close()
import os
os.system('cat names-extracted.txt | sort | uniq > names-sorted-uniq-PDF.txt')