-
Notifications
You must be signed in to change notification settings - Fork 0
/
no._tweet_extractor.py
29 lines (22 loc) · 933 Bytes
/
no._tweet_extractor.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
import nltk
from nltk.corpus import state_union
from nltk.tokenize import PunktSentenceTokenizer
train_text = state_union.raw("2005-GWBush.txt")
#sample_text = state_union.raw("2006-GWBush.txt")
custom_sent_tokenizer = PunktSentenceTokenizer(train_text)
tokenized = custom_sent_tokenizer.tokenize("Please save my ass my no is 98437598237459, 47598437")
def process_content():
try:
for i in tokenized:
words = nltk.word_tokenize(i)
tagged = nltk.pos_tag(words)
chunkGram = r"""Chunk: {<CD>+}"""
chunkParser = nltk.RegexpParser(chunkGram)
chunked = chunkParser.parse(tagged)
#print(chunked.label())
for subtree in chunked.subtrees():
if subtree.label() == 'Chunk':
print(subtree[0][0])
except Exception as e:
print(str(e))
process_content()