forked from p46318075/CodePattern
You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
15 lines
355 B
15 lines
355 B
import sys, re, string
|
|
from cppy.cp_util import *
|
|
|
|
def extract_words(path_to_file):
|
|
with open(path_to_file,encoding='utf-8') as f:
|
|
str_data = f.read()
|
|
pattern = re.compile('[\W_]+')
|
|
word_list = pattern.sub(' ', str_data).lower().split()
|
|
|
|
|
|
stop_words = get_stopwords()
|
|
|
|
return [w for w in word_list if not w in stop_words]
|
|
|