27 lines
707 B
Python
27 lines
707 B
Python
#!/usr/bin/env python
|
|
# coding: utf8
|
|
import re
|
|
from nltk.tokenize import sent_tokenize, word_tokenize
|
|
from nltk.corpus import stopwords
|
|
|
|
#source = open("mirabeau.txt", 'r')
|
|
#destination = open("mirabeau_redux.txt", "wt")
|
|
|
|
phrase = "Sous le pont Mirabeau coule la Seine Et nos amours Faut-il qu'il m'en souvienne..."
|
|
print("poeme original:", phrase)
|
|
|
|
phrase = phrase.replace("'", " ")
|
|
phrase = phrase.replace("-", " ")
|
|
print(phrase)
|
|
l_phrase = phrase.split(" ")
|
|
print("liste des mots originaux séparés:", l_phrase)
|
|
|
|
# liste vide pour recevoir la liste de mots reduits
|
|
p_reduit = []
|
|
|
|
stopWords = set(stopwords.words('french'))
|
|
for w in l_phrase:
|
|
if w not in stopWords:
|
|
p_reduit.append(w)
|
|
print(p_reduit)
|