import nltk
nltk.download('stopwords')

from nltk.corpus import stopwords
from nltk.stem import WordNetLemmatizer
from nltk.tokenize import word_tokenize
import string

def preprocess(text):
# Menghapus tanda baca
text = text.translate(str.maketrans("", "", string.punctuation))

# Tokenisasi kata
tokens = word_tokenize(text.lower())

# Menghapus stop words
stop_words = set(stopwords.words("english"))
tokens = [token for token in tokens if not token in stop_words]

# Lematisasi kata
lemmatizer = WordNetLemmatizer()
tokens = [lemmatizer.lemmatize(token) for token in tokens]

# Menggabungkan kembali kata
text = " ".join(tokens)
return text

# Pra-pemrosesan data
data = [preprocess(text) for text in data]

sklearn.feature_extraction.text
import TfidfVectorizervectorizer = TfidfVectorizer()
X = vectorizer.fit_transform(data)

from sklearn.cluster import KMeans

kmeans = KMeans(n_clusters=5)
kmeans.fit(X)

clusters = kmeans.predict(X)

from sklearn.metrics import silhouette_score

score = silhouette_score(X, clusters)
print(score)

import requests
from bs4 import BeautifulSoup
import nltk
nltk.download('stopwords')

from nltk.corpus import stopwords
from nltk.stem import WordNetLemmatizer
from nltk.tokenize import word_tokenize
import string
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.cluster import KMeans
from sklearn.metrics import silhouette_score

# Crawling data
url = "https://www.example.com"
response = requests.get(url)
soup = BeautifulSoup(response.text, "html.parser")

data = []

# Mengambil teks dari tag <p>
for p in soup.find_all("p"):
data.append(p.text)

# Pra-pemrosesan teks
def preprocess(text):
# Menghapus tanda baca
text = text.translate(str.maketrans("", "", string.punctuation))

# Tokenisasi kata
tokens = word_tokenize(text.lower())

# Menghapus stop words
stop_words = set(stopwords.words("