pip install newspaper3k
python
import newspaper
from newspaper import Article
import numpy as np
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.cluster import KMeans
python
urls = ['https://example.com/article1',
'https://example.com/article2',
'https://example.com/article3']
python
def get_article_text(url):
article.download()
article.parse()
return article.text
python
articles_text = []
for url in urls:
text = get_article_text(url)
articles_text.append(text)
python
vectorizer = TfidfVectorizer()
tfidf_matrix = vectorizer.fit_transform(articles_text)
cosine_similarity = (tfidf_matrix * tfidf_matrix.T).A
python
kmeans = KMeans(n_clusters=k)
kmeans.fit(tfidf_matrix)
python
groups = [[] for _ in range(k)]
for i, label in enumerate(kmeans.labels_):
groups[label].append(urls[i])
python
for i, group in enumerate(groups):
print(f"Cluster {i+1}:")
for url in group:
print(url)
print('
')
