File size: 1,573 Bytes
c25ddba |
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 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 |
from flask import Flask, request, jsonify
from nltk import sent_tokenize, word_tokenize, FreqDist
from nltk.corpus import stopwords
from nltk.tokenize.treebank import TreebankWordDetokenizer
import nltk
app = Flask(__name__)
nltk.download("punkt")
nltk.download("stopwords")
stop_words = set(stopwords.words("english"))
def summarize_text(text):
sentences = sent_tokenize(text)
words = word_tokenize(text)
# Remove stopwords
words = [word.lower() for word in words if word.isalnum() and word.lower() not in stop_words]
# Calculate word frequency
freq_dist = FreqDist(words)
# Sort sentences based on the sum of word frequencies
sorted_sentences = sorted(sentences, key=lambda sentence: sum(freq_dist[word] for word in word_tokenize(sentence)))
# Take the top 3 sentences as the summary
summary = " ".join(sorted_sentences[-3:])
return summary
def extract_keywords(text):
words = word_tokenize(text)
keywords = [word.lower() for word in words if word.isalnum() and word.lower() not in stop_words]
return keywords
@app.route('/text/summarize', methods=['POST'])
def summarize_text_route():
data = request.get_json()
text = data['text']
summary = summarize_text(text)
return jsonify({'summary': summary})
@app.route('/text/extract', methods=['POST'])
def extract_keywords_route():
data = request.get_json()
text = data['text']
keywords = extract_keywords(text)
return jsonify({'keywords': keywords})
if __name__ == '__main__':
app.run(debug=True)
|