Spaces:
Running
Running
File size: 1,562 Bytes
388604c 6b9ee5e 388604c 5ec43a8 388604c 11d28a4 |
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 |
from flask import Flask, request, render_template
import pandas as pd
import nltk
import re
import requests
from nltk.corpus import stopwords
from nltk.sentiment import SentimentIntensityAnalyzer
nltk.download('averaged_perceptron_tagger')
nltk.download('punkt')
app = Flask(__name__)
def clean_content(content):
content = re.sub(r'[^\w\s]','',content)
content = content.lower()
content = nltk.word_tokenize(content)
content = [word for word in content if word not in set(stopwords.words('english'))]
return content
def sentiment_analysis(content):
sentiment = SentimentIntensityAnalyzer()
sentiment_score = sentiment.polarity_scores(content)
return sentiment_score
def content_quality_detection(content):
content_tokens = clean_content(content)
sentiment_score = sentiment_analysis(content)
content_length = len(content_tokens)
if content_length >= 200 and sentiment_score['compound'] >= 0.5:
return 'High-Quality Content'
elif content_length >= 100 and sentiment_score['compound'] >= 0.2:
return 'Moderate-Quality Content'
else:
return 'Low-Quality Content'
@app.route('/')
def home():
return render_template('home.html')
@app.route('/', methods=['POST'])
def import_content():
url = request.form['url']
df = pd.read_html(requests.get(url).text)
content = df[0].to_string()
quality = content_quality_detection(content)
return render_template('result.html', quality=quality)
if __name__ == '__main__':
app.run(host="0.0.0.0",port=7860,debug=True)
|