Download app.py from imseldrith/Content-Quality-Checker: direct link, hf CLI and curl.
- Browser
- Download file 1.06 kB
-
https://huggingface.co/spaces/imseldrith/Content-Quality-Checker/resolve/main/app.py
- Command line
-
hf download hf://spaces/imseldrith/Content-Quality-Checker/app.py
-
curl -L -o app.py https://huggingface.co/spaces/imseldrith/Content-Quality-Checker/resolve/main/app.py
1.06 kB
| from flask import Flask, request, render_template | |
| import nltk | |
| import requests | |
| from bs4 import BeautifulSoup | |
| nltk.download('punkt') | |
| nltk.download('averaged_perceptron_tagger') | |
| app = Flask(__name__) | |
| def home(): | |
| if request.method == "POST": | |
| url = request.form["url"] | |
| html = requests.get(url).content | |
| soup = BeautifulSoup(html, "html.parser") | |
| text = soup.get_text() | |
| # Use nltk to perform NLP analysis on the text | |
| tokens = nltk.word_tokenize(text) | |
| tagged = nltk.pos_tag(tokens) | |
| # Check for the presence of certain POS tags to determine content quality | |
| content_quality = "High Quality" | |
| for word, pos in tagged: | |
| if pos in ["CC", "DT", "IN", "MD", "PRP", "PRP$", "TO"]: | |
| content_quality = "Low Quality" | |
| break | |
| return render_template("result.html", quality=content_quality) | |
| return render_template("home.html") | |
| if __name__ == "__main__": | |
| app.run(host="0.0.0.0",port=7860,debug=True) | |