Function_Sumrerize_URL_Read.py

from sumy.parsers.plaintext import PlaintextParser
from sumy.nlp.tokenizers import Tokenizer
from sumy.summarizers.lsa import LsaSummarizer


from newspaper import Article
import os
import requests
import gpt_2_simple as gpt2
import tensorflow as tf

import nltk
nltk.download('punkt')


def extract_course_information(course_design_variables):
 course_data = {}

# Retrieve course information from the web
 url = course_design_variables["url"]
 article = Article(url)
 article.download()
 article.parse()

# Extract course title
 course_title = article.title if article.title else "Title not found on the page"
 course_data['course_title'] = course_title

# Extract course description
 course_description = article.text if article.text else "Description not found on the page"
 course_data['course_description'] = course_description

# Extract authors
 authors = ', '.join(article.authors) if article.authors else "Authors not found"
 course_data['authors'] = authors

# Extract publish date
 publish_date = article.publish_date if article.publish_date else "Publish date not found"
 course_data['publish_date'] = publish_date

# Extract keywords
 keywords = ', '.join(article.keywords) if article.keywords else "Keywords not found"
 course_data['keywords'] = keywords

return course_data, article

# Example Usage
course_url = "https://uwex.wisconsin.edu/sustainable-management/masters/"
course_design_variables = {"url": course_url}

# Extract course information
course_data, article = extract_course_information(course_design_variables)

if False:
   # Print the extracted information
   print("Course Title: ", course_data['course_title'])
   print("Course Description: ", course_data['course_description'])
   print("Authors: ", course_data['authors'])
   print("Publish Date: ", course_data['publish_date'])
   print("Keywords: ", course_data['keywords'])

# Generate text with Sumy
parser = PlaintextParser.from_string(course_data['course_description'], Tokenizer("english"))
summarizer = LsaSummarizer()
summary_sumy = summarizer(parser.document, 3)
print("\nSumy Summary and remove the html content from this content :\n", summary_sumy)