modules/utils.py

import pdfplumber
from newspaper import Article

def read_pdf(file):
    text = ""
    with pdfplumber.open(file) as pdf:
        for page in pdf.pages:
            page_text = page.extract_text()
            if page_text:
                text += page_text + "\n"
    return text.strip()

def fetch_article_from_url(url):
    try:
        article = Article(url)
        article.download()
        article.parse()
        return article.text
    except Exception as e:
        return f"Failed to fetch article: {e}"