Build an article summarizer bot

Here’s a concise implementation of an Article Summarizer Bot using Python. It fetches an article from a URL, extracts the content, and summarizes it using natural language processing.

python
CopyEdit
import requests
from bs4 import BeautifulSoup
from transformers import pipeline

class ArticleSummarizerBot:
    def __init__(self):
        self.summarizer = pipeline("summarization", model="facebook/bart-large-cnn")

    def fetch_article(self, url):
        try:
            headers = {'User-Agent': 'Mozilla/5.0'}
            response = requests.get(url, headers=headers)
            soup = BeautifulSoup(response.text, 'html.parser')

            # Extract visible paragraphs
            paragraphs = soup.find_all('p')
            article_text = ' '.join([para.get_text() for para in paragraphs])
            return article_text.strip()
        except Exception as e:
            return f"Error fetching article: {e}"

    def summarize(self, text, max_words=1300):
        try:
            # The summarizer has a token limit, split if text too long
            if len(text.split()) > max_words:
                text = ' '.join(text.split()[:max_words])
            summary = self.summarizer(text, max_length=200, min_length=60, do_sample=False)
            return summary[0]['summary_text']
        except Exception as e:
            return f"Error summarizing: {e}"

    def run(self, url):
        article = self.fetch_article(url)
        if article.startswith("Error"):
            return article
        return self.summarize(article)

# Example Usage
if __name__ == "__main__":
    bot = ArticleSummarizerBot()
    url = "https://example.com/sample-news-article"
    summary = bot.run(url)
    print("nSummary:n", summary)

Key Features:

• Article Extraction: Pulls article content using requests and BeautifulSoup.

• Summarization: Uses facebook/bart-large-cnn from Hugging Face Transformers.

• Handles Long Articles: Trims content to fit model input limits.

Would you like a version of this as a web app or API endpoint as well?