app.py

import gradio as gr
from transformers import pipeline
from bs4 import BeautifulSoup
import requests

def summarize_blog_post(url):
    # Load summarization pipeline
    summarizer = pipeline("summarization")

    # Get blog post content
    r = requests.get(url)
    soup = BeautifulSoup(r.text, 'html.parser')
    results = soup.find_all(['h1', 'p'])
    text = [result.text for result in results]
    ARTICLE = ' '.join(text)

    # Chunk text
    max_chunk = 500
    ARTICLE = ARTICLE.replace('.', '.<eos>')
    ARTICLE = ARTICLE.replace('?', '?<eos>')
    ARTICLE = ARTICLE.replace('!', '!<eos>')

    sentences = ARTICLE.split('<eos>')
    current_chunk = 0
    chunks = []
    for sentence in sentences:
        if len(chunks) == current_chunk + 1:
            if len(chunks[current_chunk]) + len(sentence.split(' ')) <= max_chunk:
                chunks[current_chunk].extend(sentence.split(' '))
            else:
                current_chunk += 1
                chunks.append(sentence.split(' '))
        else:
            chunks.append(sentence.split(' '))

    for chunk_id in range(len(chunks)):
        chunks[chunk_id] = ' '.join(chunks[chunk_id])

    # Summarize text
    summaries = summarizer(chunks, max_length=120, min_length=30, do_sample=False)
    summary_text = " ".join([summary['summary_text'] for summary in summaries])
    return summary_text

iface = gr.Interface(
    fn=summarize_blog_post, 
    inputs="text", 
    outputs="text",
    title="Medium Blog Post Summarizer",
    description="Enter the URL of a Medium blog post to get a summarized version of the content."
)

iface.launch()