from newspaper import Article, Config
from transformers import pipeline
import gradio as gr
import nltk
nltk.download('punkt')


def extract_article_summary(url):
    USER_AGENT = "Mozilla/5.0 (Macintosh; Intel Mac OS X 10.15; rv:78.0) Gecko/20100101 Firefox/78.0"
    config = Config()
    config.browser_user_agent = USER_AGENT
    config.request_timeout = 10

    article = Article(url, config=config)
    article.download()
    article.parse()
    text = article.text
    summarizer = pipeline("summarization", model="facebook/bart-large-cnn")
    return summarizer(text)[0]["summary_text"]


sample_url = [
    [
        "https://www.technologyreview.com/2021/07/22/1029973/deepmind-alphafold-protein-folding-biology-disease-drugs-proteome/"
    ],
    [
        "https://www.technologyreview.com/2021/07/21/1029860/disability-rights-employment-discrimination-ai-hiring/"
    ],
    [
        "https://www.technologyreview.com/2021/07/09/1028140/ai-voice-actors-sound-human/"
    ],
]

desc = """
        Let Hugging Face models summarize articles for you. 
        Note: Shorter articles generate faster summaries.
        This summarizer uses bart-large-cnn model by Facebook
        """

demo = gr.Interface(
    extract_article_summary,
    inputs=gr.Textbox(lines=2, label="URL"),
    outputs="text",
    title="News Summarizer",
    theme="huggingface",
    description=desc,
    examples=sample_url,
)

demo.launch()