from newspaper import Article
from newspaper import Config
import nltk
nltk.download('punkt')

from transformers import pipeline
import gradio as gr
from gradio.mix import Parallel, Series


def extract_article_text(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
  return text

extractor = gr.Interface(extract_article_text, 'text', 'text')
summarizer = gr.Interface.load("huggingface/facebook/bart-large-cnn")

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
        '''

iface = Series(extractor, summarizer, 
  inputs = gr.inputs.Textbox(
      lines = 2,
      label = 'URL'
  ),
  outputs = 'text',
  title = 'News Summarizer',
  theme = 'huggingface',
  description = desc,
  examples=sample_url)

iface.launch()