| 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 auto_link(url): |
| USER_AGENT = 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10.15; rv:78.0) Gecko/20100101 Firefox/78.0' |
| configuration = Config() |
| configuration.browser_user_agent = USER_AGENT |
| configuration.request_timeout = 10 |
| abstract = Article(url, config =configuration) |
| abstract.download() |
| abstract.parse() |
| text = abstract.text |
| return text |
| |
| |
| extract = gr.Interface(auto_link, 'text', 'text') |
| abstractive_summarization = gr.Interface.load("huggingface/facebook/bart-large-cnn") |
|
|
| example_urls = [['https://www.ibm.com/cloud/learn/machine-learning/'], |
| ['https://www.cnn.com/2021/11/24/us/arctic-ocean-early-warming-climate/index.html/'], |
| ['https://www.britannica.com/topic/Pyramids-of-Giza']] |
|
|
| title = ''' |
| summarizeer |
| |
| ''' |
|
|
| UI_summarizer = Series(extract, abstractive_summarization, inputs = gr.inputs.Textbox (lines = 2, label = 'URL'), |
| outputs = 'text', title = 'Summarization', theme = 'huggingface', description = title, |
| examples= example_urls) |
| |
| UI_summarizer.launch(inline = False) |
|
|
