import requests from readability import Document import webbrowser,os """ So we need a url that contains a lot of boilerplate. I found one. You could insert any other url of your choice """ url = 'https://timesofindia.indiatimes.com/city/delhi/delhi-records-all-time-high-of-48-degrees-celsius-heat-wave-to-continue/articleshow/69727572.cms' """ Fetch the webpage using requests library """ response = requests.get(url) """ Run the Document function from reability package. This is what does the magic.""" document = Document(response.text) """ We get the content using the document.summary() function. Let's write it down into a file a invoke a web browser to see if we really did get what we wanted """ f = open('tempwebpage.html','w') f.write(document.summary()) f.close() webbrowser.open('file://' + os.path.realpath('tempwebpage.html'))