Obtener Titulos de articulos desde la pagina de Clarin

Python-getHtml.txt

# import the requests Python library for programmatically making HTTP requests
# after installing it according to these instructions: 
# http://docs.python-requests.org/en/latest/user/install/#install
import requests
import json
    
# import the BeautifulSoup Python library according to these instructions: 
# http://www.crummy.com/software/BeautifulSoup/bs4/doc/#installing-beautiful-soup
# use this syntax as described on the documentation page: 
# http://www.crummy.com/software/BeautifulSoup/bs4/doc/#making-the-soup
from bs4 import BeautifulSoup


# the URL of the NY Times website we want to parse
base_url = 'https://www.clarin.com/'

# the syntax (according to the documentation) for how to 
# "load" a webpage through Python
r = requests.get(base_url)
print(r)
# how to decode the text of the HTML of the NY Times homepage
# website. r comes from the requests request above
soup = BeautifulSoup(r.text,"html.parser")

# find and loop through all elements on the page with the 
# class name "story-heading"

#for link in soup.find_all('a'):
#    print(link.get('href'))



#for volanta in (  soup.find_all(class_="summary")  or soup.find_all(class_="volanta")   or soup.find_all(['h1','h2','h3'])  ) :
#    print(volanta.text,"\n" )

    

for volanta in soup.find_all (['p','h1','h2','h3'] ):
    try:
        if ('volanta'  in volanta.attrs.get('class')) :
            print(volanta.text)
    except TypeError:
        pass
    except KeyboardInterrupt:
        print("\nThey are sentinent\n")