bs4_nytimes_example.py

from bs4 import BeautifulSoup
import requests
 
# get the webpage
r  = requests.get("http://www.nytimes.com")
 
# get the HTML source from that page
html_doc = r.text
 
# turn the source into a bs4 "soup" object
soup = BeautifulSoup(html_doc, 'lxml')
 
# narrow down to the div on the page that contains our content
section = soup.find("div", class_="a-column")
 
# get the first h2, and the link text within that h2
firstHeading = (section.h2.a).get_text()
 
# remove the line breaks
firstHeading = firstHeading.replace('\n',' ')
 
# display the final text
print(firstHeading)