#! /usr/bin/python3 # =================================================================== # www.dataquest.io/blog/web-scraping-tutorial-python/ # www.geeksforgeeks.org/implementing-web-scraping-python-beautiful-soup/ # www.crummy.com/software/BeautifulSoup/bs4/doc/ # =================================================================== import requests from bs4 import BeautifulSoup as bs import sys # ------------------------------------------------------------------- # ---- global data # ------------------------------------------------------------------- URL = "http://localhost/index.html" # ------------------------------------------------------------------- # ---- main # ------------------------------------------------------------------- if __name__ == '__main__': # ---- request web page (URL) page = requests.get(URL) print(f'Request status code is {page.status_code}') if not page.status_code == 200: print('Error: request web page failed') print(URL) sys.exit() # ---- If this line causes an error, run 'pip install html5lib' soup = bs(page.content, 'html5lib') print(soup.prettify()) ##soup = bs(page.content,'html.parser')