python get html info
from bs4 import BeautifulSoup
my_HTML = #Some HTML file (could be a website, you can use urllib for that)
soup = BeautifulSoup(my_HTML, 'html.parser')
print(soup.prettify())python get html info
from bs4 import BeautifulSoup
my_HTML = #Some HTML file (could be a website, you can use urllib for that)
soup = BeautifulSoup(my_HTML, 'html.parser')
print(soup.prettify())web scraper python
def get_names():
"""
Downloads the page where the list of mathematicians is found
and returns a list of strings, one per mathematician
"""
url = 'http://www.fabpedigree.com/james/mathmen.htm'
response = simple_get(url)
if response is not None:
html = BeautifulSoup(response, 'html.parser')
names = set()
for li in html.select('li'):
for name in li.text.split('n'):
if len(name) > 0:
names.add(name.strip())
return list(names)
# Raise an exception if we failed to get any data from the url
raise Exception('Error retrieving contents at {}'.format(url))Copyright © 2021 Codeinu
Forgot your account's password or having trouble logging into your Account? Don't worry, we'll help you to get back your account. Enter your email address and we'll send you a recovery link to reset your password. If you are experiencing problems resetting your password contact us
