bs4.beautifulsoup code example

Example 1: use beautifulsoup

#start


from bs4 import BeautifulSoup
import requests

req = requests.get('https://www.slickcharts.com/sp500')
soup = BeautifulSoup(req.text, 'html.parser')

Example 2: beautiful soup 4

from bs4 import BeautifulSoup

with open("index.html") as fp:
    soup = BeautifulSoup(fp)

soup = BeautifulSoup("<html>a web page</html>")

Example 3: beautifulsoup4

from bs4 import BeautifulSoup
# works very well with Requests or urllib module 

# Quick Start
from bs4 import BeautifulSoup
soup = BeautifulSoup("<p>Some<b>bad<i>HTML")
print(soup.prettify())
#OUTPUT: 
<html>
 <body>
  <p>
   Some
   <b>
    bad
    <i>
     HTML
    </i>
   </b>
  </p>
 </body>
</html>

>>> soup.find(text="bad")
'bad'
>>> soup.i
<i>HTML</i>

# Another Example
>>> soup = BeautifulSoup("<tag1>Some<tag2/>bad<tag3>XML", "xml")
>>> print(soup.prettify())

<?xml version="1.0" encoding="utf-8"?>
<tag1>
 Some
 <tag2/>
 bad
 <tag3>
  XML
 </tag3>
</tag1>