beautifulsoup tutorial 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: beautifulsoup python

import bs4 as bs
import urllib.request

source = urllib.request.urlopen('https://pythonprogramming.net/parsememcparseface/').read()

Example 3: beautiful soup 4

from bs4 import BeautifulSoup

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

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

Example 4: webbscraping website with beautifulsoup

import requests
from bs4 import BeautifulSoup

URL = 'https://www.monster.com/jobs/search/?q=Software-Developer&where=Australia'
page = requests.get(URL)

soup = BeautifulSoup(page.content, 'html.parser')

Example 5: web scraper python

>>> from bs4 import BeautifulSoup
>>> raw_html = open('contrived.html').read()
>>> html = BeautifulSoup(raw_html, 'html.parser')
>>> for p in html.select('p'):
...     if p['id'] == 'walrus':
...         print(p.text)

'I am the walrus'

Example 6: 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))

Tags:

Misc Example

Recent Posts