web scrape from any website using python without use url code example
Example 1: python web scraping
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 2: 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))
Example 3: web scraper python
>>> raw_html = simple_get('http://www.fabpedigree.com/james/mathmen.htm')
>>> html = BeautifulSoup(raw_html, 'html.parser')
>>> for i, li in enumerate(html.select('li')):
print(i, li.text)
0 Isaac Newton
Archimedes
Carl F. Gauss
Leonhard Euler
Bernhard Riemann
1 Archimedes
Carl F. Gauss
Leonhard Euler
Bernhard Riemann
2 Carl F. Gauss
Leonhard Euler
Bernhard Riemann
3 Leonhard Euler
Bernhard Riemann
4 Bernhard Riemann
# 5 ... and many more...