Created
August 26, 2017 23:58
-
-
Save rsarai/b8a7db3289827b5f1f2e43cf6502c7a8 to your computer and use it in GitHub Desktop.
Just a quick example of how to use Beautiful Soup
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import requests | |
from bs4 import BeautifulSoup | |
url = 'http://www.someurl.com.br/products' | |
headers = { | |
'user-agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/53.0.2785.143 Safari/537.36' | |
} | |
r = requests.get(url, headers=headers, timeout=5) | |
# make sure that the page exist | |
if r.status_code == 200: | |
html = r.text | |
soup = BeautifulSoup(html, 'lxml') | |
# get all products | |
products_list_item = soup.find('div', {'class': 'row', 'id': 'products'}) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment