Created
August 27, 2024 21:55
-
-
Save ArthurN/d151d06f881a16498216f02380e28b15 to your computer and use it in GitHub Desktop.
extruct-test.py
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 pprint | |
| import extruct | |
| import requests | |
| from w3lib.html import get_base_url | |
| # https://www.crosswaterlondon.com/product/mpro-towel-holder?variant=54381#image-2 | |
| pp = pprint.PrettyPrinter(indent=0) | |
| r = requests.get('https://www.signaturehardware.com/ruscello-widespread-bathroom-faucet/951334.html') | |
| base_url = get_base_url(r.text, r.url) | |
| data = extruct.extract(r.text, base_url=base_url) | |
| pp.pprint(data) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment