Created
August 31, 2022 20:12
-
-
Save petri/2be68b82ae5414add315f41a13687ff2 to your computer and use it in GitHub Desktop.
get product metadata from web page in Python
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 extruct | |
import requests | |
from w3lib.html import get_base_url | |
from urllib.parse import urlparse | |
url = "https://www.kalevala.fi/collections/korvakorut/products/paratiisi-tappikorvakorut-hopea" | |
def extract_metadata(url, syntaxes=['json-ld']): | |
"""Extract all metadata present in the page and return a dictionary of metadata lists. | |
Args: | |
url (string): URL of page from which to extract metadata. | |
Returns: | |
metadata (dict): Dictionary of json-ld, microdata, and opengraph lists. | |
Each of the lists present within the dictionary contains multiple dictionaries. | |
""" | |
r = requests.get(url) | |
base_url = get_base_url(r.text, r.url) | |
metadata = extruct.extract(r.text, | |
base_url=base_url, | |
uniform=True, | |
syntaxes=syntaxes) | |
return metadata | |
d = extract_metadata(url)["json-ld"] | |
products = [p for p in d if p["@type"]=="Product"] | |
print(products) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment