Open Graph Parser Example

og_parser.py

from html.parser import HTMLParser
import requests
from pprint import pprint


class OpenGraphParser(HTMLParser):
    """
    Parses the Open Graph tags and returns a dictionary with values:

    For example,
    <meta property="og:type" content="website" />
    <meta property="og:url" content="https://www.1st-things-1st.com/tips/4ysX4JhY4s8v/" />
    <meta property="og:title" content="Daily Tips on Prioritization, Productivity, & Growth" />
    <meta property="og:image" content="https://www.1st-things-1st.com/media/tips/2023/4ysX4JhY4s8v/tip.png" />
    <meta property="og:description" content="" />
    <meta property="og:site_name" content="1st things 1st" />
    <meta property="og:locale" content="en_US" />
    """

    OG_PROPERTIES = [
        "og:title",
        "og:type",
        "og:image",
        "og:url",
        "og:description",
        "og:locale",
        "og:site_name",
    ]

    def __init__(self, *args, **kwargs):
        super().__init__(*args, **kwargs)
        self.og_data = {}

    def handle_starttag(self, tag, attrs):
        if tag.lower() == "meta":
            attrs_dict = dict(attrs)
            if (
                (prop := attrs_dict.get("property"))
                and (content := attrs_dict.get("content"))
                and prop in self.OG_PROPERTIES
            ):
                self.og_data[prop.replace("og:", "")] = content

    def get_data(self):
        return self.og_data


if __name__ == "__main__":
    response = requests.get("https://www.1st-things-1st.com/tips/4ysX4JhY4s8v/")
    og_parser = OpenGraphParser()
    og_parser.feed(response.text)
    og_data = og_parser.get_data()
    pprint(og_data)