https://stackoverflow.com/questions/12250580/parse-birth-and-death-dates-from-wikipedia

wikipedia_lifespan.py

from datetime import datetime
from dateutil import parser
import csv
import json
import requests


def id_for_page(page):
    """Uses the wikipedia api to find the wikidata id for a page"""
    api = "https://en.wikipedia.org/w/api.php"
    query = "?action=query&prop=pageprops&titles=%s&format=json"
    slug = page.split('/')[-1]

    response = json.loads(requests.get(api + query % slug).content)
    # Assume we got 1 page result and it is correct.
    page_info = list(response['query']['pages'].values())[0]
    return  page_info['pageprops']['wikibase_item']


def lifespan_for_id(wikidata_id):
    """Uses the wikidata API to retrieve wikidata for the given id."""
    data_url = "https://www.wikidata.org/wiki/Special:EntityData/%s.json"
    page = json.loads(requests.get(data_url % wikidata_id).content)

    claims = list(page['entities'].values())[0]['claims']
    # P569 (birth) and P570 (death) ... not everyone has died yet.
    return [get_claim_as_time(claims, cid) for cid in ['P569', 'P570']]


def get_claim_as_time(claims, claim_id):
    """Helper function to work with data returned from wikidata api"""
    try:
        claim = claims[claim_id][0]['mainsnak']['datavalue']
        assert claim['type'] == 'time', "Expecting time data type"

        # dateparser chokes on leading '+', thanks wikidata.
        return parser.parse(claim['value']['time'][1:])
    except KeyError as e:
        print(e)
        return None


def main():
    page = 'https://en.wikipedia.org/wiki/Albert_Einstein'

    # 1. use the wikipedia api to find the wikidata id for this page
    wikidata_id = id_for_page(page)

    # 2. use the wikidata id to get the birth and death dates
    span = lifespan_for_id(wikidata_id)

    for label, dt in zip(["birth", "death"], span):
        print(label, " = ", datetime.strftime(dt, "%b %d, %Y"))