LowWeiLin

import itertools

def grouper(n, iterable):
    it = iter(iterable)
    while True:
        chunk = tuple(itertools.islice(it, n))
        if not chunk:
            return
        yield chunk

LowWeiLin

import json
import time
from selenium import webdriver
from selenium.webdriver.common.desired_capabilities import DesiredCapabilities
from selenium.webdriver.chrome.options import Options


def process_browser_log_entry(entry):
    entry["message"] = json.loads(entry["message"])["message"]
    return entry

LowWeiLin

# https://www.elastic.co/blog/loading-wikipedia
# https://github.com/wikimedia/search-extra

# bin/elasticsearch-plugin install analysis-icu
# bin/elasticsearch-plugin install org.wikimedia.search:extra:6.3.1.2

# Variables
es="host.docker.internal:9200"
site="en.wikipedia.org"
index="enwiki"