Python with Selenium code to scrape quantamagazine.com and save articles to pdf using chromedriver

quanta_scrape.py

from gql import gql, Client
from gql.transport.requests import RequestsHTTPTransport
from selenium import webdriver
from selenium.webdriver.support.ui import WebDriverWait
import os
import json
import sys
import subprocess

SPECIAL_CHARS = ['\\', '/', ':', '?', '*', '<', '>', '|']
CHROMEDRIVER_PATH = 'chromedriver.exe'

class QuantaScrape(object):
    url="https://www.quantamagazine.org/graphql"
    headers={"Content-type": "application/json"}

    def __init__(self):
        self.transport = None
        self.client = None

    def define_transport(self):
        self.transport = RequestsHTTPTransport(
            use_json=True,
            url=self.url,
            verify=False,
            headers=self.headers,
            retries=3
        )

    def define_client(self):
        self.client = Client(transport=self.transport, fetch_schema_from_transport=True)

    def execute(self, query, variables):
        self.define_transport()
        self.define_client()
        return self.client.execute(query, variable_values=variables)

query = gql(
    """
    query ($offset: Int){
        operationName: getPostPageArchive(offset: $offset, type: "archive"){
            meta{
                max_num_pages
            }
            data{
                ...on Post{
                    title
                    link
                }
            }
        }
    }
    """
)

def print_to_pdf(title, link):
    appState = {
            "recentDestinations": [{
                "id": "Save as PDF",
                "origin": "local",
                "account": "",
            }],
            "selectedDestinationId": "Save as PDF",
            "version": 2
        }
    prefs = {
        'printing.print_preview_sticky_settings.appState': json.dumps(appState)
        }
    chrome_options = webdriver.ChromeOptions()
    chrome_options.add_experimental_option('prefs', prefs)
    chrome_options.add_argument('--kiosk-printing')
    driver = webdriver.Chrome(executable_path=CHROMEDRIVER_PATH, options=chrome_options)
    driver.get(link)
    driver.execute_script("window.scrollTo(0, document.body.scrollHeight);")
    WebDriverWait(driver, 20)
    driver.execute_script('window.print();')
    driver.quit()


def download_pdf(filename):
    with open(filename) as f:
        data = json.load(f)
        for article in data:
            title = '_'.join(article['title'].split(' '))
            link = article['link']
            for char in title:
                if char in SPECIAL_CHARS:
                    title = title.replace(char, '')
            print(title)
            print_to_pdf(title, link)


def main():
    articles = []
    scraper = QuantaScrape()
    offset = 1
    data = scraper.execute(query, {"offset": offset})
    for pages in range(1, data['operationName']['meta']['max_num_pages']+1):
        data = scraper.execute(query, {"offset": offset})
        articles.extend(data['operationName']['data'])
        offset += 1

    with open('articles.json', 'w') as f:
        f.write(json.dumps(articles, indent=4))

if __name__=='__main__':
    if sys.argv[1] == 'download':
        download_pdf(sys.argv[2])
    else:
        main()