Scrape app.box.com pseudo PDFs

scrape_box.py

import os
import base64
import time
from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait


TIMEOUT = 10000

driver = webdriver.Safari()
driver.maximize_window()

try:
    with open("links.txt") as f:
        links = f.read()

    for i, link in enumerate(links.splitlines()):

        if i != 0 and i % 50 == 0:
            time.sleep(20)

        name = None

        driver.get(link)
        name_el = WebDriverWait(driver, TIMEOUT).until(
            lambda d: d.find_element(by=By.CLASS_NAME, value="item-name"))
        name = name_el.text

        if not os.path.exists(name):
            os.mkdir(name)

        page_els = WebDriverWait(driver, TIMEOUT).until(
            lambda d: d.find_elements(by=By.CLASS_NAME, value="page")
        )

        for idx, page_el in enumerate(page_els):
            driver.execute_script("arguments[0].scrollIntoView(true);", page_el)
            time.sleep(0.3)
            canvas_el = WebDriverWait(driver, TIMEOUT).until(
                lambda d: page_el.find_element(by=By.TAG_NAME, value="canvas")
            )

            b64str = driver.execute_script("return arguments[0].toDataURL('image/png');", canvas_el)
            with open(f"{name}/{idx:03d}.png", 'wb') as f:
                f.write(base64.b64decode(b64str[22:]))

except Exception as e:
    raise e

finally:
    print(name, link)
    driver.quit()