Nov05

'''
Load Yelp JSON files and spit out CSV files
Does not try to reinvent the wheel and uses pandas json_normalize
Kinda hacky and requires a bit of RAM. But works, albeit naively.

Tested with Yelp JSON files in dataset challenge round 12:
https://www.yelp.com/dataset/challenge
'''

import json

Nov05

# install chromium, its driver, and selenium
!apt install chromium-chromedriver
!cp /usr/lib/chromium-browser/chromedriver /usr/bin
!pip install selenium
# set options to be headless, ..
from selenium import webdriver
options = webdriver.ChromeOptions()
options.add_argument('--headless')
options.add_argument('--no-sandbox')
options.add_argument('--disable-dev-shm-usage')