get_raw.py

from selenium import webdriver
from selenium.webdriver.common.keys import Keys
import requests
import os
import time
import json

driver = webdriver.Firefox(executable_path="D:/AITOON/dataset/geckodriver.exe")
#login
driver.get("https://translate.webtoons.com/translate/tool?webtoonNo=182")
time.sleep(2)
driver.find_element_by_class_name("btn_facebook").click()
time.sleep(2)
driver.find_element_by_id("email").send_keys("xxxxxxxxx")
driver.find_element_by_id("pass").send_keys("xxxxxxxx")
driver.find_element_by_id("pass").send_keys(Keys.ENTER)
time.sleep(5)

#ep start from 1 to 129
for ep in range(1,130):
	print("get ep : " + str(ep))
	if not os.path.exists(""+str(ep)):
		os.mkdir(""+str(ep))
	driver.get("https://translate.webtoons.com/translate/tool?webtoonNo=182&teamVersion=0&episodeNo="+str(ep))
	data = driver.execute_script("return translateData;")
	#data[0] [u'backgroundOri', u'episodImg', u'height', u'width', u'background', u'sentences']
	for idx, val in enumerate(data):
		if u'background' not in val:
			continue
		res = requests.get(val[u'background'])
		if res.status_code == 200:
			with open(str(ep)+"/"+str(idx)+".jpg", 'wb') as f:
				f.write(res.content)
	#backup next time 
	with open(str(ep)+'.json','w+') as j:
		j.write(json.dumps(data))
	time.sleep(2)