fread/readit.py

#!/usr/bin/env python3

from selenium import webdriver
from selenium.webdriver.common.keys import Keys
from selenium.common.exceptions import NoSuchElementException
import argparse, multiprocessing, urllib.request, urllib.error, urllib.parse, time, os
import helpers, setuptools

def status(driver):
 if '<a class="btn btn-primary clickable btn-login">Login</a>' not in driver.page_source:
  return True
 else:
  return False

def loadPage(url, driver, period=5,init=False):
 if not (init or status(driver)):
  login(driver)
 driver.get(url)
 time.sleep(period)

 return True if driver.current_url == url else False

def loginHandler(driver, user = setuptools.riuser(), password = setuptools.ripass()):
 loadPage("https://app.myreadit.com/login",driver,3,True)
  
 curfield = driver.find_element_by_name("email")
 curfield.send_keys(user)
  
 curfield = driver.find_element_by_name("password")
 curfield.send_keys(password)
  
 curfield.send_keys(Keys.RETURN)
 time.sleep(3)

 return status(driver)

class LoginError(Exception):
 pass

def login(driver):
 if not (status(driver) or loginHandler(driver)):
  raise LoginError("Login failed.")
 return True

def pageHandler(driver, id, page):
 if not loadPage("https://app.myreadit.com/reader/%s#%i" % (id, int(page)), driver):
  return False

 img = driver.find_element_by_id("page1").get_attribute("src")
 f = urllib.request.urlopen(img)

 with open("%s/%i.png" % (id, page), "b+w") as o:
  o.write(f.read())

 try:
  img2 = driver.find_element_by_id("page2").get_attribute("src")
  f2 = urllib.request.urlopen(img2)

  with open("%s/%i.png" % (id, page + 1), "b+w") as o2:
   o2.write(f2.read())

  return 2

 except:
  return 1
 
def magazineHandler(driver, id, makepdf = True):
 if helpers.makeDir(id):
  loginHandler(driver)
  page = 0
  val = pageHandler(driver, id, 1)

  while val:
   page += val
   val = pageHandler(driver, id, page + 1)

  if makepdf:
   helpers.makePDF(id, page, helpers.PNG)

 else:
  print("[NOTICE] Skipping issue %s - already exists." % id)

if __name__ == "__main__":
 parser = argparse.ArgumentParser()
 parser.add_argument("id", help="ID of the magazine to be downloaded. May be a URL.")

 id = parser.parse_args().id.split("/")[-1].split("#")[0]
 driver = webdriver.Firefox()

 magazineHandler(driver, id)
 driver.quit()