Some functions to simplify CF scraping

scrape_ac.py

from seleniumrequests import Chrome
from selenium.webdriver.chrome.options import Options
from selenium.webdriver.common.keys import Keys
import selenium.webdriver.support.ui as ui
import getpass
import time

# initiate headless browser driver
# should be run once before any other function
def init():
    global driver
    opt = Options()
    opt.add_argument('--headless')
    driver = Chrome(options=opt)
    driver.get('https://codeforces.com')

def check_login():
    login_url = 'https://codeforces.com/enter'
    driver.get(login_url)
    if driver.current_url != login_url:
        print('logged in as ' + driver.current_url.split('/')[-1])
        return True
    else:
        print('logged out')
        return False

def try_login(handle, password):
    login_url = 'https://codeforces.com/enter'
    driver.get(login_url)
    if driver.current_url == login_url:
        driver.find_element('id', 'handleOrEmail').send_keys(handle)
        driver.find_element('id', 'password').send_keys(password + Keys.ENTER)
        # successful login redirects to a different page, unsuccessful brings up an error message
        wait = ui.WebDriverWait(driver, 10)
        wait.until(lambda driver: 
                   driver.current_url != login_url or 
                   driver.find_element('css selector', '.error.for__password'))
        if driver.current_url != login_url:
            print('successfully logged in as ' + handle)
        else:
            print('unsuccessful login attempt')
    else: # redirects to https://codeforces.com/profile
        print('already logged in')

def request_login():
    try_login(input('handle: '), getpass.getpass('password: '))

def logout():
    if check_login():
        print('logging out...')
        driver.find_element('link text', 'Logout').click()
        check_login()

def submitSource(sId):
    url = 'https://codeforces.com/data/submitSource'
    csrf = driver.execute_script("return Codeforces.getCsrfToken()")
    data = {'submissionId':str(sId),'csrf_token':csrf}
    return driver.request('POST', url, data=data)

# wrapper for HTTP requests to Codeforces API
def cf_get(method, params):
    return driver.request('get', 'https://codeforces.com/api/' + method, params=params)

# list of all submissions on which this user got AC
def ac_subs(user):
    r = cf_get('user.status', {'handle':user})
    return [(it.get('contestId', None), it['id']) for it in r.json()['result'] if it['verdict'] == 'OK']

# Dictionary (contestId, submissionId) -> source code
def scrape_ac(user):
    acs = ac_subs(user)
    if not check_login():
        print('it is recommended to be logged in to get restricted submissions')
        print('you can skip authentication process if you don\'t feel like it')
        request_login()
    res = dict()
    for cId, sId in acs:
        sS = submitSource(sId)
        if sS:
            res[(cId, sId)] = sS.json()['source']
        time.sleep(0.3) # recommended wait so that submitSource keeps working
    return res