filmtipset2imdb.py

import glob
import os
import re
import time

import pandas as pd
from selenium import webdriver
from selenium.common import NoSuchElementException
from selenium.webdriver import ActionChains
from selenium.webdriver.chrome.options import Options
from selenium.webdriver.common.by import By
from tqdm import tqdm
from user_agent import generate_user_agent

'''
Install:
pip install selenium pandas tqdm user_agent

Run:
IMDB_EMAIL=abc IMDB_PASSWORD=abc python filmtipset2imdb.py
'''


def element_exists(**kwargs):
    try:
        driver.find_element(**kwargs)
    except NoSuchElementException:
        return False
    return True


opts = Options()
opts.add_argument("user-agent=" + generate_user_agent())

driver = webdriver.Chrome(options=opts)

driver.get('https://imdb.com')

driver.find_element(by=By.XPATH, value='//*[text()="Sign In"]').click()
driver.find_element(by=By.XPATH, value='//*[text()="Sign in with IMDb"]').click()
driver.find_element(by=By.NAME, value='email').send_keys(os.environ['IMDB_EMAIL'])
driver.find_element(by=By.NAME, value='password').send_keys(os.environ['IMDB_PASSWORD'])
driver.find_element(by=By.ID, value='signInSubmit').click()
tqdm.pandas()

csv_path = max(glob.iglob('ft_betyg_*.csv'), key=os.path.getctime)

with open(csv_path, 'r') as f:
    lines = f.readlines()
    lines = [re.sub(r'(^[0-9-]{10}),', r'\1;', line) for line in lines]
with open(csv_path, 'w') as f:
    f.writelines(lines)

df = pd.read_csv(csv_path, sep=';', header=0)
t = tqdm(df.itertuples(), total=len(df))
skipped = 0
for row in t:
    url = f'https://www.imdb.com/title/tt{str(row.IMDB).zfill(7)}'
    t.set_description(url)
    t.set_postfix({'skipped': skipped})
    driver.get(url)

    time.sleep(1.5)

    if not element_exists(by=By.ID, value='iconContext-star-border'):
        skipped += 1
        continue

    rating = row.Score * 2 - 1
    try:
        driver.find_element(by=By.XPATH, value='//*[text()="Rate"]').click()
        element = driver.find_element(by=By.XPATH, value=f'//*[contains(@aria-label, "Rate {rating}")]')

        actions = ActionChains(driver)
        actions.move_to_element(element).click().perform()

        driver.find_element(by=By.XPATH, value='//button[./*[text()="Rate"]]').click()
    except Exception as e:
        with open('test.txt', 'a') as f:
            f.write(f'{url} {rating}\n')