aleenprd

from typing import Union

def fetch_el_if_available(soup: BeautifulSoup, element_type: str, class_type: str) -> Union[str, None]:
    """Returns element text if found, otherwise returns None.
    
    Args:
        soup (BeautifulSoup): a b24 soup.
        element_type (str): HTML type e.g. 'div'.
        class_type (str): the class of the desired element.
        

aleenprd

def get_ratings_page(episode_page: str, suffix: str="/ratings/?ref_=tt_ov_rt"):
    return ("/").join(episode_page.split("/")[:-1]) + suffix 

def get_reviews_page(episode_page: str, suffix: str="/reviews?ref_=tt_urv"):
    return ("/").join(episode_page.split("/")[:-1]) + suffix 

aleenprd

import re as regex

def get_episodes_links(link: str, driver_service) -> List[str]:
    """Retrieve links to episodes, from series' season main page.
    
    Args:
        link (str): link to season main page.
        driver_service (Service): a Chrome web driver.
        
    Returns:

aleenprd

# Data manipulation
import pandas as pd
import re as regex

# Scraping
import requests
from bs4 import BeautifulSoup
from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.chrome.service import Service

aleenprd

import requests
from bs4 import BeautifulSoup
from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.chrome.service import Service
from webdriver_manager.chrome import ChromeDriverManager

def make_soup_with_selenium(url: str, driver_service: Service) -> BeautifulSoup:
    """Return an HTML body from an URL.

aleenprd

from time import time

def timing(f: Callable) -> None:
    """Times a function runtime in minutes.

    Args:
        f (callable): a function/method.
    """
    def wrap(*args, **kw):
        ts = time()