- Download csv from here https://docs.google.com/spreadsheets/d/1IFAzAM3EZgYPgTU11NLb_TaPvjCsxdIFRdhp2169PtQ/edit#gid=0

ytdl_utils.py

import pandas as pd
from urllib.parse import urlparse
df=pd.read_csv()
def url_matches_dataframe(url: str, df: pd.DataFrame) -> bool:
    # Parse the given URL to get the netloc and hostname
    parsed_url = urlparse(url)
    netloc = parsed_url.netloc
    hostname = parsed_url.hostname
    
    # Remove "www" from the netloc and hostname
    netloc = netloc.replace("www.", "")
    hostname = hostname.replace("www.", "")
    
    # Use the `isin` method to check if the given netloc or hostname is in the dataframe
    return df['netloc'].isin([netloc]).any() | df['hostname'].isin([hostname]).any()