dpbac

# importing packages

import requests
from bs4 import BeautifulSoup
import pandas as pd

def parse_website(url):
    """ 
    Parse content of a website
    

dpbac

def filter_hyperlinks(urls):
    """ Filter our hyperlinks that are not from lyrics taking into account the structure
    of songteksten.nl website """
    
    list_links_lyrics_songteksten_net = []

    for url in urls:
        list_links_lyrics_songteksten_net.extend(retrieve_hyperlinks(url))
    
    # removing possible duplicates

dpbac

import requests
from bs4 import BeautifulSoup

def retrieve_hyperlinks(main_url):
    """ Extract all hyperlinks in 'main_url' and return a list with these hyperlinks """
    
    # Packages the request, send the request and catch the response: r

    r = requests.get(main_url)

dpbac

import requests
from bs4 import BeautifulSoup


def retrieve_hyperlinks(main_url):
    """ Extract all hyperlinks in 'main_url' and return a list with these hyperlinks """
    
    # Packages the request, send the request and catch the response: r

    r = requests.get(main_url)

dpbac

#Uploading the Dataset 
from google.colab import files
uploaded = files.upload()

#Save uploaded file on the Virtual Machine's 
#Thanks to user3800642 from StackOverflow 

with open("breast_cancer.csv", 'w') as f:
    f.write(uploaded[uploaded.keys()[0]])