import libraries

# web scraping libraries
from urllib.request import urlopen # open urls
from bs4 import BeautifulSoup # extract data from html files

# ds libraries
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
import datetime as dt
%matplotlib inline
sns.set_theme(style="whitegrid")
plt.rcParams["figure.figsize"] = (12, 8) # default plot size

# word cloud
from wordcloud import WordCloud, STOPWORDS

# interactive tables
from google.colab import data_table

# regex
import re

url = "https://www.learndatasci.com/free-data-science-books/"

# get html of page
html = urlopen(url)

# create bs object
soup = BeautifulSoup(html, 'lxml') # using lxml parser