In terminal do 

python3 -m ensurepip 
curl https://bootstrap.pypa.io/get-pip.py -o get-pip.py 
pip install requests
pip install html5lib
pip install bs4 
pip install texttable 

	## Writing to files. 
from pathlib import Path 
p = Path("new.txt") 
p.write_text("test it out now") 
p.read_text() 

	## Better to use open() 
newfile = open("new.txt") 
newfile.read() 
newfile.readlines() ## One string for each new line. 
newfile = open("new.txt","a") ## a for append mode. w for write mode for overwriting the file. 
newfile.write("\nthis is the 2nd line.\n") 
newfile.close() 
newfile = open("new.txt") 
print(newfile.readlines()) 
newfile.close() 

	BeautifulSoup is a Python package useful to parse HTML and XML documents. 
	Pandas is a Python package useful for data manipulation and analysis. 

import requests
from bs4 import BeautifulSoup
from pathlib import Path
import numpy

url = 'https://www.worldometers.info/coronavirus/countries-where-coronavirus-has-spread/'
  
page = requests.get(url)
soup = BeautifulSoup(page.text, 'html.parser')
 
data = []
 
	# soup.find_all('td') will scrape every element in the url's table

data_iterator = iter(soup.find_all('td'))
 
	# data_iterator is the iterator of the table
	# This loop will keep repeating till there is no
	# data available in the iterator

while True:
    try:
        country = next(data_iterator).text
        confirmed = next(data_iterator).text
        deaths = next(data_iterator).text
        continent = next(data_iterator).text
 
        # remove the commas and convert to int
        data.append((
            country,
            int(confirmed.replace(',', '')),
            int(deaths.replace(',', '')),
            continent
        ))
     
    	# StopIteration error is raised when there 
    	# are no more elements left to iterate through
    except StopIteration:
        break
 
	# Sort the data by the number of confirmed cases
data.sort(key = lambda row: row[1], reverse = True)

	# create texttable object
import texttable as tt
table = tt.Texttable()
 
	# Add an empty row at the beginning for the headers
table.add_rows([(None, None, None, None)] + data)
 
	# 'l' denotes left, 'c' denotes center,'r' denotes right
table.set_cols_align(('c', 'c', 'c', 'c')) 
table.header((' Country ', ' Number of cases ', ' Deaths ', ' Continent '))
 
        ## Print it in python. 
print(table.draw())

        ## Save to a file called new.txt.

content = str(numpy.array(data))
out = open("new.txt","w")
out.write(content)
out.close() 









# importing modules
import requests
from bs4 import BeautifulSoup
from pathlib import Path
import numpy

url = 'https://en.wikipedia.org/wiki/List_of_best-selling_books'

# get URL html
page = requests.get(url)
soup = BeautifulSoup(page.text, 'html.parser')
 
data = []
 
# soup.find_all('td') will scrape every
# element in the url's table
data_iterator = iter(soup.find_all('td'))
 
b = []
# data_iterator is the iterator of the table
# This loop will keep repeating till there is no
# data available in the iterator

for i in range(50):
    for j in range(10):
        b.append(str(next(data_iterator).text))

content = str(numpy.array(b))
out = open("new.txt","w")
for i in range(60):
    out.write(b[i]+"\n")
out.close()

out = open("condensed.txt","w")
out.write(content)
out.close()