#Import necessary libraries:
import pandas as pd
import requests
from bs4 import BeautifulSoup
import re

#Create a list that will hold the content of all five pages:
content_collect = []
#Connect to the main page:
response = requests.get("https://storiestogrowby.org/bedtime-stories-kids-free/")
#Store the content of the main page
content = response.content
#Add content to content_collect:
content_collect.append(content)
#Do the same for pages 2 through 5 with a loop
for i in range(2,6):
    #Change the number at the end, to connect to the next page
    response = requests.get("https://storiestogrowby.org/bedtime-stories-kids-free/page/{}".format(i))
    #Get the content of the current page
    content = response.content
    #Add the current content to the list 
    content_collect.append(content)
#Print the size of the content list
print("The size of content_collect is {}.".format(len(content_collect)))

#Create a list to hold the names of the stories
title = []
#Create a list to hold the short descriptions of the stories
body =[]
#Go through each of 5 pages and parse the html code:
for i in range(5):
    parser = BeautifulSoup(content_collect[i], 'html.parser')
    #For each page, go through all the stories
    for j in range(len(parser.find_all(class_='entry-title'))):
        #For each story, add the name to the list title
        title.append(parser.find_all(class_='entry-title')[j].text)
        #For each story, add the description to the list body
        body.append(parser.find_all(class_='entry-content')[j].text)
print("First five stories' titles are:\n\n {}.\n".format(title[:5]))
print("First five stories' descriptions are:\n\n {}.".format(body[:5]))

#Create a list that will hold cleaned description 
body_new = []
#Create a list that will hold cleaned title
title_new = []
#Regex to get rid of uncoherent text
pattern=r"[\n\\']|\xa0"
#Go through all stories:
for k in range(len(body)):
    #Delete all '\n's and '\xa0's in the descriptions of the stories 
    body_new.append(re.sub(pattern, '', body[k]))
    #Store only the names of the stories, get rid of the second part
    title_new.append(title[k].split('~')[0])
print("First five stories' titles are:\n\n {}.\n".format(title_new[:5]))
print("First five stories' descriptions are:\n\n {}.".format(body_new[:5]))

#Create a dictionary to hold 
#the titles and descriptions of the stories 
store_name_descr = {}
store_name_descr['Story Name'] = title_new 
store_name_descr['Short Description'] = body_new

#Create a DataFrame by using the dictionary
story_dataframe = pd.DataFrame(data=store_name_descr,  columns=['Story Name', 'Short Description'])
#Set the DataFrame so all text is left-aligned and index is hidden
pretty_story = story_dataframe.style.set_table_styles([dict(selector='th', props=[('text-align', 'left')])])
pretty_story.set_properties(**{'text-align': 'left'}).hide_index()
pretty_story