#! Python

# Modded to grab EOC questions from CFA books

import requests, json, re, os

from bs4 import BeautifulSoup

username = input('Please type in your E-mail:')

password = input('Please type in your password:')

# Provide username and password

payload = {

'user[email]': username,

'user[password]': password

}

# Specifying year and level of books

Year = input('What year of books do you want?: ')

Level = input('What Level? (I,II,III): ')

# Creating a folder for the documents

startingLocation = os.path.abspath(os.curdir)

location = startingLocation + '\CFAEOC'

if not os.path.exists(location):

os.makedirs(location)

os.chdir(location)

print('ALL FILES WILL BE SAVED IN: %s' % location)

# Logging in and keeping a session open

with requests.Session() as s:

p = s.post('https://jigsaw.vitalsource.com/login', params=payload)

Library = p.text

parsed_Library = json.loads(Library)['books']

isbnList = []

# grabbing all the books to read

for book in parsed_Library:

title = book['title']

isbn = book['isbn']

if str(Year) in title and Level in title and 'CFA' in title:

isbnList.append({'title': title, 'isbn': int(isbn)})

# Going to each book's table of contents first

for book in isbnList:

bookUrl = 'https://jigsaw.vitalsource.com/books/' + str(book['isbn']) + '/toc'

tableOfContents = s.get(bookUrl).text

parsed_tableOfContents = json.loads(tableOfContents)

readingList = []

readingRegex = re.compile(r'Reading\s{1,10}\d{1,3}')

newLocation = startingLocation + '\CFAEOC' + r'\ ' + book['title']

if not os.path.exists(newLocation):

os.makedirs(newLocation)

os.chdir(newLocation)

# Grabbing the links to all of the readings

for reading in parsed_tableOfContents:

if readingRegex.search(reading['title']):

readingList.append(reading)

for subReading in readingList:

newLink = subReading['path']

newURL = 'https://jigsaw.vitalsource.com/books/' + str(book['isbn']) + '/epub' + str(newLink)

reading = s.get(newURL).text

soupReading = BeautifulSoup(reading, "html.parser")

for span_tag in soupReading.findAll('span'):

span_tag.replace_with('')

title = subReading['title']

#title = " ".join(re.findall("[a-zA-Z]+", title))

print('Now Scraping Reading: %s' % title)

# Grabbing the practice problems which are denoted by "chap(chapter)-ProbsAndSolutions"

eoc = soupReading.find("section", {'id': re.compile('chap\d{1,2}-ProbsAndSolutions')})

if eoc is not None:

readingFile = open('%s.html' % title, 'wb')

for image_tag in eoc.findAll('img'):

image_tag['src'] = 'https://jigsaw.vitalsource.com/books/' + str(book['isbn']) + '/epub/OEBPS/' + image_tag[

'src']

image_tag['width'] = "100%"

readingFile.write(eoc.encode('UTF-8'))

readingFile.close()

else:

continue

print('Book {} Done! Enjoy!'.format(book))

print('All books for year {0} and Level {1} done! Enjoy!'.format(Year, Level))