Turn aws service faqs to pdf books. Useful for Solution Architect or other AWS certification exam.

aws_faqs.py

#!/usr/bin/env python3
import requests
import sys
import json
from bs4 import BeautifulSoup
import pdfkit
import os
from PyPDF2 import PdfFileMerger

DOC_URL_BASE='https://aws.amazon.com/'
faq_dir = './pdf_faqs/'

# this categories can be found from https://aws.amazon.com/products/ href tags
intresting_categories = [
    (1, 'analytics'),
    (2, 'app_integration'),
    (7,'compute_containers'),
    (9, 'database'),
    (19, 'networking_content_delivery'),
    (17, 'migration'),
    (22, 'security'),
    (23, 'serverless_computing'),
    (24, 'storage'),
    (14, 'management_tools')
]

blacklist = 'lightsail serverlessrepo timestream cloudendure-migration'

def create_pdfs_for_allservices(chknsoup):
    os.mkdir(faq_dir)
    for i, cat_name in intresting_categories:
        print('==========:'+ cat_name)
        dir_name = faq_dir + cat_name
        os.mkdir(dir_name)

        for a in soup.find_all('a', href=True):
            regex_str='?c='+str(i)+'&pt='
            if regex_str in a['href']:
                service = a['href'].split('/')[1]
                if service in blacklist:
                    pass
                else:
                    try:
                        pdfkit.from_url(DOC_URL_BASE + service + '/faqs', dir_name + '/' + service + '.pdf')
                    except:
                        pass


def merge_pdfs(faq_dir):
    categories = os.listdir(faq_dir)
    for category in categories:
        merger = PdfFileMerger()
        for pdf_file in os.listdir(faq_dir + category):
            merger.append(faq_dir + category + '/' + pdf_file)
        merger.write(faq_dir + category + '.pdf')
        merger.close()

if __name__ == "__main__":
    r  = requests.get(DOC_URL_BASE + 'products/')
    data = r.text
    soup = BeautifulSoup(data, features="html.parser")
    create_pdfs_for_allservices(soup)
    merge_pdfs(faq_dir)