#!/usr/bin/env python3

import os
import re
from argparse import ArgumentParser

# PDF conversion backends
import pdfkit
import weasyprint


# CLI arguments
parser = ArgumentParser()
parser.add_argument('--backend', '-b', help = 'change the download backend', default = 'pdfkit', choices = ['pdfkit', 'weasyprint'])
parser.add_argument('--force', '-f', help = 'force download all links', action='store_false')
args = parser.parse_args()


for category in os.listdir('Links'):
    print('Examining: ' + category)
    os.makedirs(category, exist_ok=True)
    
    section = ''
    for link in open(os.path.join('Links', category), 'r').readlines():
        if link[0:2] == '# ':
            section = link[2:-1]
        if link[0] == '#' or link[0] == '\n':
            continue
        
        name = os.path.join(category, section + ' - ' + re.sub(r'(?u)[^-\w.]', '', link[5:]) + '.pdf')
        if not os.path.exists(name) or args.force:
            print('Downloading: ' + link[:-1])
            print('Destination: ' + name)
            
            # Time to print!
            try:
                if args.backend == 'pdfkit':
                    pdfkit.from_url(link, name)
                else:
                    pdf = weasyprint.HTML(link).write_pdf()
                    open(name, 'wb').write(pdf)
            except:
                print('Error when printing 😱')