#!./bin/python3
import pdfkit
import weasyprint
import re
import os
import argparse


# CLI arguments
parser = argparse.ArgumentParser()
parser.add_argument('--backend', '-b', dest = 'backend', help = 'change the download backend; default: pdfkit', default = 'pdfkit', choices = ['pdfkit', 'weasyprint'])
args = parser.parse_args()


for filename in os.listdir("."):
    if not filename.endswith(".txt"): continue
    
    print("Examining: " + filename)
    
    try:
        os.mkdir(filename[:-4])
    except:
        pass

    file = open(filename, "r")
    links = file.readlines()
    for link in links:
        print("Downloading: " + link)
        name = os.path.join(filename[:-4], re.sub(r'(?u)[^-\w.]', '', link[5:]) + ".pdf")
        # name = re.sub(r'(?u)[^-\w.]', '', link[5:]) + ".pdf"
        # print(name)
        try:
            # weasyprint seems faster?
            if args.backend == 'pdfkit':
                pdfkit.from_url(link, name)
            else:
                pdf = weasyprint.HTML(link).write_pdf()
                open(name, 'wb').write(pdf)
        except:
            # Ignore exceptions
            # Probably not a good idea
            pass