pc_engine_download_parser

#!/usr/bin/env python

import re
import os

handler = open("index.html", "r")
data = handler.readlines()

expression = re.compile(r'".*/(pc-engine-fan-.*)/.*"')

final_links = []
for line in data:
    if not 'pc-engine-fan' in line:
        continue

    links = line.split("<li>")

    for link in links:
        matches = expression.findall(link)
        if matches:
            final_links.append(matches[0])

print("#!/usr/bin/env bash")

for idx, link in enumerate(final_links):
    parts = link.split("-")

    command = f"wget https://archive.org/download/{link}/{parts[0].upper()}%20{parts[1].capitalize()}%20{parts[2].capitalize()}%20-%20{parts[3].capitalize()}%20{parts[4]}.pdf"
    print(command)