blankx.gitlab.io/gensbbsrss.py

import os
from datetime import datetime
from xml.etree import ElementTree
from bs4 import BeautifulSoup

with open('index.html') as file:
    soup = BeautifulSoup(file.read())
    sbbsbase = soup.find('link', rel='canonical')['href']

feed = ElementTree.Element('rss', version='2.0')
channel = ElementTree.SubElement(feed, 'channel')
title = ElementTree.SubElement(channel, 'title')
title.text = 'software being broken showcase'
link = ElementTree.SubElement(channel, 'link')
link.text = sbbsbase
description = ElementTree.SubElement(channel, 'description')
description.text = 'just a showcase of software being broken :)'
language = ElementTree.SubElement(channel, 'language')
language.text = 'en-us'
def parse_file(i):
    with open(i) as file:
        soup = BeautifulSoup(file.read())
    item = ElementTree.Element('item')
    title = ElementTree.SubElement(item, 'title')
    title.text = soup.h1.string
    link = ElementTree.SubElement(item, 'link')
    link.text = soup.find('link', rel='canonical')['href']
    guid = ElementTree.SubElement(item, 'guid')
    guid.text = f'sbbs/{os.path.splitext(i)[0]}'
    description = ElementTree.SubElement(item, 'description')
    description.text = str(soup.find('div', class_='content'))
    return (datetime.fromisoformat(soup.find('meta', {'name': 'created'})['content']), item)
for date, i in sorted(map(parse_file, filter(lambda i: i not in ('index.html', 'index.xml'), os.listdir('.'))), reverse=True, key=lambda i: i[0]):
    # http://johnbokma.com/blog/2019/10/09/rfc-822-and-rfc-3339-dates-in-python.html
    ctime = date.ctime()
    pubdate = ElementTree.SubElement(i, 'pubDate')
    pubdate.text = f"{ctime[0:3]}, {date.day:02d} {ctime[4:7]} {date.strftime(' %Y %H:%M:%S %z')}"
    channel.append(i)
ElementTree.ElementTree(feed).write('index.xml', 'utf-8')