# If you found this on my website, hi! This is how I generate the RSS feed from my file system. # Please feel free to use this if you want, I won't bother with a real license but you may consider it MIT licensed code. from datetime import datetime, timezone from email.utils import format_datetime from html.parser import HTMLParser import os import re class Parser(HTMLParser): tag = None title = "" description = "" category = "" def handle_starttag(self, tag, attrs): if tag == "meta": if attrs[0][0] != "name": return self.tag = attrs[0][1] self.handle_data(attrs[1][1]) self.tag = tag def handle_endtag(self, tag): self.tag = None def handle_data(self, data): if self.tag == "title": self.title = data elif self.tag == "description": self.description = data elif self.tag == "keywords": self.category = data def rss_categories(category_string): return "\n ".join([f'{f}' for f in category_string.split(", ")]) def rss_processed_page_contents(page_string): main_contents = next(re.finditer('
\n([\s\S]*)
', page_string)).group(1) return main_contents def rss_contents(file): with open(file, "r") as file_contents: contents = file_contents.read() parser = Parser() parser.feed(contents) utc_dt = datetime.utcfromtimestamp(os.stat(file).st_birthtime).replace(tzinfo=timezone.utc) published_date = format_datetime(utc_dt, usegmt=True) return f""" {parser.title} {rss_categories(parser.category)} https://eleanorkolson.com/stuff/{file} https://eleanorkolson.com/stuff/{file} {published_date} """ def html_contents(file): with open(file, "r") as file_contents: parser = Parser() parser.feed(file_contents.read()) utc_dt = datetime.utcfromtimestamp(os.stat(file).st_birthtime) published_date = utc_dt.strftime("%Y-%m-%d") return f"""
  • {parser.title}: {parser.description} ({parser.category}) ({published_date})
    • """ def should_include(file): excludedFiles = [ "index.html", "generator.py", "feed.xml", "feed", ] return file not in excludedFiles and "_draft" not in file def generate_rss_items(): files = os.listdir(os.getcwd()) files.sort(key=lambda x: -1 * os.stat(x).st_birthtime) files = [rss_contents(f) for f in files if should_include(f)] return "".join(files) def generate_html_items(): files = os.listdir(os.getcwd()) files.sort(key=lambda x: -1 * os.stat(x).st_birthtime) files = [html_contents(f) for f in files if should_include(f)] return "".join(files) def generate_rss_feed(): published_date = format_datetime(datetime.now(timezone.utc), usegmt=True) return f""" Eleanor Olson https://eleanorkolson.com https://eleanorkolson.com/public/icon.png Eleanor Olson https://eleanorkolson.com {published_date} en-us © {datetime.now().year} Eleanor Olson Eleanor's personal blog about various things. Probably mostly transit. {generate_rss_items()} """ def generate_html_blog(): return f""" Eleanor Olson's Stuff!

    My Stuff! (and my Thoughts)

    I like working on Stuff and writing about my Thoughts. Here's some Stuff I've worked on and some Thoughts that I've had.
    If you'd like to follow my Thoughts and/or my Stuff, you may do so through the wonders of RSS. This page contains the contents of that feed in a more browser-friendly form.

    """ if __name__ == "__main__": feed = generate_rss_feed() with open("../feed", "w") as file: file.write(feed) blog = generate_html_blog() with open("index.html", "w") as file: file.write(blog)