opml_to_md

#!/usr/bin/env python3
import sys
import xml.etree.ElementTree as ET


def extract_entries_from_xml(xml_content: str):
  """
  Wraps the content in a <root> tag so we can parse partial XML documents.
  Yields dicts with text, title, xmlUrl, htmlUrl when found.
  """
  wrapped = f"<root>\n{xml_content}\n</root>"

  try:
    root = ET.fromstring(wrapped)
  except ET.ParseError as e:
    print(f"Error: failed to parse XML-ish content: {e}", file=sys.stderr)
    sys.exit(1)

  for elem in root.iter():
    attrs = elem.attrib
    # We care about items that look like feed outline entries
    if "xmlUrl" in attrs and "htmlUrl" in attrs:
      text = attrs.get("text", "").strip()
      title = attrs.get("title", "").strip()
      xml_url = attrs.get("xmlUrl", "").strip()
      html_url = attrs.get("htmlUrl", "").strip()

      # Skip if core URLs are missing
      if not xml_url or not html_url:
        continue

      # Fallbacks if text/title missing
      if not text and title:
        text = title
      elif not title and text:
        title = text

      # If still nothing meaningful for label, skip
      if not text and not title:
        continue

      yield {
        "text": text,
        "title": title,
        "xmlUrl": xml_url,
        "htmlUrl": html_url,
      }


def main():
  if len(sys.argv) != 2:
    print(f"Usage: {sys.argv[0]} PATH_TO_XML_OR_FRAGMENT", file=sys.stderr)
    sys.exit(1)

  path = sys.argv[1]

  try:
    with open(path, "r", encoding="utf-8") as f:
      content = f.read()
  except FileNotFoundError:
    print(f"Error: file not found: {path}", file=sys.stderr)
    sys.exit(1)

  for entry in extract_entries_from_xml(content):
    text = entry["text"]
    title = entry["title"]
    html_url = entry["htmlUrl"]
    xml_url = entry["xmlUrl"]

    # If text and title are identical, don't duplicate them
    if text == title:
      label = text
    else:
      label = f"{text} - {title}"

    print(f"- [{label}]({html_url}) [RSS]({xml_url})")


if __name__ == "__main__":
  main()