books/genfeed.py

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
from datetime import datetime, timezone
from typing import Mapping, MutableMapping
import csv
import sys
import xmltodict

RSS_DATE_FORMAT = '%a, %d %b %Y %T %z'
ISO_DATE_FORMAT = '%Y-%m-%dT%H:%M:%S%z'


def parse_book(book: MutableMapping[str, str]) -> Mapping:
    item = {
        "title": book["title_sort"],
        "pubDate": datetime.strptime(book.pop("timestamp"), ISO_DATE_FORMAT)
                           .strftime(RSS_DATE_FORMAT),
        "guid": {
            "@isPermaLink": "false",
            "#text": book.pop("uuid"),
        },
        "description": book.pop("comments"),
        # The CSV's first character is a non-breaking space for some reason,
        # which breaks the author column
        "author": book.get("author_sort") or book["\ufeffauthor_sort"],
    }

    # Prepend metadata to the item description
    item["description"] = "<dl>{}</dl>{}".format(
        "".join(
            "<dt>{}</dt><dd>{}</dd>".format(
                key.replace('_sort', '').replace('_', ' ').replace('\ufeff', '').capitalize(),
                value,
            )
            for key, value in book.items()
            # Ignore empty columns
            if value
        ),
        item['description']
    )

    if book.get("tags"):
        item["category"] = [
            {
                "@domain": "https://git.tilde.town/dozens/books",
                "#text": tag
            }
            for tag in book["tags"].split(", ")
        ]

    return item


def main():
    sys.stdout.write(xmltodict.unparse({
        "rss": {
            "@version": "2.0",
            "@xmlns:atom": "http://www.w3.org/2005/Atom",
            "@xmlns:sy": "http://purl.org/rss/1.0/modules/syndication/",
            "channel": {
                "title": "dozens books",
                "description": "the cool calibre library of dozens",
                "link": "https://git.tilde.town/dozens/books",
                "atom:link": {
                    "@rel": "self",
                    "@type": "application/rss+xml",
                    # TODO: set the correct public URL of your feed!
                    "@href": "http://fuck",
                },
                "language": "en-US",
                "pubDate": datetime.now(timezone.utc)
                                   .strftime(RSS_DATE_FORMAT),
                "docs": "https://www.rssboard.org/rss-specification",
                "webMaster": "dozens@tilde.town (~dozens)",
                "generator": "Python " + ".".join(map(str, sys.version_info[:3])),
                # Update on the first of every month, at midnight UTC
                "sy:updatePeriod": "monthly",
                "sy:updateFrequency": "1",
                "sy:updateBase": "1971-01-01T00:00+00:00",
                # One month, roughly, for clients that do not support mod_syndication
                "ttl": 60 * 24 * 30,
                "item": list(map(parse_book, csv.DictReader(sys.stdin))),
            }
        }
    }, pretty=True, short_empty_elements=True))


if __name__ == '__main__':
    main()