Torchons et serviettes

#!/usr/bin/env python

from bs4 import BeautifulSoup
from datetime import datetime
import glob
import os
import sys
from xml.etree.ElementTree import Element, SubElement, tostring
from xml.dom import minidom


PSEUDO = "fredg"
BASE_LINK = "https://galusik.fr/log"
FEED_LINK = BASE_LINK + "/feed.xml"

# blog posts
LOG = "/home/f/g/galusik.fr/log"
# fridayrockmetal posts
FRM = "/home/f/g/galusik.fr/frm"

# feeds
LOG_FEED = LOG + "/feed.xml"
FRM_FEED = FRM + "/feed.xml"


def prettify(elem):
    """Return a pretty-printed XML string for the Element."""
    rough_string = tostring(elem, 'utf-8')
    reparsed = minidom.parseString(rough_string)
    return reparsed.toprettyxml(indent="  ")

def create_atom_feed(blog_dir, feed_file):
    # Create the root element
    feed = Element('feed', xmlns='http://www.w3.org/2005/Atom')

    # Add feed metadata
    title = SubElement(feed, 'title')
    title.text = "@fredg's feed"

    link = SubElement(feed, 'link', href=FEED_LINK, rel='self')
    updated = SubElement(feed, 'updated')
    updated.text = datetime.now().strftime('%Y-%m-%dT%H:%M:%SZ')

    author = SubElement(feed, 'author')
    name = SubElement(author, 'name')
    name.text = PSEUDO

    # Get all HTML files in the blog directory, excluding index.html
    html_files = glob.glob(os.path.join(blog_dir, '*.html'))
    html_files = [f for f in html_files if not f.endswith('index.html')]

    # Sort files by date in descending order
    html_files.sort(key=lambda x: os.path.basename(x)[:10], reverse=True)

    # Add each entry to the feed
    for html_file in html_files:
        entry = SubElement(feed, 'entry')

        # Extract the title and date from the filename
        basename = os.path.basename(html_file)
        date_str, title_text = basename[:10], basename[11:-5]

        title = SubElement(entry, 'title')
        title.text = title_text

        link = SubElement(entry, 'link', href=f'{BASE_LINK}/{basename}')

        # Set the id to the file path
        id = SubElement(entry, 'id')
        id.text = html_file

        # Set the updated and published date
        published = SubElement(entry, 'published')
        published.text = f'{date_str}T00:00:00Z'

        updated = SubElement(entry, 'updated')
        updated.text = f'{date_str}T00:00:00Z'

        # Read and clean the content of the HTML file
        with open(html_file, 'r', encoding='utf-8') as file:
            soup = BeautifulSoup(file, 'html.parser')

            # Remove head, preamble, and topnav div tags
            if soup.head:
                soup.head.decompose()
            if soup.preamble:
                soup.preamble.decompose()
            topnav = soup.find('div', class_='topnav')
            if topnav:
                topnav.decompose()

            content = SubElement(entry, 'content', type='html')
            content.text = str(soup)

    # echo var
    print(f"Source Dir:{blog_dir}\nGenerated feed file: {feed_file}")
    # Write the feed to the file
    with open(feed_file, 'w', encoding='utf-8') as f:
        f.write(prettify(feed))

# Usage
def main():
    try:
        arg = sys.argv[1]
    except IndexError:
        raise SystemExit(f"Usage: {sys.argv[0]} log OR frm")
    # only update classical blog articles
    if arg == "log":
        create_atom_feed(LOG, LOG_FEED)
    # only update the fridayrockmetal feed
    elif arg == "frm":
        create_atom_feed(FRM, FRM_FEED)
    else:
        print('log or frm args are expected as only arg.\nAborted!\n')


if __name__ == "__main__":
    main()