very basic YouTube-to-RSS extractor

yt.py

#!/usr/bin/env python3

# pip install scrapetube

# for basic operation, use `python -m http.server --cgi`
# and access /cgi-bin/yt.py?c={CHANNEL_ID}

# Note that due to scrapetube limits, dates are fetched as eg "3 days ago"
# so the further in the past a video is, the less precise the date will be.

from email.utils import format_datetime
from datetime import datetime, timedelta
import cgi

import scrapetube

def determine_date(string: str, dt: datetime):
    "Return best guess at date of video release."
    assert len(string.split()) == 3
    num, unit, ago = string.split()
    assert ago == 'ago'
    unit = unit.removesuffix('s')
    num = int(num)
    
    UNITS = {
        'second': timedelta(seconds=1),
        'minute': timedelta(seconds=60),
        'hour': timedelta(seconds=3600),
        'day': timedelta(days=1),
        'week': timedelta(days=7),
        'month': timedelta(days=31),
        'year': timedelta(days=365),
    }
    assert unit in UNITS
    dt = dt or datetime.today()
    return dt - (num * UNITS[unit])

FETCH_LIMIT = 15
DAY_LIMIT = 100

def obtain(channel_id: str):
    dt = datetime.now()
    for v in scrapetube.get_channel(channel_id, limit=FETCH_LIMIT):
        dt = determine_date(v['publishedTimeText']['simpleText'], dt)
        yield dt, v

RSS = """
<?xml version="1.0" encoding="UTF-8" ?>
<rss version="2.0">
<channel>
  <title>Automatically-fetched Youtube Channel</title>
  <link>https://youtube.com/channel/{channel_id}</link>
  {items}
</channel>
</rss>
"""
ITEM = """
<item>
<title>{title}</title>
<link>https://youtube.com/watch?v={video_id}</link>
<description>{description}</description>
<pubDate>{date}</pubDate>
</item>"""

if __name__ == '__main__':
    print("Content-Type: application/rss+xml\n\n")
    data = cgi.FieldStorage()
    channel_id = data.getfirst('c')

    ITEMS = [
        ITEM.format(
            title=v['title']['runs'][0]['text'],
            description=f"<img src=\"{v['thumbnail']['thumbnails'][-1]['url']}\">",
            video_id=v['videoId'],
            date=format_datetime(dt)
            )
        for dt, v in obtain(channel_id)
    ]
    print(RSS.format(channel_id=channel_id, items='\n'.join(ITEMS)))