yt_dearrow_shorts_removal_rss

#!/usr/bin/env python3
# SPDX-License-Identifier: Unlicense
import requests
import xml.etree.ElementTree as ET
import sys


def is_short(video_id) -> bool:
    """Return whether this is a YouTube Short"""
    return requests.head(f"https://www.youtube.com/shorts/{video_id}").status_code == 200

    # If you also want to remove other short videos, use this instead (slower):
    # import yt_dlp
    # with yt_dlp.YoutubeDL() as ydl:
    #     info = ydl.extract_info(f'https://www.youtube.com/watch?v={video_id}', download=False)
    #     print(info["duration_string"])  # human-friendly
    #     return info["duration"] < 60


def fetch_dearrow_title(video_id) -> str | None:
    """Get best non-clickbaity title from DeArrow's community database"""

    # https://wiki.sponsor.ajay.app/w/API_Docs/DeArrow
    r = requests.get(f"https://dearrow.minibomba.pro/sbserver/api/branding/?videoID={video_id}").json()
    if not r["titles"]:
        return None

    best = r["titles"][0]
    if best["locked"] or best["votes"] >= 0:
        return best["title"]
    else:
        return None


def main():
    tree = ET.parse(sys.stdin)
    root = tree.getroot()

    namespaces = {
        "yt": "http://www.youtube.com/xml/schemas/2015",
        "media": "http://search.yahoo.com/mrss/",
        "": "http://www.w3.org/2005/Atom",
    }

    for k, v in namespaces.items():
        ET.register_namespace(k, v)

    for entry in root.findall("entry", namespaces):
        video_id = entry.find("yt:videoId", namespaces).text
        if is_short(video_id):
            root.remove(entry)
            continue
        if new_title := fetch_dearrow_title(video_id):
            title_element = entry.find("title", namespaces)
            if title_element is not None:
                title_element.text = f"{new_title}  ◎  {title_element.text}"

    sys.stdout.buffer.write(ET.tostring(root, encoding="utf-8"))


main()