Trump's truthsocial.com RSS feed generator

trump-rss.py

#!/usr/bin/env python3
"""
RSS feed generator for @realDonaldTrump's Truth Social posts.
"""

import sys
import io
import re
import html
from datetime import datetime
from email.utils import format_datetime
from xml.sax.saxutils import escape as xml_escape

import requests

ACCOUNT_ID = "107780257626128497"
API_URL = (
    f"https://truthsocial.com/api/v1/accounts/{ACCOUNT_ID}/statuses"
    "?exclude_replies=true&with_muted=true"
)

MAX_LEN = 420

sys.stdout = io.TextIOWrapper(sys.stdout.buffer, encoding="utf-8", newline="")


def strip_html(raw: str) -> str:
    text = raw
    text = text.replace("<br/>", " ").replace("<br />", " ").replace("<br>", " ")
    text = re.sub(r'</span><span class="ellipsis">', "", text)
    text = re.sub(r'</span><span class="invisible">', "", text)
    text = re.sub(r'</span><span class="">', "", text)
    text = text.replace("</span>", " ")
    text = re.sub(r"<[^>]*>", "", text)  # strip any remaining tags
    text = html.unescape(text)  # &amp; -> &, &gt; -> >, etc.
    text = re.sub(r"\s{2,}", " ", text).strip()
    return text


def truncate(text: str, limit: int = MAX_LEN) -> str:
    if len(text) > limit:
        return text[: limit - 1] + "…"
    return text


def format_pubdate(created_at: str) -> str:
    try:
        dt = datetime.fromisoformat(created_at.replace("Z", "+00:00"))
        return format_datetime(dt)
    except ValueError:
        return created_at


HEADERS = {
    "User-Agent": (
        "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 "
        "(KHTML, like Gecko) Chrome/126.0.0.0 Safari/537.36"
    ),
    "Accept": "application/json",
}


def fetch_statuses():
    resp = requests.get(API_URL, headers=HEADERS, timeout=15)
    resp.encoding = "utf-8"
    resp.raise_for_status()
    return resp.json()


def build_item(status: dict) -> str:
    created = format_pubdate(status.get("created_at", ""))
    url = status.get("url", "")

    content_html = status.get("content", "")
    if content_html and content_html != "<p></p>":
        content = strip_html(content_html.replace("*", "٭"))
    else:
        media = status.get("media_attachments") or [{}]
        content = media[0].get("url", "")

    content = truncate(content)

    title = xml_escape(content)
    description = xml_escape(content)
    link = xml_escape(url)

    return (
        "    <item>\n"
        f"      <title>{title}</title>\n"
        "      <dc:creator>@realDonaldTrump</dc:creator>\n"
        f"      <description>{description}</description>\n"
        f"      <pubDate>{created}</pubDate>\n"
        f"      <link>{link}</link>\n"
        "    </item>"
    )


def main():
    print("Content-type: application/rss+xml; charset=utf-8")
    print("Cache-control: public, max-age=4000")
    print("Access-Control-Allow-Origin: *")
    print()

    print('<?xml version="1.0" encoding="UTF-8"?>')
    print(
        '<rss version="2.0" '
        'xmlns:dc="http://purl.org/dc/elements/1.1/" '
        'xmlns:webfeeds="http://webfeeds.org/rss/1.0" '
        'xmlns:media="http://search.yahoo.com/mrss/">'
    )
    print("  <channel>")
    print("    <title>realDonaldTrump</title>")
    print("    <description>Public posts from @realDonaldTrump</description>")
    print("    <link>https://truthsocial.com/@realDonaldTrump</link>")
    print("    <language>en-us</language>")

    try:
        statuses = fetch_statuses()
    except (requests.RequestException, ValueError) as exc:
        sys.stderr.write(f"Failed to fetch/parse statuses: {exc}\n")
        statuses = []

    for status in statuses:
        print(build_item(status))

    print("  </channel>")
    print("</rss>")


if __name__ == "__main__":
    main()