Files
trumpsignal-backend/app/scrapers/trumpstruth.py
T

179 lines
6.2 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
"""
Trump Truth Social scraper — trumpstruth.org RSS fallback.
Why a second scraper?
CNN's archive (the primary source) sometimes lags 510 minutes behind real
posts. trumpstruth.org publishes an RSS feed of the same Truth Social account
that often updates faster. Running both in parallel and deduping by the
Truth Social `originalId` gives us "min(latency_a, latency_b)" — i.e. whoever
sees the post first wins.
Dedup strategy:
Both CNN and trumpstruth expose the underlying Truth Social post id. We
hash it the same way (md5(str(id))) so the second source is a no-op when
the first already inserted the row.
Source: https://www.trumpstruth.org/feed (RSS 2.0 with custom truth:originalId tag)
"""
import hashlib
import logging
import re
import xml.etree.ElementTree as ET
from datetime import datetime, timezone
from email.utils import parsedate_to_datetime
from typing import Optional
from app.scrapers.truth_social import (
NOT_MODIFIED,
_known_external_ids,
_process_entry,
dispatch_post,
)
logger = logging.getLogger(__name__)
FEED_URL = "https://www.trumpstruth.org/feed"
NS = {
"atom": "http://www.w3.org/2005/Atom",
"truth": "https://truthsocial.com/ns",
}
# Liveness — read by /api/health/deep
last_successful_poll_at: Optional[datetime] = None
last_poll_error: Optional[str] = None
# Conditional-GET validators (same scheme as truth_social.py — most polls
# come back 304 and skip the download + XML parse entirely).
_etag: Optional[str] = None
_last_modified: Optional[str] = None
async def _fetch_feed():
"""Fetch the RSS body. Returns str, NOT_MODIFIED (304), or None on error."""
global _etag, _last_modified
headers = {
"User-Agent": "Mozilla/5.0 (compatible; TrumpSignal/1.0)",
"Accept": "application/rss+xml, application/xml",
}
if _etag:
headers["If-None-Match"] = _etag
if _last_modified:
headers["If-Modified-Since"] = _last_modified
try:
from app.services.http_client import get_client
resp = await get_client().get(FEED_URL, headers=headers, timeout=20)
if resp.status_code == 304:
return NOT_MODIFIED
resp.raise_for_status()
_etag = resp.headers.get("etag")
_last_modified = resp.headers.get("last-modified")
return resp.text
except Exception as exc:
# Include type name — httpx often raises bare ConnectError/RemoteProtocolError
# with empty .args, which formats as just "Failed to fetch ..." with no body.
logger.warning("Failed to fetch trumpstruth.org feed: %s (%s)",
type(exc).__name__, exc)
return None
_HTML_TAG = re.compile(r"<[^>]+>")
def _to_cnn_shape(item: ET.Element) -> Optional[dict]:
"""Convert one <item> from the RSS feed into the dict shape the existing
`_process_entry` expects (CNN archive format).
Required output keys: id, created_at (ISO), content (HTML)."""
orig_id_el = item.find("truth:originalId", NS)
if orig_id_el is None or not (orig_id_el.text or "").strip():
return None
orig_id = orig_id_el.text.strip()
pub_el = item.find("pubDate")
if pub_el is None or not pub_el.text:
return None
try:
dt = parsedate_to_datetime(pub_el.text)
if dt.tzinfo is None:
dt = dt.replace(tzinfo=timezone.utc)
else:
dt = dt.astimezone(timezone.utc)
created_iso = dt.isoformat().replace("+00:00", "Z")
except Exception:
return None
desc_el = item.find("description")
content_html = (desc_el.text or "").strip() if desc_el is not None else ""
return {
"id": orig_id,
"created_at": created_iso,
"content": content_html,
}
async def poll_trumpstruth(db_session_factory) -> None:
"""One poll cycle. Called by APScheduler.
Idempotent: posts already inserted by the CNN scraper are skipped via the
`external_id` uniqueness check inside `_process_entry`.
"""
global last_successful_poll_at, last_poll_error
raw = await _fetch_feed()
if raw is NOT_MODIFIED:
# Feed unchanged — successful cycle, nothing to do.
last_successful_poll_at = datetime.now(timezone.utc)
last_poll_error = None
return
if raw is None:
last_poll_error = "fetch_feed returned None"
return
try:
root = ET.fromstring(raw)
except ET.ParseError as exc:
logger.warning("trumpstruth RSS parse error: %s", exc)
last_poll_error = f"parse: {exc}"
return
items = root.findall(".//item")
if not items:
last_poll_error = "feed had no <item>"
return
# Same as CNN: process the latest 50 only — keeps poll fast and avoids
# re-scanning the whole feed every 15s.
recent = items[:50]
entries = [e for e in (_to_cnn_shape(it) for it in recent) if e]
async with db_session_factory() as db:
try:
known_ids = await _known_external_ids(entries, db)
# Newest-first: commit + dispatch each new post immediately so an
# actionable post never queues behind older entries' AI analysis.
# dispatch_post is the shared fan-out (WS + Telegram + X + trade)
# from truth_social.py — delivery must not depend on which poller
# wins the race.
for entry in entries:
try:
post = await _process_entry(entry, db, known_ids)
if post:
await db.commit()
logger.info("[trumpstruth] beat CNN — new post id=%d",
post.id)
await dispatch_post(post, db)
except Exception as exc:
logger.error("trumpstruth: error on entry %s: %s",
entry.get("id"), exc)
# Capture any remaining writes (entry-filter stub rows).
await db.commit()
last_successful_poll_at = datetime.now(timezone.utc)
last_poll_error = None
except Exception as exc:
logger.error("trumpstruth transaction error: %s", exc)
last_poll_error = f"transaction: {exc}"
await db.rollback()