Files
trumpsignal-backend/app/scrapers/truth_social.py
T
2026-04-21 19:33:24 +08:00

207 lines
6.9 KiB
Python

"""
Trump Truth Social scraper — CNN public archive
Source: https://ix.cnn.io/data/truth-social/truth_archive.json
Updated every ~5 minutes by CNN.
"""
import hashlib
import html
import logging
import re
from datetime import datetime, timezone
from typing import Optional
import httpx
from sqlalchemy import select
from sqlalchemy.ext.asyncio import AsyncSession
from app.models import Post, iso_utc
from app.services.analysis import analyze_post
from app.services.price_store import price_store
from app.ws.manager import manager
logger = logging.getLogger(__name__)
ARCHIVE_URL = "https://ix.cnn.io/data/truth-social/truth_archive.json"
def _strip_html(text: str) -> str:
text = re.sub(r"<[^>]+>", " ", text)
text = html.unescape(text)
return re.sub(r"\s+", " ", text).strip()
def _parse_dt(iso: str) -> datetime:
try:
return datetime.fromisoformat(iso.replace("Z", "+00:00")).replace(tzinfo=None)
except Exception:
return datetime.now(timezone.utc).replace(tzinfo=None)
async def _fetch_archive() -> Optional[list]:
headers = {
"User-Agent": "Mozilla/5.0 (compatible; TrumpSignal/1.0)",
"Accept": "application/json",
}
try:
async with httpx.AsyncClient(timeout=30, follow_redirects=True) as client:
resp = await client.get(ARCHIVE_URL, headers=headers)
resp.raise_for_status()
return resp.json()
except Exception as exc:
logger.error("Failed to fetch CNN archive: %s", exc)
return None
async def _process_entry(entry: dict, db: AsyncSession) -> Optional[Post]:
external_id = hashlib.md5(str(entry["id"]).encode()).hexdigest()
result = await db.execute(select(Post).where(Post.external_id == external_id))
if result.scalar_one_or_none():
return None
text = _strip_html(entry.get("content") or "").strip()
if not text:
return None
published_at = _parse_dt(entry.get("created_at", ""))
analysis = await analyze_post(text)
asset = analysis["asset"]
price_impact_m5 = price_impact_m15 = price_impact_m1h = price_at_post = None
if asset and analysis["relevant"]:
price_at_post = price_store.get_price_at(asset, published_at)
price_impact_m5 = price_store.get_pct_change(asset, published_at, 5)
price_impact_m15 = price_store.get_pct_change(asset, published_at, 15)
price_impact_m1h = price_store.get_pct_change(asset, published_at, 60)
post = Post(
external_id=external_id,
text=text,
source="truth",
published_at=published_at,
sentiment=analysis["sentiment"],
signal=analysis.get("signal"),
ai_confidence=analysis["confidence"],
ai_reasoning=analysis.get("reasoning"),
prefilter_reason=analysis.get("prefilter_reason"),
analysis_version=analysis.get("analysis_version"),
relevant=analysis["relevant"],
price_impact_asset=asset if analysis["relevant"] else None,
price_impact_m5=price_impact_m5,
price_impact_m15=price_impact_m15,
price_impact_m1h=price_impact_m1h,
price_at_post=price_at_post,
)
db.add(post)
await db.flush()
return post
def _post_to_ws_payload(post: Post) -> dict:
price_impact = None
if post.price_impact_asset and post.price_at_post is not None:
price_impact = {
"asset": post.price_impact_asset,
"m5": post.price_impact_m5 or 0.0,
"m15": post.price_impact_m15 or 0.0,
"m1h": post.price_impact_m1h or 0.0,
"price_at_post": post.price_at_post,
}
return {
"type": "new_post",
"post": {
"id": post.id,
"text": post.text,
"source": post.source,
"published_at": iso_utc(post.published_at),
"sentiment": post.sentiment,
"signal": post.signal,
"ai_confidence": post.ai_confidence,
"ai_reasoning": post.ai_reasoning,
"relevant": post.relevant,
"price_impact": price_impact,
},
}
async def poll_truth_social(db_session_factory) -> None:
logger.info("Polling CNN Truth Social archive...")
entries = await _fetch_archive()
if not entries:
return
# Only process the latest 50 entries each poll (archive has 30k+ posts)
recent = entries[:50]
logger.info("Checking %d recent entries...", len(recent))
async with db_session_factory() as db:
try:
new_posts = []
for entry in recent:
try:
post = await _process_entry(entry, db)
if post:
new_posts.append(post)
except Exception as exc:
logger.error("Error processing entry %s: %s", entry.get("id"), exc)
if new_posts:
await db.commit()
for post in new_posts:
await manager.broadcast(_post_to_ws_payload(post))
logger.info("Saved new post id=%d: %s", post.id, post.text[:60])
try:
from app.services.bot_engine import process_post
await process_post(post, db)
except Exception as exc:
logger.error("process_post failed for post %d: %s", post.id, exc)
else:
logger.info("No new posts found.")
except Exception as exc:
logger.error("Transaction error: %s", exc)
await db.rollback()
async def backfill_history(db_session_factory, limit: int = 500) -> None:
"""One-time backfill of historical posts (no Claude analysis, no price impact)."""
logger.info("Starting historical backfill (limit=%d)...", limit)
entries = await _fetch_archive()
if not entries:
logger.error("Backfill failed: could not fetch archive")
return
to_process = entries[:limit]
saved = 0
async with db_session_factory() as db:
try:
for entry in to_process:
external_id = hashlib.md5(str(entry["id"]).encode()).hexdigest()
result = await db.execute(select(Post).where(Post.external_id == external_id))
if result.scalar_one_or_none():
continue
text = _strip_html(entry.get("content") or "").strip()
if not text:
continue
post = Post(
external_id=external_id,
text=text,
source="truth",
published_at=_parse_dt(entry.get("created_at", "")),
sentiment="neutral",
ai_confidence=0,
relevant=False,
)
db.add(post)
saved += 1
await db.commit()
logger.info("Backfill complete: saved %d posts", saved)
except Exception as exc:
logger.error("Backfill error: %s", exc)
await db.rollback()