Files
workspace/skills/deep-scraper/scripts/triage-posts.py
Case 5ce3e812a1 Feed Hunter portal: dark theme dashboard on localhost:8888
- Web portal with 5 views: dashboard, feed, investigations, sims, status
- Enhanced triage with 40+ claim patterns
- Position monitor script
- Pipeline report generator
- Systemd service for portal
2026-02-08 00:06:24 -06:00

341 lines
13 KiB
Python

#!/usr/bin/env python3
"""
Triage scraped X posts — identify posts with verifiable claims and links.
Extracts structured "investigation tasks" for agent follow-up.
Usage:
python3 triage-posts.py <posts.json> [--output triage.json]
"""
import argparse
import json
import re
import os
from datetime import datetime, timezone
# Patterns that suggest a verifiable claim
CLAIM_PATTERNS = [
# Specific dollar amounts and profits
(r'\$(\d{1,3}(?:,\d{3})*(?:\.\d{2})?)\s*(profit|gained|made|earned|up|return)', 'dollar_profit'),
(r'made\s+\$(\d{1,3}(?:,\d{3})*(?:\.\d{2})?)', 'dollar_profit'),
(r'(\d{1,3}(?:,\d{3})*)\s*(k|K)\s*(profit|gained|made|earned|up|return)', 'k_profit'),
(r'(\d+(?:\.\d+)?)\s*(million|M)\s+(profit|made|earned|up)', 'million_profit'),
# Performance claims
(r'(\d+[\d.]*)\s*%\s*(win|success|profit|return|accuracy|hit rate)', 'performance_claim'),
(r'wins?\s+(\d+[\d.]*)\s*%', 'performance_claim'),
(r'(\d+[\d.]*)\s*%\s+of the time', 'performance_claim'),
(r'(\d+[\d.]*)x\s+(return|profit|gain|returns)', 'multiplier_claim'),
(r'(\d+[\d.]*)\s*x\s+in\s+(\d+)\s+(day|week|month|year)s?', 'timeframe_multiplier'),
# Trading track record claims
(r'(\d+)\s+(win|profitable)\s+(trade|bet|position)s?\s+in\s+a\s+row', 'streak_claim'),
(r'(\d+)\s+out\s+of\s+(\d+)\s+(trade|bet|call)s?\s+(right|correct|profitable)', 'ratio_claim'),
(r'(\d+[\d.]*)\s*%\s+accuracy\s+(this|last)\s+(week|month|year)', 'accuracy_claim'),
(r'portfolio\s+up\s+(\d+[\d.]*)\s*%', 'portfolio_performance'),
# Copy/follow trading
(r'copy(ing|cat)?\s+(trader|user|bet|position|strat)', 'copy_trading'),
(r'follow\s+(this|my|their)\s+(trade|bet|position|strat)', 'copy_trading'),
(r'mirror(ing)?\s+(trade|bet|position)', 'copy_trading'),
(r'best\s+(trader|performer)\s+(on|in)\s+\w+', 'top_trader'),
# Crypto/DeFi specific claims
(r'(\d+[\d.]*)\s+(eth|btc|sol|bnb|ada|dot)\s+(profit|gained|made|up)', 'crypto_profit'),
(r'yield\s+farming\s+.{0,30}\s*(\d+[\d.]*)\s*%', 'yield_claim'),
(r'staking\s+.{0,30}\s*(\d+[\d.]*)\s*%\s*(apy|apr)', 'staking_yield'),
(r'liquidity\s+provider?\s+.{0,30}\s*(\d+[\d.]*)\s*%', 'lp_yield'),
(r'(\d+[\d.]*)x\s+(leverage|margin)', 'leverage_claim'),
# NFT claims
(r'(flip|sold|bought)\s+.{0,30}\s+for\s+(\d+[\d.]*)\s+(eth|sol)', 'nft_flip'),
(r'(\d+[\d.]*)\s+(eth|sol)\s+floor', 'nft_floor'),
(r'mint\s+(price|cost)\s+(\d+[\d.]*)', 'mint_price'),
# Arbitrage/spread
(r'(arb|arbitrage|spread|mismatch|mispriced)', 'arbitrage_opp'),
(r'risk[\s-]?free', 'arbitrage_opp'),
(r'guaranteed\s+(profit|return|money)', 'arbitrage_opp'),
(r'(\d+[\d.]*)\s*%\s+guaranteed', 'guaranteed_return'),
# Sports betting / Prediction markets
(r'(polymarket|kalshi|manifold|prediction\s+market)', 'prediction_market'),
(r'(odds|probability)\s+.{0,20}\s*(\d+[\d.]*)\s*%', 'odds_claim'),
(r'(yes|no)\s+shares?\s+at\s+(\d+)', 'shares_price'),
(r'betting\s+(\d+[\d.]*)\s*%\s+on', 'betting_confidence'),
(r'(\d+[\d.]*)\s*%\s+chance\s+(of|that)', 'probability_estimate'),
# Price/target claims
(r'(target|pt|price target)\s*[:\s]+\$?\s*(\d[\d,.]*)', 'price_target'),
(r'(entry|buy)\s*(at|zone|point)\s*[:\s]+\$?\s*(\d[\d,.]*)', 'entry_point'),
(r'next\s+(resistance|support)\s+at\s+\$?(\d[\d,.]*)', 'technical_level'),
(r'going\s+to\s+\$?(\d[\d,.]*)', 'price_prediction'),
# Airdrop/free money
(r'(airdrop|free\s+money|free\s+tokens?|claiming)', 'airdrop'),
(r'(step\s+\d|how\s+to\s+(get|claim|earn))', 'howto'),
(r'eligible\s+for\s+(\d+[\d.]*)\s+tokens?', 'airdrop_amount'),
# Signal/alert claims
(r'(signal|alert|call)\s+.{0,30}\s*(\d+[\d.]*)\s*%\s+(gain|profit)', 'signal_performance'),
(r'last\s+(\d+)\s+(signal|call|alert)s?\s+all\s+(profit|green|won)', 'signal_streak'),
(r'(\d+[\d.]*)\s*%\s+win\s+rate\s+on\s+(signal|call)s?', 'signal_winrate'),
# Time-sensitive claims
(r'(today|yesterday|this\s+week)\s+.{0,30}\s*(\d+[\d.]*)\s*%\s+(up|gain|profit)', 'recent_performance'),
(r'(\d+[\d.]*)\s*%\s+in\s+(\d+)\s+(hour|day|week)s?', 'timeframe_performance'),
(r'last\s+(\d+)\s+(day|week|month)s?\s+.{0,30}\s*(\d+[\d.]*)\s*%', 'period_performance'),
# User/account references with performance
(r'@\w+.*?(portfolio|track\s*record|history|performance)', 'user_reference'),
(r'(this\s+(guy|trader|user|person|account))\s+.{0,30}(profit|win|return|made)', 'user_reference'),
(r'trader\s+with\s+(\d+[\d.]*)\s*%\s+(accuracy|win\s+rate)', 'trader_stats'),
(r'(\d+[\d.]*)\s*(million|M|k|K)\s+follower\s+trader', 'influencer_trader'),
# Strategy claims
(r'(strategy|method|system)\s+that\s+.{0,30}(\d+[\d.]*)\s*%', 'strategy_claim'),
(r'using\s+.{0,30}\s+(\d+[\d.]*)\s*%\s+(success|win)', 'method_performance'),
(r'secret\s+(strategy|method|formula)', 'secret_method'),
# Options/derivatives
(r'(call|put)\s+option\s+.{0,30}\s*(\d+[\d.]*)\s*%', 'options_claim'),
(r'(\d+[\d.]*)\s*%\s+(otm|itm|out\s+of\s+the\s+money|in\s+the\s+money)', 'options_probability'),
(r'delta\s+(\d+[\d.]*)', 'options_delta'),
# Course/education monetization
(r'course\s+that\s+.{0,30}(\d+[\d.]*)\s*(k|K|dollar)', 'course_earning'),
(r'teaching\s+.{0,30}\s+(\d+[\d.]*)\s*(k|K)\s+student', 'teaching_claim'),
(r'(\d+[\d.]*)\s*%\s+of\s+students\s+(profit|succeed)', 'student_success'),
]
# Link domains that are investigatable
INVESTIGATABLE_DOMAINS = {
'polymarket.com': 'prediction_market',
'kalshi.com': 'prediction_market',
'manifold.markets': 'prediction_market',
'dexscreener.com': 'token_chart',
'dextools.io': 'token_chart',
'birdeye.so': 'token_chart',
'coingecko.com': 'token_info',
'coinmarketcap.com': 'token_info',
'tradingview.com': 'chart',
'etherscan.io': 'blockchain',
'solscan.io': 'blockchain',
'basescan.org': 'blockchain',
'github.com': 'code_repo',
'docs.google.com': 'document',
'notion.so': 'document',
'medium.com': 'article',
'substack.com': 'article',
'youtube.com': 'video',
'youtu.be': 'video',
}
def extract_claims(text):
"""Extract verifiable claims from post text."""
claims = []
for pattern, claim_type in CLAIM_PATTERNS:
matches = re.finditer(pattern, text, re.IGNORECASE)
for m in matches:
claims.append({
'type': claim_type,
'match': m.group(0),
'span': [m.start(), m.end()],
})
return claims
def classify_links(links):
"""Classify links by investigatable domain."""
classified = []
for link in links:
url = link.get('url', '')
link_type = 'unknown'
for domain, dtype in INVESTIGATABLE_DOMAINS.items():
if domain in url:
link_type = dtype
break
classified.append({
'url': url,
'text': link.get('text', ''),
'type': link_type,
})
return classified
def triage_post(post):
"""Analyze a single post for investigation potential."""
text = post.get('text', '') or ''
# Extract claims
claims = extract_claims(text)
# Classify links
all_links = (post.get('links', []) or [])
card = post.get('card') or {}
if card.get('url'):
all_links.append({'url': card['url'], 'text': card.get('title', '')})
classified_links = classify_links(all_links)
investigatable_links = [l for l in classified_links if l['type'] != 'unknown']
# Has the post got something worth investigating?
has_claims = len(claims) > 0
has_links = len(investigatable_links) > 0
has_any_links = len(classified_links) > 0
# Priority scoring
priority = 0
if has_claims:
priority += 2
# Performance claims are highest priority
if any(c['type'] in ('performance_claim', 'multiplier_claim') for c in claims):
priority += 2
if any(c['type'] in ('copy_trading', 'arbitrage_opp') for c in claims):
priority += 1
if has_links:
priority += 2
if any(l['type'] == 'prediction_market' for l in investigatable_links):
priority += 2
if any(l['type'] in ('token_chart', 'blockchain') for l in investigatable_links):
priority += 1
if has_any_links and not has_links:
priority += 1
# Build investigation tasks
tasks = []
for claim in claims:
if claim['type'] == 'performance_claim':
tasks.append({
'action': 'verify_performance',
'description': f"Verify claim: {claim['match']}",
'method': 'Check linked profile/data for actual track record',
})
elif claim['type'] == 'copy_trading':
tasks.append({
'action': 'verify_trader',
'description': f"Verify trader referenced: {claim['match']}",
'method': 'Check trader profile, recent bets/trades, actual P&L',
})
elif claim['type'] == 'arbitrage_opp':
tasks.append({
'action': 'verify_arb',
'description': f"Verify opportunity: {claim['match']}",
'method': 'Check if spread/mismatch still exists, calculate actual risk',
})
elif claim['type'] in ('odds_claim', 'shares_price', 'prediction_market'):
tasks.append({
'action': 'check_market',
'description': f"Check prediction market: {claim['match']}",
'method': 'Verify current odds, volume, resolution criteria',
})
elif claim['type'] == 'price_target':
tasks.append({
'action': 'check_price',
'description': f"Verify price claim: {claim['match']}",
'method': 'Check current price vs target, chart pattern',
})
elif claim['type'] == 'airdrop':
tasks.append({
'action': 'verify_airdrop',
'description': f"Check airdrop legitimacy: {claim['match']}",
'method': 'Verify project, check for scam signals, confirm eligibility',
})
for link in investigatable_links:
tasks.append({
'action': f'browse_{link["type"]}',
'description': f'Follow and analyze: {link["url"]}',
'url': link['url'],
'method': f'Browse to {link["type"]} link, extract current data',
})
# For unknown links that might be interesting
for link in classified_links:
if link['type'] == 'unknown' and link['url'].startswith('http') and 'x.com' not in link['url']:
tasks.append({
'action': 'browse_unknown',
'description': f'Check external link: {link["url"]}',
'url': link['url'],
'method': 'Browse to link, determine if relevant',
})
return {
'author': post.get('author', {}),
'text': text,
'url': post.get('url', ''),
'timestamp': post.get('timestamp'),
'metrics': post.get('metrics', {}),
'claims': claims,
'links': classified_links,
'investigatable_links': investigatable_links,
'priority': priority,
'tasks': tasks,
'worth_investigating': priority >= 2,
}
def main():
parser = argparse.ArgumentParser(description="Triage X posts for investigation")
parser.add_argument("input", help="Path to posts.json")
parser.add_argument("--output", help="Output file")
parser.add_argument("--min-priority", type=int, default=2, help="Min priority to include")
args = parser.parse_args()
with open(args.input) as f:
data = json.load(f)
posts = data.get('posts', [])
print(f"Triaging {len(posts)} posts...")
triaged = []
for post in posts:
result = triage_post(post)
triaged.append(result)
# Sort by priority
triaged.sort(key=lambda x: x['priority'], reverse=True)
# Filter
worth = [t for t in triaged if t['priority'] >= args.min_priority]
output = {
'triaged_at': datetime.now(timezone.utc).isoformat(),
'total_posts': len(posts),
'worth_investigating': len(worth),
'posts': triaged,
'investigation_queue': worth,
}
output_path = args.output or os.path.join(os.path.dirname(args.input), 'triage.json')
with open(output_path, 'w') as f:
json.dump(output, f, indent=2)
# Print summary
print(f"\n=== Triage Summary ===")
print(f"Total: {len(posts)} | Worth investigating: {len(worth)}")
if worth:
print(f"\n=== Investigation Queue ===")
for t in worth:
author = t['author'].get('handle', '?')
claims = [c['type'] for c in t['claims']]
links = [l['type'] for l in t['investigatable_links']]
print(f"\n [{t['priority']}] {author}")
print(f" {t['text'][:150]}...")
if claims:
print(f" Claims: {', '.join(claims)}")
if links:
print(f" Links: {', '.join(links)}")
print(f" Tasks: {len(t['tasks'])}")
else:
print("\nNo posts met the investigation threshold.")
print(f"\nSaved to {output_path}")
if __name__ == "__main__":
main()