#!/usr/bin/env python3 """Generate X Account Monitor report from scan JSON files.""" import json, os from datetime import datetime CHUNK1 = "/home/kiro/trend-engine/trends/x/account-monitor/scan_results_2026-06-18_CHUNK1.json" CHUNK2 = "/home/kiro/trend-engine/trends/x/account-monitor/scan_results_2026-06-18_CHUNK2.json" OUTPUT = "/home/kiro/trend-engine/trends/x/account-monitor/2026-06-18_account-monitor.txt" DATE_STR = "2026-06-18" IRRELEVANT = { "CINEMA505", "TheAIColony", "GoogleLabs", "GoogleAI", "Ai_Vaidehi", "AI_with_jasmin", "CharaspowerAI", "AIBuzzNews", "ChrisLaubAI", "FaithJaiye2187", "KammelaBala", "MyStageAI", "AlexStudio44", "AIGuideHQ", "4aibsc", } BIO_INFO = { "runwayml": "Runway AI — professional AI filmmaking (~260K)", "CuriousRefuge": "Curious Refuge — home for AI filmmakers", "nofilmschool": "No Film School — filmmaking news (~241.7K)", "venturetwins": "Justine Moore — a16z partner AI video (~149.5K)", "Kling_ai": "Kling AI — AI video generation (~130K)", "paultrillo": "Paul Trillo — LA director/artist (~15K)", "c_valenzuelab": "Cristobal Valenzuela — Runway CEO (~42.7K)", "CorridorDigital": "Corridor Digital — VFX/filmmaking (15M+ YouTube)", "karenxcheng": "Karen X. Cheng — Director, brand AI video (~58K)", "higgsfield": "Higgsfield AI — multi-model platform (~63K)", "pika_labs": "Pika — AI video for social creators (~143K)", "EHuanglu": "el.cine / Elsa Huang — Film director, AI consultant (~128K)", "azed_ai": "Amira Zairi — Adobe & Leonardo AI ambassador (~37K)", "JeffSynthesized": "Jeff Synthesized — NeoCinema AI Studio founder (~8.5K)", "ai_filmmaker": "Dmitry Alekseev — Film director/AI filmmaker", "visiblemaker": "The Visiblemaker — AI cinema director", "Magiermogul": "Particle Panic — AI filmmaker, Kling/Runway CPP", "WuxiaRocks": "WuxIA Rocks — AI filmmaker, character consistency (~6.5K)", "JiamingSuen": "Jiaming Sun — AI/VFX creator", "moonvalley": "Moonvalley — AI film model startup", "higgsfield_ai": "Higgsfield AI (secondary) — Kling/Seedance integration news", "Chandan_Perla": "Chandan Perla — India AI Film Festival organizer", "AITOPIAai": "AI platform — Grok Imagine Video integrations", "AI_Video_Dumps": "AI video content aggregator", "cladlabs": "CLAD Labs — AI/creative tools", "DonutAI": "AI tool ecosystem — small but on-topic", "AIFrontliner": "AI news aggregator — ChatGPT/Claude, some Seedance", "AIWarper": "AI creator — Seedance 2.0, ComfyUI workflows", "AITECHio": "AI/crypto hybrid — ACN token, AI infrastructure", "ChrisLaubAI": "RT-only — FILTERED (finance/news RTs)", "CINEMA505": "Brazilian cinema account — FILTERED (non-AI)", "TheAIColony": "General AI news aggregator — FILTERED", "GoogleLabs": "Google product news — FILTERED", "GoogleAI": "Google AI — FILTERED", "Ai_Vaidehi": "RT aggregator — FILTERED", "AI_with_jasmin": "RT/job board aggregator — FILTERED", "CharaspowerAI": "RT-heavy general AI — FILTERED", "AIBuzzNews": "General AI news — FILTERED", } # Load both chunks all_accounts = [] all_errors = [] for chunk_file in [CHUNK1, CHUNK2]: with open(chunk_file) as f: data = json.load(f) all_accounts.extend(data.get("accounts", [])) all_errors.extend(data.get("errors", [])) total_scanned = len(all_accounts) + len(all_errors) # Collect all qualifying tweets with their account info (handle, bio) all_tweets = [] accounts_with_content = 0 accounts_with_qualifying = 0 total_fetched_total = 0 for acc in all_accounts: tweet_count = acc.get("total_fetched", 0) total_fetched_total += tweet_count if tweet_count > 0: accounts_with_content += 1 for t in acc.get("tweets", []): t["handle"] = acc["handle"] t["bio"] = BIO_INFO.get(acc["handle"], "") all_tweets.append(t) if len(acc.get("tweets", [])) > 0: accounts_with_qualifying += 1 # Sort by score descending all_tweets.sort(key=lambda x: x["score"], reverse=True) # Separate top 10 by unique account (best tweet per account) seen_handles_top10 = set() top10_relevant = [] for t in all_tweets: if t["handle"] in IRRELEVANT: continue if t["handle"] in seen_handles_top10: continue seen_handles_top10.add(t["handle"]) top10_relevant.append(t) if len(top10_relevant) >= 10: break # Build report lines = [] lines.append(f"Title: X Account Monitor — {DATE_STR}") lines.append("") lines.append("Top 10 by Engagement Score") lines.append("") lines.append("#, Account, Best Tweet, Views, Date") for i, t in enumerate(top10_relevant): handle = t["handle"] url = f"https://x.com/{handle}/status/{t['id']}" snippet = t["text"][:80] date = t["date"] views = f"{t['views']:,}" lines.append(f"{i+1}, @{handle}, {snippet} ({url}), {views}, {date}") lines.append("") # Full breakdown lines.append("--- Full Breakdown ---") lines.append("") for acc in all_accounts: handle = acc["handle"] bio = acc.get("bio", BIO_INFO.get(handle, "")) tweets = acc.get("tweets", []) fetched = acc.get("total_fetched", 0) is_filtered = handle in IRRELEVANT filter_tag = " [FILTERED]" if is_filtered else "" if len(tweets) == 0: if fetched == 0: lines.append(f"@{handle}{filter_tag}: 0 tweets fetched (empty/suspended)") else: lines.append(f"@{handle}{filter_tag}: {fetched} tweets fetched, 0 qualifying") else: top = tweets[0] lines.append(f"@{handle}{filter_tag} ({bio}): {len(tweets)} qualifying tweets") for j, t in enumerate(tweets[:3]): url = f"https://x.com/{handle}/status/{t['id']}" lines.append(f" [{t['score']}pts] {t['text'][:100]} ({url}) — {t['likes']}L/{t['retweets']}RT/{t['views']}V, {t['date']}") lines.append("") # Summary lines.append("---") lines.append(f"Summary: {total_scanned} accounts scanned, {accounts_with_content} with content, {accounts_with_qualifying} with qualifying tweets. {len(all_errors)} API failures.") # Write to file with open(OUTPUT, "w") as f: f.write("\n".join(lines)) print("\n".join(lines))