m3taversal
81afcd319f
Some checks are pending
CI / lint-and-test (push) Waiting to run
24 files: 8 pipeline lib modules, 6 diagnostics updates, 4 new diagnostics modules, telegram bot fix, 5 active operational scripts. Key changes: - Security: SQL injection prevention (alerting.py), SSL verification (review_queue.py), path traversal guard (extract.py) - Cost tracking: per-PR cost accumulation in evaluate.py - Auto-recovery: watchdog tier0 reset with retry cap + cooldown - Extraction: structured edge fields, post-write vector connection - New modules: vitality, research_tracking, research_routes Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
86 lines
2.8 KiB
Python
86 lines
2.8 KiB
Python
#!/usr/bin/env python3
|
|
"""Pull all tweets from specified X accounts and save as JSON archives."""
|
|
import json
|
|
import sys
|
|
import time
|
|
import urllib.request
|
|
|
|
API_KEY = "new1_280dafc879374475a86a64f6f388ac22"
|
|
BASE = "https://api.twitterapi.io/twitter/user/last_tweets"
|
|
OUT_DIR = "/opt/teleo-eval/x-archives"
|
|
|
|
ACCOUNTS = [
|
|
"m3taversal",
|
|
"Living_IP",
|
|
"teLEOhuman",
|
|
"aiCLAYno",
|
|
"futaRdIO_ai",
|
|
]
|
|
|
|
import os
|
|
os.makedirs(OUT_DIR, exist_ok=True)
|
|
|
|
def fetch_page(username, cursor=None):
|
|
url = f"{BASE}?userName={username}"
|
|
if cursor:
|
|
url += f"&cursor={cursor}"
|
|
req = urllib.request.Request(url, headers={"X-API-Key": API_KEY})
|
|
try:
|
|
with urllib.request.urlopen(req, timeout=30) as resp:
|
|
return json.loads(resp.read())
|
|
except Exception as e:
|
|
print(f" ERROR fetching {username}: {e}")
|
|
return None
|
|
|
|
def pull_all_tweets(username):
|
|
all_tweets = []
|
|
cursor = None
|
|
page = 0
|
|
while True:
|
|
page += 1
|
|
print(f" Page {page} (cursor: {'yes' if cursor else 'start'})...", end=" ")
|
|
data = fetch_page(username, cursor)
|
|
if not data or data.get("status") != "success":
|
|
print(f"FAILED: {data}")
|
|
break
|
|
|
|
tweets = data.get("data", {}).get("tweets", [])
|
|
next_cursor = data.get("data", {}).get("next_cursor")
|
|
|
|
# Deduplicate
|
|
seen_ids = {t["id"] for t in all_tweets}
|
|
new_tweets = [t for t in tweets if t["id"] not in seen_ids]
|
|
all_tweets.extend(new_tweets)
|
|
print(f"{len(new_tweets)} new tweets (total: {len(all_tweets)})")
|
|
|
|
if not next_cursor or not new_tweets:
|
|
break
|
|
cursor = next_cursor
|
|
time.sleep(1) # Rate limit courtesy
|
|
|
|
return all_tweets
|
|
|
|
for account in ACCOUNTS:
|
|
print(f"\n=== @{account} ===")
|
|
tweets = pull_all_tweets(account)
|
|
|
|
# Save raw
|
|
outfile = os.path.join(OUT_DIR, f"{account}-tweets.json")
|
|
with open(outfile, "w") as f:
|
|
json.dump({"account": account, "tweet_count": len(tweets), "tweets": tweets}, f, indent=2)
|
|
print(f" Saved {len(tweets)} tweets to {outfile}")
|
|
|
|
# Quick stats
|
|
originals = [t for t in tweets if not t.get("text", "").startswith("RT @") and not t.get("isReply")]
|
|
replies = [t for t in tweets if t.get("isReply")]
|
|
rts = [t for t in tweets if t.get("text", "").startswith("RT @")]
|
|
print(f" Breakdown: {len(originals)} original, {len(replies)} replies, {len(rts)} RTs")
|
|
|
|
if originals:
|
|
top = sorted(originals, key=lambda t: int(t.get("viewCount", 0) or 0), reverse=True)[:5]
|
|
print(f" Top 5 by views:")
|
|
for t in top:
|
|
text = t["text"][:80].replace("\n", " ")
|
|
print(f" {t.get('viewCount', '?')} views | {t.get('likeCount', '?')} likes | {text}...")
|
|
|
|
print("\n=== DONE ===")
|