import json, subprocess, re

data = json.load(open("/home/hermes/syslog/drafts/scot-hermes-playbook/research/video-verification.json"))
have = {r["videoId"] for r in data}
extra = []
for v in ["8GjyOQy19so", "zwqhemjHq3E"]:
    if v in have:
        continue
    url = f"https://www.youtube.com/watch?v={v}"
    oe = subprocess.run(["curl", "-s", f"https://www.youtube.com/oembed?url={url}&format=json"],
                        capture_output=True, text=True, timeout=30)
    try:
        oej = json.loads(oe.stdout)
        o = {"status": "PASS", "title": oej.get("title"), "author": oej.get("author_name")}
    except Exception:
        o = {"status": "FAIL", "raw": oe.stdout[:200]}
    wp = subprocess.run(["curl", "-s", "-L", url,
                         "-H", "User-Agent: Mozilla/5.0 (Windows NT 10.0) Chrome/124.0",
                         "-H", "Accept-Language: en-US"], capture_output=True, text=True, timeout=30)
    html = wp.stdout
    pub = re.search(r'"publishDate":"([\d\-T:Z]+)"', html)
    dur = re.search(r'"lengthSeconds":"(\d+)"', html)
    views = re.search(r'"viewCount":"(\d+)"', html)
    rec = {"videoId": v, "oembed": o,
           "publishDate": pub.group(1) if pub else None,
           "lengthSeconds": int(dur.group(1)) if dur else None,
           "views": int(views.group(1)) if views else None}
    extra.append(rec)
    print(json.dumps(rec))

data.extend(extra)
json.dump(data, open("/home/hermes/syslog/drafts/scot-hermes-playbook/research/video-verification.json", "w"), indent=2)
print("total videos in ledger:", len(data))