Files
buryan-infra/ops/media/media_maintenance.py

121 lines
3.9 KiB
Python

#!/usr/bin/env python3
"""M-22/M-23: обслуживание медиа — дубли, осиротевшие файлы, крупные файлы.
Пишет отчёт в Matrix и в лог. Ничего не удаляет автоматически.
"""
import json
import os
import time
import urllib.parse
import urllib.request
MEDIA = "/mnt/media"
BOTS_ENV = "/etc/hub-bots/bots.env"
DM_ENV = "/etc/hub-bots/dm.env"
REPORT = "/var/lib/hub-media/report.json"
MIN_SIZE = 50 * 1024 * 1024
def env(path):
out = {}
try:
for line in open(path, encoding="utf-8"):
line = line.strip()
if line and not line.startswith("#") and "=" in line:
k, v = line.split("=", 1)
out[k] = v
except Exception:
pass
return out
def matrix(text):
e = env(BOTS_ENV)
token = e.get("MEDIA_TOKEN")
hs = e.get("HS", "https://matrix.buryans.ru").rstrip("/")
rooms = []
try:
for line in open(DM_ENV, encoding="utf-8"):
if line.startswith("MEDIA="):
rooms.append(line.split("=", 1)[1].strip())
except Exception:
pass
for room in rooms:
url = (hs + "/_matrix/client/r0/rooms/" + urllib.parse.quote(room, safe="")
+ "/send/m.room.message/" + str(int(time.time() * 1000)))
body = json.dumps({"msgtype": "m.text", "body": text}).encode()
req = urllib.request.Request(url, data=body, method="PUT",
headers={"Authorization": "Bearer " + token,
"Content-Type": "application/json"})
try:
urllib.request.urlopen(req, timeout=15).read()
except Exception as ex:
print("matrix:", ex)
def scan():
files = []
for root, dirs, names in os.walk(MEDIA):
dirs[:] = [d for d in dirs if not d.startswith(".")]
for n in names:
if not n.lower().endswith((".mkv", ".mp4", ".avi", ".ts", ".m4v", ".mov")):
continue
p = os.path.join(root, n)
try:
st = os.stat(p)
except Exception:
continue
files.append({"path": p, "size": st.st_size, "mtime": st.st_mtime,
"name": n})
return files
def main():
os.makedirs("/var/lib/hub-media", exist_ok=True)
files = scan()
total = sum(f["size"] for f in files)
# дубли по имени+размеру
seen = {}
dups = []
for f in files:
key = (f["name"].lower(), f["size"])
if key in seen:
dups.append((seen[key], f["path"]))
else:
seen[key] = f["path"]
# крупные и старые
big = sorted(files, key=lambda x: -x["size"])[:5]
old = [f for f in files if (time.time() - f["mtime"]) > 365 * 86400]
report = {
"ts": time.strftime("%Y-%m-%dT%H:%M:%S"),
"files": len(files),
"total_gb": round(total / 1024 ** 3, 1),
"duplicates": dups[:10],
"old_files": len(old),
"biggest": [{"name": f["name"][:70], "gb": round(f["size"] / 1024 ** 3, 1)}
for f in big],
}
json.dump(report, open(REPORT, "w"), ensure_ascii=False, indent=1)
lines = [f"🎬 **Обслуживание медиа**",
f"файлов: {report['files']}, всего {report['total_gb']} ГБ"]
if dups:
lines.append(f"⚠️ возможных дублей: {len(dups)}")
for a, b in dups[:3]:
lines.append(f" • {os.path.basename(a)} ↔ {os.path.basename(b)}")
if old:
lines.append(f"🕸 файлов старше года: {len(old)}")
if big:
lines.append("📦 крупнейшие: " + ", ".join(
f"{b['name']} ({b['gb']} ГБ)" for b in report["biggest"][:3]))
text = "\n".join(lines)
print(text)
matrix(text)
if __name__ == "__main__":
main()