feat: mazání data/ souborů starších než 30 dní

daily_top.py

@@ -0,0 +1,89 @@
+#!/usr/bin/env python3
+import html
+import json
+import os
+import re
+import sys
+import urllib.request
+import urllib.error
+from datetime import datetime, timezone
+
+def load_env(path=".env"):
+    env = {}
+    try:
+        with open(path) as f:
+            for line in f:
+                line = line.strip()
+                if not line or line.startswith("#") or "=" not in line:
+                    continue
+                key, _, val = line.partition("=")
+                env[key.strip()] = val.strip().strip('"').strip("'")
+    except FileNotFoundError:
+        pass
+    return env
+
+def api_get(url, token):
+    req = urllib.request.Request(url, headers={"Authorization": f"Bearer {token}"})
+    try:
+        with urllib.request.urlopen(req) as resp:
+            return json.loads(resp.read().decode())
+    except urllib.error.HTTPError as e:
+        print(f"HTTP {e.code} při volání {url}: {e.read().decode()}", file=sys.stderr)
+        raise
+    except urllib.error.URLError as e:
+        print(f"Chyba sítě při volání {url}: {e.reason}", file=sys.stderr)
+        raise
+
+def clean_content(content):
+    text = re.sub(r'<a\b[^>]*class="[^"]*hashtag[^"]*"[^>]*>.*?</a>', "", content, flags=re.IGNORECASE)
+    text = re.sub(r"<[^>]+>", " ", text)
+    text = html.unescape(text)
+    return re.sub(r"\s+", " ", text).strip()
+
+def main():
+    env = {**load_env(), **os.environ}
+
+    for var in ("NOVINKY_TOKEN", "INSTANCE_URL"):
+        if not env.get(var):
+            print(f"Chybí proměnná prostředí: {var}", file=sys.stderr)
+            sys.exit(1)
+
+    token = env["NOVINKY_TOKEN"]
+    base_url = env["INSTANCE_URL"].rstrip("/")
+
+    try:
+        statuses = api_get(f"{base_url}/api/v1/trends/statuses?limit=10", token)
+    except Exception:
+        sys.exit(1)
+
+    candidates = []
+    for s in statuses:
+        if "@" in s.get("account", {}).get("acct", ""):
+            continue
+        text = clean_content(s.get("content", ""))
+        if len(text) < 10:
+            continue
+        reblogs = s.get("reblogs_count", 0)
+        favourites = s.get("favourites_count", 0)
+        candidates.append({
+            "acct": s["account"]["acct"],
+            "text": text,
+            "reblogs": reblogs,
+            "favourites": favourites,
+            "score": reblogs + favourites,
+        })
+
+    candidates.sort(key=lambda x: x["score"], reverse=True)
+    top = candidates[:3]
+
+    today = datetime.now(timezone.utc).strftime("%Y-%m-%d")
+    os.makedirs("data", exist_ok=True)
+    out_path = os.path.join("data", f"{today}.json")
+
+    with open(out_path, "w", encoding="utf-8") as f:
+        json.dump({"date": today, "top": top}, f, ensure_ascii=False, indent=2)
+
+    print(f"Uloženo: {out_path} ({len(top)} tootů)")
+
+if __name__ == "__main__":
+    main()