feat: daily paper rss generator with dockerfile + entrypoint

run.py

@@ -0,0 +1,92 @@
+#!/usr/bin/env python3
+"""
+run.py — entrypoint for HF Daily Paper RSS generation.
+
+Generates:
+  - Daily feed (always)
+  - Weekly feed (every Monday)
+  - Monthly feed (1st of month)
+
+Usage:
+  python run.py                              # output to ./feeds/
+  python run.py --output-dir /data/feeds
+  python run.py --date 2026-06-27            # simulate date
+"""
+import argparse
+import datetime
+import os
+import subprocess
+import sys
+
+
+def main():
+    parser = argparse.ArgumentParser(description="HF Daily Paper RSS Generator")
+    parser.add_argument("--output-dir", default=os.path.join(os.getcwd(), "feeds"),
+                        help="Directory to save RSS feeds")
+    parser.add_argument("--date", default=None,
+                        help="Simulate a specific date (YYYY-MM-DD)")
+    args = parser.parse_args()
+
+    output_dir = os.path.abspath(args.output_dir)
+    os.makedirs(output_dir, exist_ok=True)
+
+    # Resolve date
+    if args.date:
+        today = datetime.date.fromisoformat(args.date)
+    else:
+        today = datetime.date.today()
+
+    year = today.year
+    month = f"{today.month:02d}"
+    week_num = today.isocalendar()[1]
+    is_monday = today.isoweekday() == 1
+    is_first = today.day == 1
+
+    script_dir = os.path.dirname(os.path.abspath(__file__))
+    parser_py = os.path.join(script_dir, "parser.py")
+
+    print(f"[run.py] Date: {today.isoformat()} "
+          f"(Year={year} Month={month} Week={week_num} "
+          f"Mon={is_monday} First={is_first})")
+    print(f"[run.py] Output: {output_dir}")
+
+    def run_parser(source, outfile):
+        full_path = os.path.join(output_dir, outfile)
+        print(f"\n── Generating {outfile} ──")
+        result = subprocess.run(
+            [sys.executable, parser_py, "--source", source, "--output", full_path],
+            capture_output=False, text=True, cwd=script_dir,
+        )
+        return result.returncode
+
+    # 1. Daily (always)
+    run_parser("https://huggingface.co/papers", "feed.xml")
+
+    # 2. Weekly (Mondays)
+    if is_monday:
+        run_parser(
+            f"https://huggingface.co/papers/week/{year}-W{week_num}",
+            "feed_weekly.xml",
+        )
+    else:
+        print("[run.py] Skipping weekly (not Monday)")
+
+    # 3. Monthly (1st)
+    if is_first:
+        run_parser(
+            f"https://huggingface.co/papers/month/{year}-{month}",
+            "feed_monthly.xml",
+        )
+    else:
+        print("[run.py] Skipping monthly (not 1st)")
+
+    print(f"\n[run.py] ✅ Done — feeds in {output_dir}")
+    for f in sorted(os.listdir(output_dir)):
+        if f.endswith(".xml"):
+            fpath = os.path.join(output_dir, f)
+            size = os.path.getsize(fpath)
+            print(f"  {f}  ({size:,} bytes)")
+
+
+if __name__ == "__main__":
+    main()