feat: add strip_pdf_metadata.py tool

Author: Ricardo Decal

README.md

@@ -49,6 +49,21 @@ Options:
   --help                  Show this message and exit.
 ```
 
+### [strip_pdf_metadata.py](python/strip_pdf_metadata.py)
+
+Output of `uv run https://tools.ricardodecal.com/python/strip_pdf_metadata.py --help`:
+
+```text
+Usage: strip_pdf_metadata.py [OPTIONS] INPUT_FILE [OUTPUT_FILE]
+
+  Strip metadata from a PDF file.
+
+  If OUTPUT_FILE is not provided, writes to 'stripped_<INPUT_FILE>'.
+
+Options:
+  --help  Show this message and exit.
+```
+
 ### [yt_transcript.py](python/yt_transcript.py)
 
 Output of `uv run https://tools.ricardodecal.com/python/yt_transcript.py --help`:

index.html

@@ -202,6 +202,17 @@ <h3><a href="python/convert_arrow_to_parquet_streaming.py">convert_arrow_to_parq
                           dir
   --help                  Show this message and exit.
 </code></pre>
+<h3><a href="python/strip_pdf_metadata.py">strip_pdf_metadata.py</a></h3>
+<p>Output of <code>uv run https://tools.ricardodecal.com/python/strip_pdf_metadata.py --help</code>:</p>
+<pre><code class="language-text">Usage: strip_pdf_metadata.py [OPTIONS] INPUT_FILE [OUTPUT_FILE]
+
+  Strip metadata from a PDF file.
+
+  If OUTPUT_FILE is not provided, writes to 'stripped_&lt;INPUT_FILE&gt;'.
+
+Options:
+  --help  Show this message and exit.
+</code></pre>
 <h3><a href="python/yt_transcript.py">yt_transcript.py</a></h3>
 <p>Output of <code>uv run https://tools.ricardodecal.com/python/yt_transcript.py --help</code>:</p>
 <pre><code class="language-text">Usage: yt_transcript.py [OPTIONS] URL [OUTPUT_FILE]

python/strip_pdf_metadata.py

@@ -0,0 +1,64 @@
+#!/usr/bin/env python3
+# /// script
+# requires-python = ">=3.12"
+# dependencies = [
+#     "click",
+#     "pikepdf",
+# ]
+# ///
+"""
+Strip metadata from a single PDF file.
+"""
+
+import sys
+from pathlib import Path
+
+import click
+import pikepdf
+
+
+def strip_metadata(src: Path, dst: Path) -> None:
+    """Strip metadata from a PDF file."""
+    try:
+        with pikepdf.open(src) as pdf:
+            root = pdf.trailer.get("/Root")
+            if root and "/Metadata" in root:
+                del root["/Metadata"]
+
+            info = pdf.trailer.get("/Info")
+            if info:
+                for k in list(info.keys()):
+                    del info[k]
+                del pdf.trailer["/Info"]
+
+            pdf.save(dst)
+            click.echo(f"Successfully stripped metadata: {src} -> {dst}")
+    except Exception as e:
+        click.echo(f"Error stripping metadata from '{src}': {e}", err=True)
+        sys.exit(1)
+
+
+@click.command()
+@click.argument(
+    "input_file",
+    type=click.Path(exists=True, dir_okay=False, path_type=Path),
+)
+@click.argument(
+    "output_file",
+    type=click.Path(writable=True, dir_okay=False, path_type=Path),
+    required=False,
+)
+def main(input_file: Path, output_file: Path | None) -> None:
+    """
+    Strip metadata from a PDF file.
+
+    If OUTPUT_FILE is not provided, writes to 'stripped_<INPUT_FILE>'.
+    """
+    if output_file is None:
+        output_file = input_file.with_name(f"stripped_{input_file.name}")
+
+    strip_metadata(input_file, output_file)
+
+
+if __name__ == "__main__":
+    main()