From baa3c2434fc16c982961267a087f60037197892d Mon Sep 17 00:00:00 2001
From: James Brechtel <git@jamesbrechtel.com>
Date: Tue, 19 May 2026 23:07:53 -0400
Subject: [PATCH] feat: add recipe scraping script and update Docker image

- scripts/scrape-recipe: Python script using recipe-scrapers to extract
  schema.org JSON-LD from a recipe URL (or local HTML file for testing)
- Dockerfile: add Python3 + recipe-scrapers in virtualenv, install the
  scrape-recipe script at /usr/local/bin/scrape-recipe
---
 Dockerfile            | 11 +++++--
 scripts/scrape-recipe | 73 +++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 82 insertions(+), 2 deletions(-)
 create mode 100755 scripts/scrape-recipe

diff --git a/Dockerfile b/Dockerfile
index 87f21e7..2eab883 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -1,15 +1,22 @@
 FROM debian:bookworm-slim
 
 RUN apt-get update && apt-get install -y --no-install-recommends \
-    ca-certificates curl tini && \
+    ca-certificates curl python3 python3-pip python3-venv tini && \
     rm -rf /var/lib/apt/lists/*
 
+# Install recipe-scrapers in a virtualenv to isolate dependencies.
+RUN python3 -m venv /opt/roux-venv && \
+    /opt/roux-venv/bin/pip install --no-cache-dir recipe-scrapers==15.11.0 && \
+    rm -rf /root/.cache/pip
+
 # Build timestamp — read at runtime for diagnostics.
 RUN mkdir -p /build && date -u '+%Y-%m-%d %H:%M UTC' > /build/build-time
 
 ADD roux-server /usr/local/bin/roux-server
+ADD scripts/scrape-recipe /usr/local/bin/scrape-recipe
 
-RUN chmod +x /usr/local/bin/roux-server
+RUN chmod +x /usr/local/bin/roux-server /usr/local/bin/scrape-recipe
+ENV PATH="/opt/roux-venv/bin:${PATH}"
 
 ENTRYPOINT ["/usr/bin/tini", "-s", "--"]
 
diff --git a/scripts/scrape-recipe b/scripts/scrape-recipe
new file mode 100755
index 0000000..4e84547
--- /dev/null
+++ b/scripts/scrape-recipe
@@ -0,0 +1,73 @@
+#!/usr/bin/env python3
+"""Extract recipe schema.org JSON-LD from a recipe URL.
+
+Uses the recipe-scrapers library (https://github.com/hhursev/recipe-scrapers)
+to download a recipe page and extract the schema.org JSON-LD recipe data.
+
+Outputs the raw schema.org JSON-LD to stdout as a JSON object suitable for
+parsing by Roux's SchemaOrg Haskell types.
+
+Usage:
+    ./scripts/scrape-recipe <url>
+    ./scripts/scrape-recipe --html <file> <url>   # Use pre-fetched HTML
+
+Examples:
+    ./scripts/scrape-recipe https://cooking.nytimes.com/recipes/12177-fried-rice
+    ./scripts/scrape-recipe --html fried-rice.html https://example.com/recipe
+"""
+
+import argparse
+import json
+import sys
+
+from recipe_scrapers import scrape_html
+
+
+def main() -> None:
+    parser = argparse.ArgumentParser(
+        description="Extract schema.org JSON-LD from a recipe URL"
+    )
+    parser.add_argument("url", help="URL of the recipe")
+    parser.add_argument(
+        "--html",
+        metavar="FILE",
+        help="Read HTML from FILE instead of downloading (for testing)",
+    )
+    parser.add_argument(
+        "--pretty",
+        action="store_true",
+        help="Pretty-print the JSON output",
+    )
+    args = parser.parse_args()
+
+    try:
+        if args.html:
+            with open(args.html) as f:
+                html = f.read()
+            scraper = scrape_html(html=html, org_url=args.url, online=False)
+        else:
+            # Download the page and scrape it
+            scraper = scrape_html(html=None, org_url=args.url, online=True)
+
+        # Extract the raw schema.org data from the scraper
+        schema = getattr(scraper, "schema", None)
+        if schema is None:
+            print("Error: scraper has no schema data", file=sys.stderr)
+            sys.exit(1)
+
+        data: dict = schema.data
+        if not data:
+            print("Error: schema data is empty", file=sys.stderr)
+            sys.exit(1)
+
+        indent = 2 if args.pretty else None
+        json.dump(data, sys.stdout, indent=indent, ensure_ascii=False)
+        sys.stdout.write("\n")
+
+    except Exception as e:
+        print(f"Error: {e}", file=sys.stderr)
+        sys.exit(1)
+
+
+if __name__ == "__main__":
+    main()