jbrechtel
baa3c2434f
Build and Deploy / build-and-deploy (push) Successful in 1m55s
- 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
74 lines
2.1 KiB
Python
Executable File
74 lines
2.1 KiB
Python
Executable File
#!/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()
|