skills.rest
SamChaps
SamChapsCOMMUNITY
Explore all skills by this author →
GitHub

extract-recipes

Extract recipe text from website URLs using recipe-scrapers with JSON-LD fallback.

1|Updated Mar 12, 2026
Search Tags:#web scraping#url#extraction#recipe#json-ld#beautifulsoup#recipe-scrapers
One-click install
npx skills add https://github.com/SamChaps/monmanger --skill extract-recipes-samchaps
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: extract-recipes
Source: https://github.com/SamChaps/monmanger/tree/main/.github/skills/extract-recipes
Command: npx skills add https://github.com/SamChaps/monmanger --skill extract-recipes-samchaps

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires recipe-scrapers, requests, beautifulsoup4, and includes scripts (resource) components.

What problem does it solve? Manually copying recipe titles, times, ingredients, and instructions from websites is slow and error-prone. This Skill automates scraping a recipe URL into a clean plain-text file ready for conversion into recipe markdown. ## Core Features & Use Cases - Structured Extraction: Uses the recipe-scrapers library, which supports over 400 recipe websites, to pull title, prep/cook/total times, servings, ingredients, and instructions. - JSON-LD Fallback: When a site is not supported by recipe-scrapers, it fetches the page and parses embedded JSON-LD Recipe schema data, including HowToSection instruction groups. - Use Case: You find a recipe on a food blog and want to add it to your Jekyll recipe collection. Run the script with the URL to get a .txt file, then hand it to the new-recipe skill for bilingual markdown conversion. ## Quick Start Extract the recipe from this URL https://example.com/some-recipe and save it as a text file for conversion.

Frequently Asked Questions about extract-recipes

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I extract a recipe from a website URL in Python?▼

Run extract_url.py with the recipe URL and an optional output folder. It first tries the recipe-scrapers library, which supports over 400 sites, and saves the title, times, ingredients, and instructions to a .txt file named after the URL slug.

What Python library can scrape recipes from cooking websites?▼

The recipe-scrapers library supports structured extraction from over 400 recipe websites. This Skill uses it as the primary method and falls back to parsing JSON-LD Recipe schema with requests and BeautifulSoup when a site is unsupported.

What happens when a recipe site is not supported by recipe-scrapers?▼

The script falls back to fetching the page HTML and parsing embedded JSON-LD Recipe schema data. It handles nested @graph structures and HowToSection instruction groups. If no Recipe schema is found, it reports an error and exits.

What dependencies are required to run recipe URL extraction?▼

You need Python 3 with the recipe-scrapers, requests, and beautifulsoup4 packages installed via pip. If recipe-scrapers is missing, the script still works using only the JSON-LD fallback path.

What output format does recipe extraction produce?▼

The script writes a UTF-8 .txt file containing the source URL, recipe title, prep/cook/total times, servings, a bulleted ingredient list, and numbered instructions. The file is named after the URL slug and is designed as input for the new-recipe skill.

Related Skills

Explore More Content & Communication Skills→
Buntyarora97Buntyarora97

recipe-creator

Generate custom recipes with serving scaling and USFDA nutritional data.

Community
Intermediate
typemdtypemd
9

sync-blog

Synchronize Chinese blog posts into English while preserving markdown formatting.

Official
Intermediate
TakazudoTakazudo

verify-translation

Compare translated text against PDF page images to detect extraction gaps.

Community
Advanced
gemini-cli-extensionsgemini-cli-extensions
625

google-sheets

Search Google Sheets spreadsheets and read data as text, CSV, or JSON.

Official
Intermediate