Better Fetch

Tools

Ready-made web tools built on the Better Fetch retrieval engine. Find and run them from Claude or ChatGPT via MCP, the REST API, or fork and run locally — one Better Fetch account, metered per engine call.

Content extraction

Website Content Crawler

Crawl a small same-origin website slice and return clean page text, titles, final URLs, and discovered internal links for RAG, audits, and agent context.

Returns
titleurltextlinksword_count
Examplehttps://example.com
~3 credits/runView
Content extraction

Wikipedia Article Scraper

Search Wikipedia or fetch a specific article through the official MediaWiki API, returning titles, page IDs, canonical URLs, summaries or full extracts, categories, links, images, revision metadata, and Wikidata IDs.

Returns
titlecategoriesextractextract_truncatedlanguage
Examplepage
~1 credit/runView
Content extraction

Open Library Book Scraper

Search Open Library books, ISBN records, subjects, ebooks, and public author records through the public Open Library APIs, returning normalized catalog metadata, author names, editions, covers, ratings, ebook access, Internet Archive IDs, and author summaries.

Returns
titleauthor_keysauthorscover_idcover_url
Examplelord of the rings
~1 credit/runView
Content extraction

Extract Article

Turn any article URL into clean, structured text: title, byline, publish date, and full body text — ready for LLM context windows. Works on paywalled-lite and bot-protected pages via the stealth engine.

Returns
titletextbylinefinal_urlpublished
Examplehttps://en.wikipedia.org/wiki/Web_scraping
~1 credit/runView
Content extraction

JSON-LD Extractor

Retrieve a page and extract valid JSON-LD documents with detected schema types and serialized structured data.

Returns
jsontype
Examplehttps://www.hardgraft.com/products/onepack-coal
~1 credit/runView
Content extraction

Open Graph Extractor

Retrieve a rendered page and extract Open Graph, Twitter Card, canonical, and standard metadata into reusable records.

Returns
contentproperty
Examplehttps://www.hardgraft.com/products/onepack-coal
~1 credit/runView
Content extraction

Sitemap Extractor

Discover and normalize URLs from XML sitemaps or sitemap indexes for crawl planning and content inventory.

Returns
urlchange_frequencylast_modifiedpriority
Examplehttps://nextjs.org/sitemap.xml
~1 credit/runView
Content extraction

Webpage Change Fingerprint

Create a deterministic fingerprint from normalized rendered page content for scheduled monitoring and change detection.

Returns
titleurlfingerprintnormalized_charsword_count
Examplehttps://example.com
~1 credit/runView
Content extraction

Webpage Links Extractor

Retrieve a rendered page and normalize internal or external links with anchor text, relationship labels, and domains.

Returns
urltextdomainrelscope
Examplehttps://example.com
~1 credit/runView
Content extraction

WordPress Posts Scraper

Fetch public WordPress REST posts and normalize titles, excerpts, authors, publication dates, status, links, slugs, and rendered text.

Returns
titleurlauthor_idcontent_textexcerpt
Examplehttps://wordpress.org/news
~1 credit/runView