web-search-and-content

Website homepage metadata extraction: title, meta description, OpenGraph title/description/image/site name, language, favicon and viewport presence, HTTP status and final URL. Quick site profiling for directories, link previews, SEO audits and lead enrichment. $0.01 per site.

Extract all outbound links from a web page's main content as absolute URLs, plus its headings outline and title. Crawling, link discovery, sitemap building, backlink and citation research. $0.01 per page.

Name the fields you want from a page and get exactly those as JSON. URL + wanted fields -> clean JSON. Scrapes the page from a residential IP (reaches sites that block datacenters) and uses an LLM to return exactly the fields you ask for. The 'scrape into this shape' call agents love (Firecrawl-extract territory), cheaper. Query: ?url=&fields=price,rating,stock (or ?schema=free-text)

High-speed vector computation microservice to compute dot products, cosine similarities, and ranking for 1536-d float32 embeddings.

Extract text from images using Tesseract OCR. Send image as image_base64 (PNG/JPEG/WebP/TIFF/BMP, max 10 MB decoded). Returns text and confidence (0-100, where 80+ is reliable). Set language to Tesseract code: 'eng' (default), 'deu' (German

Extract all text from a PDF. Send as pdf_base64 (base64-encoded PDF, max ~10 MB decoded). Returns text (full concatenated text), pages array (per-page text + char_count), page_count, and metadata (title, author, creator). Encode with: Buffe

Fetch and extract clean readable text from any URL. Full JS rendering via Playwright — works on SPAs and dynamic sites. Returns title, text (cleaned content, default max 8000 chars), description, word_count, and optional links array. Ideal

Keyword extraction from text: the top terms and bigrams by frequency with stopwords removed. Tag, route or index agent-generated content. $0.01 per call.

Structured data extractor: every JSON-LD block on a page parsed, with the schema.org types found (Organization, Product, Article, FAQPage, BreadcrumbList, LocalBusiness...), key fields (name, price, rating, author, date) and microdata/Open Graph hints. Rich data without scraping the layout. $0.01 per page.

llms.txt reader: checks whether a site publishes llms.txt or llms-full.txt (the emerging standard for telling AI agents what a site offers), returns the content (up to 20 KB) and its headings and links. Discover agent-friendly documentation instantly. $0.01 per domain.

Date extraction from a page: the published and modified dates from meta tags and schema.org, plus dates found in the text (ISO, US and long forms), the earliest and latest, and a best guess at the publication date. Content freshness and timeline building. $0.01 per page.

Hacker News search (Algolia): top 15 stories and comments matching a phrase, with points, comment counts, author, date and links, sorted by relevance. Find prior discussion of any topic or product. $0.01 per search.

OpenAPI / Swagger discovery: probes the common spec locations (/openapi.json, /swagger.json, /api-docs, /v1/openapi.json, /.well-known/openapi.json...) and any link on the homepage, then summarises the spec: title, version, server URLs, path and operation counts, tags. Find a site's machine-readable API. $0.01 per site.

Code block extraction from a page: every / block with its language hint (from class names or fences), line count and text, plus the counts by language. Mine documentation for examples. $0.01 per page.

Document link finder: every link on a page to PDF, Word, Excel, PowerPoint, CSV, ZIP or other downloadable files, with anchor text and file type counts. Find reports, whitepapers and datasets fast. $0.01 per page.

Search Wikipedia, Wikivoyage, Wiktionary, arXiv, OpenAlex, Hacker News and Stack Overflow in one call. Research search in one call: Wikipedia, Wikivoyage (travel guides), Wiktionary (meanings, translations), PsychonautWiki (harm reduction: name a substance and the answer leads with dose ranges, duration and dangerous combinations), arXiv, OpenAlex (300M+ scholarly works, counted 30 Sep), Hacker News and Stack Overflow asked in parallel, answered in about a second, each hit with its source,…

Raw HTML fetch: the page source (up to 500 KB) with status, final URL after redirects, content type, byte size and response headers. For agents that want to run their own parser without managing fetch, redirects and timeouts. $0.01 per URL.

Phone number extraction from a page: candidate numbers found in the text and tel: links, normalised, with the tel-link ones marked as high confidence. Contact discovery for lead lists. $0.01 per page.

HTML to plain text: strips tags, scripts and styles, decodes entities, keeps paragraph and line breaks, and returns word count. Clean up scraped or generated HTML. $0.01 per call.

HTML tables to JSON: every table on a page as arrays of rows (header row detected, cells cleaned of markup), with row and column counts and a caption. Pull structured data out of any web page. $0.01 per page.

ads.txt parser: fetches a publisher's ads.txt and lists authorised ad systems with account IDs and relationship (DIRECT/RESELLER), totals per relationship and the top ad exchanges. Ad-tech and publisher research. $0.01 per domain.

Site navigation extraction: links inside , header menus and elements with menu/nav roles, deduplicated with their text, grouped as internal or external, plus a guess at the primary sections. Understand a site's structure in one call. $0.01 per page.

Is a URL crawlable? Fetches the site's robots.txt and evaluates the given path for a specific user-agent (Googlebot, GPTBot, ClaudeBot, Bingbot or any token; default *), returning allowed/disallowed, the matching rule, the group used, crawl-delay and declared sitemaps. Pre-flight for crawlers and SEO checks. $0.01 per check.

Convert any web page URL to clean Markdown for LLMs and agents: fetches the page, removes navigation, ads, scripts and boilerplate, keeps the main article content with headings, lists, tables, links, images and code blocks, and returns title, meta description, word count, headings outline and outbound links. Web scraping, article extraction, readability and HTML-to-Markdown in one call, no API key. $0.05 per page.