web-search-and-content

Google web search (Serper-backed). POST { query, num? } → { results: [{title,url,snippet}] }. No API key, no subscription — pay per call.

Semantic/neural web search (Exa-backed). POST { query, num? } → { results: [{title,url,snippet}] }.

URL to clean JSON for AI agents. Fetches any public web page server-side and returns title, meta description, canonical URL, a heading outline, and boilerplate-stripped plain text — navigation, sidebars, cookie banners and footers removed. Saves an agent from running its own fetch + HTML-parsing + readability stack. Flat $0.01 per call, no account, no API key, no rate limit.

美股科技股财报+AI解读 — 标普500 科技板块核心龙头 25 只（AAPL/MSFT/NVDA/GOOGL/AMZN/META/TSLA/AVGO/ORCL/AMD/PLTR/ARM 等）最新单季财报：营收、净利润及同比增速，每只附中文 AI 解读。数据取自 SEC EDGAR XBRL 官方申报，已做单季口径清洗（剔除累计值混算，同比可直接使用），比二手财经站更准更早。

Extract a public web page into clean structured JSON for agent workflows: title, description, main text, all JSON-LD, Open Graph and Twitter metadata, headings, links, and AI-crawler and structured-data signals. Follows redirects and enforces timeout, response-size, and SSRF safeguards.

Top podcasts or apps for a term (?term=ai&type=podcast|app) — media/marketing signal (iTunes). Live. Returns JSON.

Search Hacker News newest-first via Algolia (param q = query). Query: ?q= Returns JSON.

Web scraping proxy API - send a URL, get clean markdown/HTML back

GlianaAI - pay-per-call AI: LLM chat (OpenAI-compatible), image, video, music, speech - 80+ models, no signup, USDC. This resource: flux-2-max (Text-to-Image). https://ai.glianalabs.com

Prueft Text oder Quelltext auf 20 Arten von Geheimnissen: AWS, GitHub, GitLab, Slack, Stripe, OpenAI, Anthropic, Google, SendGrid, Twilio, npm, private Schluesselbloecke, JWT, Zugangsdaten in URLs, Datenbankverbindungen und allgemeine Zuweisungen mit Entropiepruefung. Liefert Regel, Schwere, Zeile, Spalte und eine gekuerzte Vorschau. Fundwerte werden nie vollstaendig zurueckgegeben.

One page load answers everything an agent needs to reason about a page: the DOM after JavaScript capped at 2 MB, the CDP accessibility tree flattened with parent references, every link with rel and target and an internal or external verdict, every form field with its label and autocomplete hint, console errors and warnings with source and line, a screenshot, navigation timings and a summary of the requests the page fired. Chrome runs without credentials, without cookies and without login, so a s

Loads one https page in a real headless browser and performs up to eight steps on it: click, fill, select, check, uncheck, wait, wait_for_selector. Returns a per-step log saying what was attempted and whether it succeeded, plus the final URL, title, visible text, links, form structure and an optional screenshot as a base64 PNG. Three limits are part of the product, not accidents.

Dark web intelligence from Telegram: marketplace listings, forum chatter, access broker posts, credential shops, Tor site activity. Filters: severity, min_confidence, since, tag, sector, country, organization, limit, offset.

Convert a web page (by URL) or raw HTML into clean, readable Markdown plus structured metadata (title, description, Open Graph tags, canonical URL, language). Strips scripts, styles and boilerplate tags; preserves headings, links, images, lists, code blocks and tables. Built for agents that need web content as LLM-ready text. POST a JSON body like: {"url":"https://example.com/article"}

Extract title and common meta tags from caller-held HTML — first-party local utility for agent preflight and proven micro-utils expansion. Returns deterministic machine-readable JSON for $0.002 USDC via x402 on Base. Execution is first-party, local-only, stateless, and memory-only with no paid upstream, no input retention, no web search, no live RPC, and no mediagen. Results are advisory; the caller owns authorization, budgets, and production controls. Sibling of Delx routes that already conver…

Capture a citable snapshot of a public web page: final URL after redirects, HTTP status, timestamp, security headers, extracted text, and SHA-256 hashes of both the raw response and the text. Deterministic and reproducible — no model involved, nothing generated. Use it to prove what a page said at a point in time, or to detect whether content actually changed.

Turn tabular text — pasted tables, statements, reports, CSV-ish fragments — into clean JSON rows with consistent column names. Handles ragged formatting that regex-based parsers break on. The cloud equivalent for table extraction bills around $15 per 1,000 pages.

Convert any public web page into clean, LLM-ready Markdown with the navigation, scripts and boilerplate stripped. Pay per call with no account, no subscription and no monthly minimum — useful for agents that need a handful of pages rather than a scraping plan. Obeys robots.txt and fetches logged-out public pages only.

Extract structured JSON from unstructured text against a JSON Schema you supply. Returns data conforming to your schema, or nulls where the text does not contain a field. Runs on dedicated local hardware — no per-token cloud billing. Typical alternative: $15-30 per 1,000 pages.

Fetch a public web page and return structured JSON matching a JSON Schema you supply. Combines retrieval and extraction in one paid call, so an agent does not need a separate scraping subscription. Obeys robots.txt and fetches logged-out public pages only.

Harvest URL and DOI citation patterns from text without network access — call when harvesting URL/DOI citation patterns without network. Use on text/URLs the agent already holds—adjacent to high-volume extract demand, never advertised as general web or X search. Returns deterministic machine-readable JSON for $0.003 USDC via x402 on Base. Execution is first-party, local-only, stateless, and memory-only with no paid upstream, no input retention, and no claim of live chain tip, web search, or media generation. Results are advisory; the caller owns authorization and production controls.

robots.txt / llms.txt — Fetch and parse a site's robots.txt and llms.txt.

Erkennt CMS, Shop, Framework, Server, CDN, Analytics, Consent-Tool, Zahlungsanbieter und Marketing-Stack aus Headern, HTML und Skript-URLs. Liefert Trefferliste mit Kategorie, Beleg und Sicherheit.

Any web URL -> clean LLM-ready markdown (title + main content, boilerplate stripped). The retrieval/RAG primitive for agents.