openclaw skills install @hasdata/hasdata-api

Web scraping for OpenClaw,
without a scraper to maintain

You ask in plain language. The skill picks the source, calls it and hands back parsed fields, so nothing in the conversation has to read a page.

1,000 free credits. No credit card required.

ask in plain language·fields, not a page·30+ sources by name

The skill runs on the hasdata CLI. One install line, then hasdata configure once.

zshclawhub.ai
$ openclaw skills install @hasdata/hasdata-api
OpenClawhasdata/hasdata-apiskill active
What do USB-C charging cables go for right now, and which ones are discounted?
fields, already parsed
titlepricewasratingreviews
Apple 240W USB-C to USB-C Woven Charge Cable (2 m)$24$294.79,200
LISEN USB C to USB C Cable, 240W (6.6FT, 2-Pack)$8.99$9.994.510,800
Anker USB C to USB C Cable, 60W (2-Pack, 6 ft)$9.994.786,800
amazon-search · one of the 30+ sources the skill maps intent onto
ClientsClients

Install the OpenClaw skill, then just ask.

Nothing to look up before you ask. The skill knows which source answers which question, and it fills in the parameters itself.

zshfree skill
add the skill
$ openclaw skills install @hasdata/hasdata-api
npx clawhub@latest install hasdata-api  # from ClawHub
install the binary it wraps
$ curl -sSL https://raw.githubusercontent.com/HasData/hasdata-cli/main/install.sh | sh
# Go and Windows paths on the CLI page
point it at your key
$ hasdata configure
# ~/.hasdata/config.yaml, mode 0600, or export HASDATA_API_KEY
$ hasdata <api> --flag value --raw | jq .  # the shape of every call the skill makes
what the skill passes
--rawJSON the skill reads
--prettywhen you run it yourself
-o, --outputto a file
--verboseURL + X-RateLimit-*
--timeout · --retries2m · 2 on 429/5xx
rules · exit codes

kebab-case in, camelCase out · --no-* twins for true-by-default booleans · -json takes inline JSON, @file or stdin · enums validate client-side

0 ok1 input2 net3 4xx4 5xx

Ask in the chat. Read the fields.

Six questions the agent answered end to end, quirks included. No browser anywhere in the loop.

in the chat

Coffee shops around here, with phone numbers

$ hasdata google-maps --q "coffee shop" --ll "@30.2672,-97.7431,13z"
google-maps20 places back
placephonerating
Stouthaus Coffee - Sunset Valley(512) 721-00304.6 (772)
Terrible Love4.9 (419)
Hometown Coffee - East Austin4.9 (78)

Two of the three have no phone. Google holds none for them, so phone comes back as null instead of a guess.

fields in the response
titlephoneaddresswebsiteratingreviewstype

Search, retail, property, jobs. One skill, 57 tools behind it.

You name the site, the skill picks the source. Every one of them costs the same per call whether the agent asks for it or you type the command yourself.

All Scraper APIs
Search

Search, every surface of it

The Google results page, Light SERP, AI Mode, AI Overview, News, Shopping, Images, Events and short videos. Plus Bing and Trends.

positiontitlelinksnippet
Local & leads

Businesses, phone included

Google Maps places, reviews, author reviews, photos and posts. Plus Yelp and YellowPages.

phonewebsiteratingaddress
Listings & stays

Homes, stays and fares

Zillow, Redfin, Airbnb, Booking, Google Hotels, Google Flights.

pricebedsareadaysOnZillow
Commerce

Products and their sellers

Amazon search, product, seller and seller inventory. Plus Shopify.

currentPricebeforePrice
Video & social

Channels, posts and transcripts

YouTube search, video, channel and transcript. TikTok profile, posts and keyword search. Instagram.

viewslikesfollowersCounthashtags
Jobs

Openings and employers

Indeed for the openings, Glassdoor for the employers behind them.

companylocationsalarybenefits
Universal

Anything with a URL

Any public URL through the web-scraping command. Markdown for reading, or name the fields and get typed JSON. A site we don't parse out of the box is a custom scraper away.

markdowntextemailslinks

1,000 free credits is a finished job.

100 SERPs
the parsed page of Google, position to snippet
100 × 10 credits, the free tier exactly
~4,000 rows
Maps businesses, phones where Google has them
200 pages × 5 credits · 20 per page
1,000 pages
read as clean markdown
1 credit each when the skill reads the page without rendering, 10 with it on
Free
$0 /mo
One-time free trial
1,000 credits to start
1,000 credits, one time
1 concurrent request
Pay only for successful requests
One balance across the skill, the CLI and REST
Start free
Startup
$49 /mo
$0.24 / 1k credits
200K credits / month
200K credits / month
15 concurrent requests
Pay only for successful requests
One balance across the skill, the CLI and REST
Get started
Business
Recommended
$99 /mo
$0.10 / 1k credits
1M credits / month
1M credits / month
30 concurrent requests
Pay only for successful requests
One balance across the skill, the CLI and REST
Get started
Growth
$249 /mo
$0.08 / 1k credits
3M credits / month
50 concurrent requests
Pay only for successful requests
One balance across the skill, the CLI and REST
Get started
Monthly credit volume
Free 1M 5M 20M 60M 100M
Best fit
Business
credits / mo
1M
Concurrency
30
$ / 1k credits
$0.10
$99 /mo
Get Started
Enterprise
Custom price based on required volume

Past 100M credits a month, or terms the self-serve plans do not cover. We shape the contract around your workload.

Credits rollover
Unused credits carry into the next billing period.
Concurrency 2000+
Parallel request limits set to your peak load.
#1 request priority
Highest speed, always first in the queue.
Personal manager
A direct line to the founding team.
SSO
SAML single sign-on for the whole team.
SOC-2 compliance
Security review, DPA, and audit reports.
Talk to sales Quote within one business day

Frequently asked
questions.

The short answers. Everything longer lives in the docs and on Discord.

How do I scrape a website with OpenClaw?

OpenClaw can reach a page three ways. Its own fetch tool reads a URL as text, the built-in browser drives a real Chromium when the page needs one, and a skill hands the whole job to an API that already did both. This skill is the third route, so no Chromium runs on your machine and nothing has to be parsed afterwards. You ask for coffee shops with phone numbers and get the fields back. Setup is one install line and your key in hasdata configure.

Is the skill free?

Yes. The skill and the binary under it cost nothing. Credits only start moving when a call fetches data, and you start with 1,000 free, no card.

What does a call cost?

It depends on the source the skill picks. Reading a page without rendering costs 1 credit, Maps and light SERP are 5, a full Google results page is 10, and the specialized endpoints run up to 15. Those are the same rates as calling the API directly, and a failed call is never charged.

How many questions can it answer at once?

One at a time on the free tier, so a batch of asks runs sequentially. Paid plans start at 15 concurrent requests. Past your limit the API answers 429 and the call retries twice before it gives up, and nothing is charged for the attempts that failed.

Does my API key end up in the conversation?

No. hasdata configure writes it to ~/.hasdata/config.yaml with mode 0600, and the skill calls the binary, which reads the key itself. A flag beats HASDATA_API_KEY, which beats the file, so a container can pass the variable instead.

Can the agent tell a refusal from an empty result?

The exit code says which. 1 means the call was malformed, 3 means the API refused it, and 0 with an empty array means the source had nothing for that query. Errors go to stderr behind an error: prefix, so what the skill reads back stays clean JSON.

Does it update itself?

Only when you say so. hasdata update --check looks for a new release and hasdata update installs it. The binary checks daily and mentions a new version on stderr, but it never replaces itself without your consent.

When would I want the MCP server instead?

When nothing should be installed. The MCP server is a hosted endpoint, so a client that speaks MCP connects with a URL and a key and reaches the same tools. The skill is the local route, where the binary sits on your machine and the key never leaves it. Same endpoints, same balance either way.

One skill away.

Web scraping inside OpenClaw, minus the infrastructure. No headless browsers, no proxy pools, no parsers to maintain, just fields your agent can read.

Get started → Documentation

One skill · 1,000 free credits · no card