View as Markdown
Webscrape AI icon

Webscrape AI ACTION

Scrape Website

Scrape the provided URL and store the results in the system. See the documentation
  • Action
  • Writes data
  • API key
  • SDK
  • MCP

IMPLEMENTATION

Call this tool

Connect a user's Webscrape AI account once, then configure and run Scrape Website from your backend or agent.

import { PipedreamClient } from "@pipedream/sdk"

const pd = new PipedreamClient({
  projectId: process.env.PIPEDREAM_PROJECT_ID!,
  clientId: process.env.PIPEDREAM_CLIENT_ID!,
  clientSecret: process.env.PIPEDREAM_CLIENT_SECRET!,
  projectEnvironment: "production",
})

const result = await pd.actions.run({
  id: "webscrape_ai-scrape-website",
  externalUserId: "{external_user_id}", // any stable ID for this user in your system
  configuredProps: {
    webscrape_ai: { authProvisionId: "apn_xxxxxxx" },
    url: "URL",
    command: "Command",
  },
})

console.log(result)

SCHEMA

Inputs

Pipedream supplies the connected account. Your application provides the operation-specific values below. Dynamic inputs are resolved against that user's account.

Scrape Website inputs
Property Type Description
url URL string
The URL of the website to scrape
Required
command Command string
The data you want to extract. E.g. I want to extract all the news details
Required
schema Schema string
Schema representing the fields you want to scrape. E.g. {"author":"string","comments_count":"integer","points":"integer","posted_time":"string","title":"string","url":"url"}
Required
pages Pages integer
Number of pages to scrape. Default value is 1.
Optional
headers Headers string
List of headers in key-value pairs. i.e Accept: application/json
Optional
instructions Instructions string
List of JavaScript instructions that you want to execute, like clicking a specific button, waiting for a specific code block to appear, etc. Example: {"click": "#button_id"}. See the documentation for more information.
Optional

REFERENCE

Tool details

Behavior hints are published with the component in the Pipedream registry and surface as MCP tool annotations, so an agent can reason about a tool before it calls it.

Registry key
webscrape_ai-scrape-website
Version
0.0.3
App
Webscrape AI
Authentication
API key
Read-only
No
Destructive
No
Open world
Yes