Scrapegraph Start Smartscraper Skill — Scrapegraphai API Tool for AI Agents

Tool Skill

Scrapegraph Start Smartscraper

scrapegraph_start_smartscraper

Extract content from a webpage using AI by providing a natural language prompt and a URL.

$0.08/call

Flat rate

Scrapegraphai API

Raw SKILL.md Tool Page

When to Use

Use this tool when you need to extract content from a webpage using ai by providing a natural language prompt and a url.. This is part of the Scrapegraphai API provider on xpay✦.

MCP Connection

Connect to xpay✦ to access this tool (and 10+ others):

{
  "mcpServers": {
    "xpay": {
      "url": "https://mcp.xpay.sh/mcp?key=YOUR_API_KEY"
    }
  }
}

For Claude Code:

claude mcp add --transport http xpay "https://mcp.xpay.sh/mcp?key=YOUR_API_KEY"

How to Execute

Use the xpay✦ meta-tools to run this tool:

xpay_details — Get full input schema: xpay_details("scrapegraph/scrapegraph_start_smartscraper")
xpay_run — Execute: xpay_run("scrapegraph/scrapegraph_start_smartscraper", { ...inputs })

Input Parameters

Parameter	Type	Required	Description
`headers`	object	No	Optional custom HTTP headers to send with the request. Useful for setting User-Agent, cookies, authentication tokens, and other request metadata. Example: {"User-Agent": "Mozilla/5.0...", "Cookie": "session=abc123"}
`website_markdown`	string	No	Raw Markdown content to process directly (max 2MB). Mutually exclusive with website_url and website_html. Perfect for extracting structured data from Markdown documentation, README files, or any content already in Markdown format.
`steps`	string	No	Optional array of interaction steps to perform on the webpage before extraction. Each step is a string describing the action to take (e.g., “click on filter button”, “wait for results to load”). Example: ["click on search button", "type query in search box", "wait for results"]
`cookies`	object	No	Optional cookies object for authentication and session management. Useful for accessing authenticated pages or maintaining session state. Example: {"session_id": "abc123", "auth_token": "xyz789"}
`user_prompt`	string	Yes	Natural language description of what information you want to extract from the webpage.
`total_pages`	number	No	Optional parameter to enable pagination and scrape multiple pages. Specify the number of pages to extract data from. Default: 1 Range: 1-100
`render_heavy_js`	boolean	No	Optional parameter to enable enhanced JavaScript rendering for heavy JS websites (React, Vue, Angular, SPAs). Use when standard rendering doesn’t capture all content. Default: false
`number_of_scrolls`	number	No	Optional parameter for infinite scroll pages. Specify how many times to scroll down to load more content before extraction. Default: 0 Range: 0-50
`website_html`	string	No	Raw HTML content to process directly (max 2MB). Mutually exclusive with website_url and website_markdown. Useful when you already have HTML content cached or want to process modified HTML.
`website_url`	string	Yes	The URL of the webpage you want to extract information from. You must provide exactly one of: website_url, website_html, or website_markdown.
`stealth`	boolean	No	Enable stealth mode to bypass bot protection using advanced anti-detection techniques. Adds +4 credits to the request cost
`output_schema`	object	No	Optional schema to structure the output. If provided, the AI will attempt to format the results according to this schema.
`mock`	boolean	No	Optional parameter to enable mock mode. When set to true, the request will return mock data instead of performing an actual extraction. Useful for testing and development. Default: false

Pricing

Cost: $0.08/call
Balance check: Use xpay_balance to check remaining credits
Get your API key at xpay.tools — $5 free credits included

Related Skills

Scrapegraphai API (all tools) — 11 tools
Scrapegraph Scrape — $0.06/call
Scrapegraph Start Searchscraper — $0.24/call
Scrapegraph Start Smartcrawler — $0.08/call
Scrapegraph Start Sitemap — $0.02/call
Scrapegraph Start Markdownify — $0.06/call

Links

Tool page: https://xpay.tools/scrapegraph/scrapegraph-start-smartscraper/
Provider: https://xpay.tools/scrapegraph/
All tools: https://xpay.tools/explore

How to Execute

// 1. Get full schema

xpay_details("scrapegraph/scrapegraph_start_smartscraper")

// 2. Execute

xpay_run("scrapegraph/scrapegraph_start_smartscraper", { ...inputs })

Input Parameters

Parameter	Type	Required	Description
headers	object	No	Optional custom HTTP headers to send with the request. Useful for setting User-Agent, cookies, authentication tokens, and other request metadata. Example: {"User-Agent": "Mozilla/5.0...", "Cookie": "session=abc123"}
website_markdown	string	No	Raw Markdown content to process directly (max 2MB). Mutually exclusive with website_url and website_html. Perfect for extracting structured data from Markdown documentation, README files, or any content already in Markdown format.
steps	string	No	Optional array of interaction steps to perform on the webpage before extraction. Each step is a string describing the action to take (e.g., “click on filter button”, “wait for results to load”). Example: ["click on search button", "type query in search box", "wait for results"]
cookies	object	No	Optional cookies object for authentication and session management. Useful for accessing authenticated pages or maintaining session state. Example: {"session_id": "abc123", "auth_token": "xyz789"}
user_prompt	string	Yes	Natural language description of what information you want to extract from the webpage.
total_pages	number	No	Optional parameter to enable pagination and scrape multiple pages. Specify the number of pages to extract data from. Default: 1 Range: 1-100
render_heavy_js	boolean	No	Optional parameter to enable enhanced JavaScript rendering for heavy JS websites (React, Vue, Angular, SPAs). Use when standard rendering doesn’t capture all content. Default: false
number_of_scrolls	number	No	Optional parameter for infinite scroll pages. Specify how many times to scroll down to load more content before extraction. Default: 0 Range: 0-50
website_html	string	No	Raw HTML content to process directly (max 2MB). Mutually exclusive with website_url and website_markdown. Useful when you already have HTML content cached or want to process modified HTML.
website_url	string	Yes	The URL of the webpage you want to extract information from. You must provide exactly one of: website_url, website_html, or website_markdown.
stealth	boolean	No	Enable stealth mode to bypass bot protection using advanced anti-detection techniques. Adds +4 credits to the request cost
output_schema	object	No	Optional schema to structure the output. If provided, the AI will attempt to format the results according to this schema.
mock	boolean	No	Optional parameter to enable mock mode. When set to true, the request will return mock data instead of performing an actual extraction. Useful for testing and development. Default: false

Related Tools from Scrapegraphai API

Scrapegraph Scrape — $0.06 Scrapegraph Start Searchscraper — $0.24 Scrapegraph Start Smartcrawler — $0.08 Scrapegraph Start Sitemap — $0.02 Scrapegraph Start Markdownify — $0.06 Scrapegraph Get Searchscraper Status — $0.01 Scrapegraph Get Markdownify Status — $0.01 Scrapegraph Get Sitemap Status — $0.01

Install Skill

Claude Code

claude /install-skill https://xpay.tools/skills/scrapegraph/scrapegraph-start-smartscraper/SKILL.md

CLI

npx @xpaysh/cli install scrapegraph/scrapegraph-start-smartscraper

Manual

curl -o SKILL.md https://xpay.tools/skills/scrapegraph/scrapegraph-start-smartscraper/SKILL.md

Pricing

Cost

$0.08/call

Model

Flat rate

Provider

Scrapegraphai API

Input Parameters

Parameter

Type

Required

Description

headers

object

Optional custom HTTP headers to send with the request. Useful for setting User-Agent, cookies, authentication tokens, and other request metadata. Example: {"User-Agent": "Mozilla/5.0...", "Cookie": "session=abc123"}

website_markdown

string

Raw Markdown content to process directly (max 2MB). Mutually exclusive with website_url and website_html. Perfect for extracting structured data from Markdown documentation, README files, or any content already in Markdown format.

steps

string

Optional array of interaction steps to perform on the webpage before extraction. Each step is a string describing the action to take (e.g., “click on filter button”, “wait for results to load”). Example: ["click on search button", "type query in search box", "wait for results"]

cookies

object

Optional cookies object for authentication and session management. Useful for accessing authenticated pages or maintaining session state. Example: {"session_id": "abc123", "auth_token": "xyz789"}

user_prompt

string

Yes

Natural language description of what information you want to extract from the webpage.

total_pages

number

Optional parameter to enable pagination and scrape multiple pages. Specify the number of pages to extract data from. Default: 1 Range: 1-100

render_heavy_js

boolean

Optional parameter to enable enhanced JavaScript rendering for heavy JS websites (React, Vue, Angular, SPAs). Use when standard rendering doesn’t capture all content. Default: false

number_of_scrolls

number

Optional parameter for infinite scroll pages. Specify how many times to scroll down to load more content before extraction. Default: 0 Range: 0-50

website_html

string

Raw HTML content to process directly (max 2MB). Mutually exclusive with website_url and website_markdown. Useful when you already have HTML content cached or want to process modified HTML.

website_url

string

Yes

The URL of the webpage you want to extract information from. You must provide exactly one of: website_url, website_html, or website_markdown.

stealth

boolean

Enable stealth mode to bypass bot protection using advanced anti-detection techniques. Adds +4 credits to the request cost

output_schema

object

Optional schema to structure the output. If provided, the AI will attempt to format the results according to this schema.

mock

boolean

Optional parameter to enable mock mode. When set to true, the request will return mock data instead of performing an actual extraction. Useful for testing and development. Default: false

Parameter

Type

Required

Description

headers

object

website_markdown

string

steps

string

object

Optional cookies object for authentication and session management. Useful for accessing authenticated pages or maintaining session state. Example: {"session_id": "abc123", "auth_token": "xyz789"}

user_prompt

string

Yes

Natural language description of what information you want to extract from the webpage.

total_pages

number

Optional parameter to enable pagination and scrape multiple pages. Specify the number of pages to extract data from. Default: 1 Range: 1-100

render_heavy_js

boolean

Optional parameter to enable enhanced JavaScript rendering for heavy JS websites (React, Vue, Angular, SPAs). Use when standard rendering doesn’t capture all content. Default: false

number_of_scrolls

number

Optional parameter for infinite scroll pages. Specify how many times to scroll down to load more content before extraction. Default: 0 Range: 0-50

website_html

string

Raw HTML content to process directly (max 2MB). Mutually exclusive with website_url and website_markdown. Useful when you already have HTML content cached or want to process modified HTML.

website_url

string

Yes

The URL of the webpage you want to extract information from. You must provide exactly one of: website_url, website_html, or website_markdown.

stealth

boolean

Enable stealth mode to bypass bot protection using advanced anti-detection techniques. Adds +4 credits to the request cost

output_schema

object

Optional schema to structure the output. If provided, the AI will attempt to format the results according to this schema.

mock

boolean

Optional parameter to enable mock mode. When set to true, the request will return mock data instead of performing an actual extraction. Useful for testing and development. Default: false