Detail Page Extraction · MrScraper

Provide one detail-page URL to request extracted information about its product, property, hotel, job or article. You can optionally describe the information you need and choose page-loading settings. The returned details depend on the content the source can retrieve.

Your AI

Use with your AI

For tasks with several steps, continue in the AI you already use.

CodexClaude CodeCursorWindsurfCline

View instructions

Reuse my existing Toolmu connection; if setup is needed, follow https://toolmu.com/SKILL.md. Use get_tool for extract-detail-page-mrscraper (Tool ID 788ff74f-c8f2-423c-a149-1779037bae3f), then check its current availability, input requirements and cost against my authorized budget. Ask for the actual page URL only if it is missing. Use {"body":{"url":"<my actual detail-page URL>"}} and add optional prompt, browserRendering, waitForSelector, waitUntil, timeout, blockResources, geoCode, proxyCountry or super only when useful for this task. Explain the chosen settings and set important values explicitly. A prompt describes how to parse content already fetched; it cannot steer navigation or invent missing information. Run only within my authorized budget. Organize the actual returned details, preserve missing values and distinguish your interpretation from source information. Report the actual outcome and confirmed cost, or say when either is unconfirmed.

Task:
Please list the key details from this page: [paste the page link]. If you want specific information, add it in everyday words: [what you want to know]. Mark anything the page does not show.

Paste into your connected AI's conversation.

Connection guide

Up to 120 credits / call

The final charge is based on confirmed usage. Unused reserved credits return to your available balance.

MrScraper

Detail Page Extraction · MrScraper

You receive

Extracted detail-page information from the single URL you provide, when the source can retrieve and parse the page. The extractor adapts the information to the page type; your Agent can organize the actual returned details into a readable record. An optional prompt describes the desired fields or form using the content already fetched.

Start with your task

Please list the key details from this page: [paste the page link]. If you want specific information, add it in everyday words: [what you want to know]. Mark anything the page does not show.

What to know

A prompt cannot make the scraper click, navigate or obtain information the page did not expose. Rendering and waiting options help choose how the page loads but do not guarantee complete content or access. Field availability varies by page. This single-page task does not establish a full-site inventory or a uniform set of fields across websites.

Inputs & outputs

Inspect the current inputs, availability, and maximum charge before starting.

Input schema

Input schema
Field / Path	Type	Requirement	Meaning
Detail-page request`body`	`object`	Required	Required object containing url and any useful optional parsing or loading settings. Only the documented properties are accepted; url is the only required child. Required fields `url`
Page URL`body.url`	`string`	Required	Required full URI for the single page to extract, including http:// or https:// as described by the supplier. There is no default URL. Format validity does not guarantee access or complete page content. Format `uri`
Real-device routing`body.super`	`boolean`	Optional	Optional boolean requesting real-device routing for difficult access conditions. Supplier-described default: false. It uses more upstream resources and can increase token usage; it does not guarantee that a page will be accessible.
Information to extract`body.prompt`	`string`	Optional	Optional nonempty string describing the desired information, field names or form. It parses only content already scraped and cannot steer the scraper, navigate elsewhere or create missing source values. Minimum length `1`
Page access country`body.geoCode`	`string`	Optional	Optional string of exactly two characters for the country from which to load the page. Supplier-described default: us. It requests an access context; it does not prove a particular language, currency or localized page version was returned. Minimum length `2` Maximum length `2`
Page-load time limit`body.timeout`	`integer`	Optional	Optional integer from 1 to 300, measured in seconds. It limits how long to wait for page loading. Supplier-described default: 300. A longer deadline does not guarantee all dynamic content or successful extraction. Minimum `1` Maximum `300`
Navigation completion event`body.waitUntil`	`string`	Optional	Optional string for browser rendering only: domcontentloaded, load, networkidle0 or networkidle2. Supplier-described default: domcontentloaded; networkidle0 is described as the most thorough and slowest option. The chosen event does not establish that every later page update is complete. Options `domcontentloaded, load, networkidle0, networkidle2`
Proxy exit country`body.proxyCountry`	`string`	Optional	Optional string of exactly two characters specifying the proxy exit country. Supplier-described default: us. Keep it distinct from geoCode and do not treat the requested country as verification of a returned local offer or page language. Minimum length `2` Maximum length `2`
Skip page resources`body.blockResources`	`boolean`	Optional	Optional boolean to skip images, fonts and stylesheets during loading. Supplier-described default: false. This can reduce bandwidth use, but changes what is loaded; use it only when those resources are not needed for the requested extraction.
Element to wait for`body.waitForSelector`	`string`	Optional	Optional nonempty CSS-selector string. It requests waiting until that selector appears in the DOM before extraction, for content arriving after the initial page. Presence alone does not confirm the element's final contents or every requested value. Minimum length `1`
Browser rendering`body.browserRendering`	`boolean`	Optional	Optional boolean to load the page in Chromium and render JavaScript-dependent content. Supplier-described default: false. Enable it when the needed content requires browser rendering; it does not guarantee page access, interaction or completeness.

View raw JSON

{
  "type": "object",
  "required": [
    "body"
  ],
  "properties": {
    "body": {
      "type": "object",
      "$schema": "https://json-schema.org/draft/2020-12/schema",
      "required": [
        "url"
      ],
      "~standard": {
        "vendor": "zod",
        "version": 1,
        "jsonSchema": {}
      },
      "properties": {
        "url": {
          "type": "string",
          "format": "uri",
          "description": "Full URL to scrape, including the http:// or https:// scheme."
        },
        "super": {
          "type": "boolean",
          "description": "Route through real devices to bypass hard anti-bot protection. Uses more upstream resources, so runs consume more tokens. Default false."
        },
        "prompt": {
          "type": "string",
          "minLength": 1,
          "description": "Natural-language description of the data to extract (field names, shape). Parses the scraped content only — it cannot steer the scraper itself."
        },
        "geoCode": {
          "type": "string",
          "maxLength": 2,
          "minLength": 2,
          "description": "Two-letter country code to load the page from (default 'us')."
        },
        "timeout": {
          "type": "integer",
          "maximum": 300,
          "minimum": 1,
          "description": "Maximum seconds to wait for the page to fully load (default 300)."
        },
        "waitUntil": {
          "enum": [
            "domcontentloaded",
            "load",
            "networkidle0",
            "networkidle2"
          ],
          "type": "string",
          "description": "When the browser considers navigation complete (browser rendering only). 'networkidle0' is the most thorough but slowest. Default 'domcontentloaded'."
        },
        "proxyCountry": {
          "type": "string",
          "maxLength": 2,
          "minLength": 2,
          "description": "Two-letter country code of the proxy exit (default 'us')."
        },
        "blockResources": {
          "type": "boolean",
          "description": "Skip images, fonts, and stylesheets to speed up scraping and cut bandwidth-driven token usage. Default false."
        },
        "waitForSelector": {
          "type": "string",
          "minLength": 1,
          "description": "Wait until this CSS selector appears in the DOM before extracting — for content that loads after the initial page."
        },
        "browserRendering": {
          "type": "boolean",
          "description": "Render the page in a real Chromium browser. Required for JavaScript-heavy sites and SPAs. Default false."
        }
      },
      "additionalProperties": false
    }
  },
  "additionalProperties": false
}

Result schema

Output fields have not been documented yet.

Additional notes

The request covers one full page URL. The detail extractor is intended for product, property, hotel, job and article pages. The information available varies with the page type and accessible content; a single request is not a site crawl or a request for every linked detail page.

The optional prompt describes information to extract or how to arrange it. It only affects parsing of the content already fetched. It cannot control the scraper, open tabs, click through the site or create a value that the source did not provide.

Browser rendering loads the page in Chromium for JavaScript-dependent content. A navigation event or selector wait can help target when extraction occurs. The timeout is a page-load limit in seconds, not proof that every later update has completed. Waiting for a selector means waiting for its presence, not verifying all desired information.

Resource blocking skips images, fonts and stylesheets, which can change what is loaded. Country and proxy options select the requested access context, while super requests real-device routing with greater resource use. None of these options guarantees access, a particular localized offer or complete extraction.

Defaults mentioned in the input descriptions are supplier-described behavior; select important settings explicitly. Review the actual returned details and preserve missing or conflicting information. Your Agent can format the record or explain it, but that presentation does not create additional source fields.

General MrScraper Marketplace guidance

Questions about this tool.

Inputs, results and details to know before running it.

Get connected

No. A prompt describes what to parse from content already fetched. It cannot steer page navigation, click a tab or make unavailable information appear. Request the details you need, then keep any value not supplied by the source marked as missing.

Detail Page Extraction · MrScraper

Detail Page Extraction · MrScraper

You receive

Start with your task

What to know

Inputs & outputs

Input schema

Result schema

Choose the page to check

Say what you would like to know

Check the details against the page

Questions about this tool.

You receive

Start with your task

What to know

Inputs & outputs

Input schema

Result schema

Choose the page to check

Say what you would like to know

Check the details against the page

Questions about this tool.

Can a prompt make the scraper click or reveal hidden information?

Does rendering or waiting guarantee the whole page is ready?

Do country options guarantee local prices or language?

Will one request collect all linked pages with the same fields?