Listing Page Extraction · MrScraper

Start with a listing, catalog or search-results URL to request information about its repeated items. Choose a page limit and, if useful, describe what to extract. Review the returned records together; their contents and coverage depend on what 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-listing-pages-mrscraper (Tool ID a671897d-626d-4ebb-8fbd-e9158b6f1218) and check current availability, inputs and cost against my authorized budget. Ask only for the actual listing URL if missing. Prepare {"body":{"url":"<my actual listing URL>"}} and set the requested maxPages explicitly within 1–20; it is a page limit, not guaranteed coverage. Add prompt or loading, resource and country options only when useful, explaining important values. A prompt parses content already fetched; it cannot control navigation or create missing information. Execute only within my authorized budget. Organize actual returned records, preserve source context and missing values, and distinguish your formatting or interpretation from source data. Report the actual outcome and confirmed cost, or state when they are unconfirmed.

Task:
Please make a clear list of the items on this page: [paste the listing page link]. If the list continues, check up to [number of pages]. Keep each item’s shown details together and mark what is missing.

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

Listing Page Extraction · MrScraper

You receive

Listing records from the URL you provide and any accessible pagination within your requested limit. The information describes the items exposed on those listing pages, with details varying by source. Your Agent can arrange the actual returned records for review and retain source links or context when provided.

Start with your task

Please make a clear list of the items on this page: [paste the listing page link]. If the list continues, check up to [number of pages]. Keep each item’s shown details together and mark what is missing.

What to know

A page limit does not guarantee that every requested page or item will be retrieved. A prompt cannot steer navigation or supply information that was not fetched. Listing information does not establish the contents of individual detail pages, complete catalog coverage or a uniform field set across websites.

Inputs & outputs

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

Input schema

Input schema
Field / Path	Type	Requirement	Meaning
Listing request`body`	`object`	Required	Required object containing url and optional extraction or loading settings. Only defined properties are accepted; url is the only required child. Required fields `url`
Starting listing URL`body.url`	`string`	Required	Required full URI for the listing to examine, including http:// or https:// as described by the supplier. No default URL. A valid URI does not establish that the page is accessible or suitable for extraction. Format `uri`
Real-device routing`body.super`	`boolean`	Optional	Optional boolean for requesting real-device routing under difficult access conditions. Supplier-described default: false. It consumes more upstream resources and tokens; access is not guaranteed.
Information to parse`body.prompt`	`string`	Optional	Optional nonempty string describing desired information, fields or form. It parses only already scraped content. It cannot steer the scraper, change site filters or obtain missing source information. Minimum length `1`
Page access country`body.geoCode`	`string`	Optional	Optional string of exactly two characters selecting the country from which to load the page. Supplier-described default: us. It requests context rather than proving a returned language, currency or regional catalog. Minimum length `2` Maximum length `2`
Page-load timeout`body.timeout`	`integer`	Optional	Optional integer from 1 to 300 seconds for waiting on page loading. Supplier-described default: 300. It is not the requested page count or proof that every update and listing item has loaded. Minimum `1` Maximum `300`
Maximum listing pages`body.maxPages`	`integer`	Optional	Optional integer from 1 to 20 limiting requested pagination. Each additional page adds runtime and AI token usage. No default is defined in the current schema or description. The cap guarantees neither a page count nor complete item coverage. Minimum `1` Maximum `20`
Navigation completion event`body.waitUntil`	`string`	Optional	Optional browser-rendering string: domcontentloaded, load, networkidle0 or networkidle2. Supplier-described default: domcontentloaded; networkidle0 is described as most thorough but slowest. Later content may still change. Options `domcontentloaded, load, networkidle0, networkidle2`
Proxy exit country`body.proxyCountry`	`string`	Optional	Optional string of exactly two characters for the proxy exit country. Supplier-described default: us. It is separate from geoCode and does not verify a local offer, language or complete localized result set. Minimum length `2` Maximum length `2`
Skip images, fonts and styles`body.blockResources`	`boolean`	Optional	Optional boolean for skipping images, fonts and stylesheets while loading. Supplier-described default: false. This can reduce bandwidth usage but changes loaded resources; check whether the needed listing content depends on them.
Element to wait for`body.waitForSelector`	`string`	Optional	Optional nonempty CSS-selector string. Waits for its appearance in the DOM before extraction, for content arriving after initial loading. Appearance does not prove final content or complete pagination. Minimum length `1`
Browser rendering`body.browserRendering`	`boolean`	Optional	Optional boolean for loading in Chromium and rendering JavaScript-dependent content. Supplier-described default: false. Use when the needed listing content requires it; this setting alone does not guarantee access or all items.

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)."
        },
        "maxPages": {
          "type": "integer",
          "maximum": 20,
          "minimum": 1,
          "description": "Maximum listing pages to paginate through (1-20). Each page adds runtime and AI tokens to the run's cost."
        },
        "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

This task starts from one listing URL and requests repeating entries from listings, catalogs or search results. The information available is determined by the listing content the source can retrieve. It is a way to review items together, rather than evidence that every page on a website was examined.

maxPages is an optional integer from 1 to 20 that limits requested pagination. It is not a result count or proof that a particular number of pages was retrieved. Supply important scope explicitly: the current input description does not define a maxPages default, and sites can differ in how they expose more items.

An optional prompt describes the information to parse or how to arrange it. It works on content already fetched and cannot direct clicks, select new filters or obtain detail-page information that was not retrieved. Requested fields that the source does not supply must remain missing.

Browser rendering and navigation or selector waits choose loading conditions; a selector appearing does not prove its content is complete. Resource blocking changes what loads, and country, proxy or real-device routing requests an access context. These settings cannot guarantee page access, local offers or complete extraction.

Review actual records before comparing or counting them. Preserve any currency, units, links and source context that are supplied. A listing may repeat an item; any Agent sorting or deduplication is a separate interpretation and should use stated criteria, not assumed uniqueness or ranking.

MrScraper listing extraction guidance

Questions about this tool.

Inputs, results and details to know before running it.

Get connected

No. It caps requested pagination between 1 and 20 pages. Fewer pages or items may be returned because of the source and its loading behavior. Review the actual scope before claiming completeness; the page limit is not a total item count.

Listing Page Extraction · MrScraper

Listing Page Extraction · MrScraper

You receive

Start with your task

What to know

Inputs & outputs

Input schema

Result schema

Choose the page with the items

Choose how many pages to check

Check the list against the original page

Questions about this tool.

You receive

Start with your task

What to know

Inputs & outputs

Input schema

Result schema

Choose the page with the items

Choose how many pages to check

Check the list against the original page

Questions about this tool.

Does maxPages mean the entire catalog will be collected?

Can a prompt open each item and collect detail-page fields?

Are returned entries unique or ordered as a ranking?

Does an empty or partial result prove there are no more items?