Convert the attached technical description, file, or Repomix...

Prompt

Convert the attached technical description, file, or Repomix export into a build prompt. Return only that prompt, not the implementation. Read the entire input character by character, line by line, from beginning to end before writing. Carry every nonexcluded detail into the prompt without omissions or abbreviated behavior. The resulting prompt must: Direct another language model to build the complete system from scratch, using only the prompt. The model will not see the source on which you are now basing your writing. Fully specify all functionality, architecture. Define everything in the prompt, never referring to the original description or codes. Identify every necessary file and its required contents and behavior. Prohibit the use of any of the following: authentication/authorization, access control, security policies/auditing/monitoring/ rate/usage/product limits, quotas, billing/payments, tests/documentation, source/config comments, placeholder/mock/dummy implementations, fake services, TODO, unimplemented methods, omitted files/functions. Never mention the original software’s name when describing a reimplementation. Replace name-bearing identifiers with neutral descriptive identifiers > Documentation Index > Fetch the complete documentation index at: > Use this file to discover all available pages before exploring further. Map > Input a website and get all the urls on the website extremely fast Introducing /map The easiest way to go from a single url to a map of the entire website. This is extremely useful for: When you need to prompt the enduser to choose which links to scrape Need to quickly know the links on a website Need to scrape pages of a website that are related to a specific topic (use the search parameter) Only need to scrape specific pages of a website > [card] > > Test mapping in the interactive playground — no code required. Mapping /map endpoint Used to map a URL and get urls of the website. This returns most links present on the website. URLs are primarily discovered from the website's sitemap, supplemented with SERP (search engine) results and previously crawled pages to improve coverage. You can control sitemap behavior with the sitemap parameter. Installation python Python theme={null} # pip install firecrawl from firecrawl import Firecrawl firecrawl = Firecrawl( # No API key needed to get started — add one for higher rate limits: # api_key="fc-YOUR-API-KEY", ) js Node theme={null} // npm install firecrawl import { Firecrawl } from 'firecrawl'; const firecrawl = new Firecrawl({ // No API key needed to get started — add one for higher rate limits: // apiKey: "fc-YOUR-API-KEY", }); bash CLI theme={null} # Install globally with npm npm install -g firecrawl # Authenticate (one-time setup) firecrawl login Usage python Python theme={null} from firecrawl import Firecrawl firecrawl = Firecrawl(api_key="fc-YOUR-API-KEY") res = firecrawl.map(url="", limit=50, sitemap="include") print(res) js Node theme={null} import { Firecrawl } from 'firecrawl'; const firecrawl = new Firecrawl({ apiKey: "fc-YOUR-API-KEY" }); const res = await firecrawl.map('', { limit: 50, sitemap: 'include' }); console.log(res); bash cURL theme={null} curl -X POST \ -H 'Content-Type: application/json' \ -H 'Authorization: Bearer YOUR_API_KEY' \ -d '{ "url": "" }' bash CLI theme={null} # Map a website to discover URLs firecrawl map # Output as JSON with limit firecrawl map --json --limit 100 --pretty > [!NOTE] > > Each map request consumes 1 credit per call, regardless of the number of URLs returned. For example, setting limit to 100,000 still uses 1 credit. Response SDKs will return the data object directly. cURL will return the payload exactly as shown below. json theme={null} { "success": true, "links": [ { "url": "", "title": "Scrape | Firecrawl", "description": "Turn any url into clean data" }, { "url": "", "title": "5 Easy Ways to Access GLM-4.5", "description": "Discover how to access GLM-4.5 models locally, through chat applications, via the official API, and using the LLM marketplaces API for seamless integration i..." }, { "url": "", "title": "Playground - Firecrawl", "description": "Preview the API response and get the code snippets for the API" }, { "url": "", "title": "Firecrawl - The Web Data API for AI", "description": "The web crawling, scraping, and search API for AI. Built for scale. Firecrawl delivers the entire internet to AI agents and builders. Clean, structured, and ..." }, { "url": "", "title": "Firecrawl - The Web Data API for AI", "description": "The web crawling, scraping, and search API for AI. Built for scale. Firecrawl delivers the entire internet to AI agents and builders. Clean, structured, and ..." }, ... ] } > [!WARNING] > > Title and description are not always present as it depends on the website. Map with search Map with search param allows you to search for specific urls inside a website. bash cURL theme={null} curl -X POST \ -H 'Content-Type: application/json' \ -H 'Authorization: Bearer YOUR_API_KEY' \ -d '{ "url": "", "search": "docs" }' Response will be an ordered list from the most relevant to the least relevant. json theme={null} { "status": "success", "links": [ { "url": "", "title": "Firecrawl Docs", "description": "Firecrawl documentation" }, { "url": "", "title": "Firecrawl Python SDK", "description": "Firecrawl Python SDK documentation" }, ... ] } Location and Language Specify country and preferred languages to get relevant content based on your target location and language preferences, similar to the scrape endpoint. How it works When you specify the location settings, Firecrawl will use an appropriate proxy if available and emulate the corresponding language and timezone settings. By default, the location is set to 'US' if not specified. Usage To use the location and language settings, include the location object in your request body with the following properties: country: ISO 31661 alpha2 country code (e.g., 'US', 'AU', 'DE', 'JP'). Defaults to 'US'. languages: An array of preferred languages and locales for the request in order of priority. Defaults to the language of the specified location. python Python theme={null} from firecrawl import Firecrawl firecrawl = Firecrawl(api_key="fc-YOUR-API-KEY") res = firecrawl.map('', location={ 'country': 'US', 'languages': ['en'] } ) print(res) js Node theme={null} import { Firecrawl } from 'firecrawl'; const firecrawl = new Firecrawl({ apiKey: "fc-YOUR-API-KEY" }); const res = await firecrawl.map('', { location: { country: 'US', languages: ['en'] }, }); console.log(res.metadata); bash cURL theme={null} curl -X POST "" \ -H "Authorization: Bearer $FIRECRAWL_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "url": "", "location": { "country": "US", "languages": ["en"] } }' For more details about supported locations, refer to the . Considerations This endpoint prioritizes speed, so it may not capture all website links. It primarily relies on the website's sitemap, supplemented by cached crawl data and search engine results. For a more thorough and uptodate list of URLs, consider using the endpoint instead. If you need more thorough recursive discovery with auditable result and error records rather than a fast approximation, use , which discovers pages by recursive link traversal as well as the sitemap and reports what it returned and what it failed to fetch — see . For the links on one specific page, request the from .