Update openapi.json
This commit is contained in:
Nicolas
parent
3ead2efdca
commit
de7e1f501b
|
|
@ -1,295 +1,309 @@
|
|||
{
|
||||
"openapi": "3.0.0",
|
||||
"info": {
|
||||
"title": "Firecrawl API",
|
||||
"version": "1.0.0",
|
||||
"description": "API for interacting with Firecrawl services to convert websites to LLM-ready data.",
|
||||
"contact": {
|
||||
"name": "Firecrawl Support",
|
||||
"url": "https://firecrawl.dev/support",
|
||||
"email": "help@mendable.ai"
|
||||
}
|
||||
},
|
||||
"servers": [
|
||||
{
|
||||
"url": "https://api.firecrawl.dev/v0"
|
||||
}
|
||||
],
|
||||
"paths": {
|
||||
"/scrape": {
|
||||
"post": {
|
||||
"summary": "Scrape a single URL",
|
||||
"operationId": "scrapeSingleUrl",
|
||||
"tags": ["Scraping"],
|
||||
"security": [
|
||||
{
|
||||
"bearerAuth": []
|
||||
}
|
||||
],
|
||||
"requestBody": {
|
||||
"required": true,
|
||||
"content": {
|
||||
"application/json": {
|
||||
"schema": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"url": {
|
||||
"type": "string",
|
||||
"format": "uri",
|
||||
"description": "The URL to scrape"
|
||||
}
|
||||
},
|
||||
"required": ["url"]
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"responses": {
|
||||
"200": {
|
||||
"description": "Successful response",
|
||||
"content": {
|
||||
"application/json": {
|
||||
"schema": {
|
||||
"$ref": "#/components/schemas/ScrapeResponse"
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"402": {
|
||||
"description": "Payment required"
|
||||
},
|
||||
"429": {
|
||||
"description": "Too many requests"
|
||||
},
|
||||
"500": {
|
||||
"description": "Server error"
|
||||
}
|
||||
"openapi": "3.0.0",
|
||||
"info": {
|
||||
"title": "Firecrawl API",
|
||||
"version": "1.0.0",
|
||||
"description": "API for interacting with Firecrawl services to perform web scraping and crawling tasks.",
|
||||
"contact": {
|
||||
"name": "Firecrawl Support",
|
||||
"url": "https://firecrawl.dev/support",
|
||||
"email": "support@firecrawl.dev"
|
||||
}
|
||||
},
|
||||
"servers": [
|
||||
{
|
||||
"url": "https://api.firecrawl.dev/v0"
|
||||
}
|
||||
],
|
||||
"paths": {
|
||||
"/scrape": {
|
||||
"post": {
|
||||
"summary": "Scrape a single URL",
|
||||
"operationId": "scrapeSingleUrl",
|
||||
"tags": ["Scraping"],
|
||||
"security": [
|
||||
{
|
||||
"bearerAuth": []
|
||||
}
|
||||
}
|
||||
},
|
||||
"/crawl": {
|
||||
"post": {
|
||||
"summary": "Crawl multiple URLs based on options",
|
||||
"operationId": "crawlUrls",
|
||||
"tags": ["Crawling"],
|
||||
"security": [
|
||||
{
|
||||
"bearerAuth": []
|
||||
}
|
||||
],
|
||||
"requestBody": {
|
||||
"required": true,
|
||||
"content": {
|
||||
"application/json": {
|
||||
"schema": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"url": {
|
||||
"type": "string",
|
||||
"format": "uri",
|
||||
"description": "The base URL to start crawling from"
|
||||
},
|
||||
"crawlerOptions": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"includes": {
|
||||
"type": "array",
|
||||
"items": {
|
||||
"type": "string"
|
||||
},
|
||||
"description": "URL patterns to include"
|
||||
},
|
||||
"excludes": {
|
||||
"type": "array",
|
||||
"items": {
|
||||
"type": "string"
|
||||
},
|
||||
"description": "URL patterns to exclude"
|
||||
},
|
||||
"generateImgAltText": {
|
||||
"type": "boolean",
|
||||
"description": "Generate alt text for images using LLMs (must have a paid plan)",
|
||||
"default": false
|
||||
},
|
||||
"limit": {
|
||||
"type": "integer",
|
||||
"description": "Maximum number of pages to crawl"
|
||||
}
|
||||
}
|
||||
},
|
||||
"pageOptions": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"onlyMainContent": {
|
||||
"type": "boolean",
|
||||
"description": "Only return the main content of the page excluding headers, navs, footers, etc.",
|
||||
"default": false
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"required": ["url"]
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"responses": {
|
||||
"200": {
|
||||
"description": "Successful response",
|
||||
"content": {
|
||||
"application/json": {
|
||||
"schema": {
|
||||
"$ref": "#/components/schemas/CrawlResponse"
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"402": {
|
||||
"description": "Payment required"
|
||||
},
|
||||
"429": {
|
||||
"description": "Too many requests"
|
||||
},
|
||||
"500": {
|
||||
"description": "Server error"
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"/crawl/status/{jobId}": {
|
||||
"get": {
|
||||
"tags": ["Crawl"],
|
||||
"summary": "Get the status of a crawl job",
|
||||
"operationId": "getCrawlStatus",
|
||||
"security": [
|
||||
{
|
||||
"bearerAuth": []
|
||||
}
|
||||
],
|
||||
"parameters": [
|
||||
{
|
||||
"name": "jobId",
|
||||
"in": "path",
|
||||
"description": "ID of the crawl job",
|
||||
"required": true,
|
||||
],
|
||||
"requestBody": {
|
||||
"required": true,
|
||||
"content": {
|
||||
"application/json": {
|
||||
"schema": {
|
||||
"type": "string"
|
||||
}
|
||||
}
|
||||
],
|
||||
"responses": {
|
||||
"200": {
|
||||
"description": "Successful response",
|
||||
"content": {
|
||||
"application/json": {
|
||||
"schema": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"url": {
|
||||
"type": "string",
|
||||
"format": "uri",
|
||||
"description": "The URL to scrape"
|
||||
},
|
||||
"pageOptions": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"status": {
|
||||
"type": "string",
|
||||
"description": "Status of the job (completed, active, failed, paused)"
|
||||
},
|
||||
"current": {
|
||||
"type": "integer",
|
||||
"description": "Current page number"
|
||||
},
|
||||
"current_url": {
|
||||
"type": "string",
|
||||
"description": "Current URL being scraped"
|
||||
},
|
||||
"current_step": {
|
||||
"type": "string",
|
||||
"description": "Current step in the process"
|
||||
},
|
||||
"total": {
|
||||
"type": "integer",
|
||||
"description": "Total number of pages"
|
||||
},
|
||||
"data": {
|
||||
"type": "array",
|
||||
"items": {
|
||||
"$ref": "#/components/schemas/ScrapeResponse"
|
||||
},
|
||||
"description": "Data returned from the job (null when it is in progress)"
|
||||
"onlyMainContent": {
|
||||
"type": "boolean",
|
||||
"description": "Only return the main content of the page excluding headers, navs, footers, etc.",
|
||||
"default": false
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"402": {
|
||||
"description": "Payment required"
|
||||
},
|
||||
"429": {
|
||||
"description": "Too many requests"
|
||||
},
|
||||
"500": {
|
||||
"description": "Server error"
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"components": {
|
||||
"securitySchemes": {
|
||||
"bearerAuth": {
|
||||
"type": "http",
|
||||
"scheme": "bearer"
|
||||
}
|
||||
},
|
||||
"schemas": {
|
||||
"ScrapeResponse": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"success": {
|
||||
"type": "boolean"
|
||||
},
|
||||
"data": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"content": {
|
||||
"type": "string"
|
||||
},
|
||||
"markdown": {
|
||||
"type": "string"
|
||||
},
|
||||
"metadata": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"title": {
|
||||
"type": "string"
|
||||
},
|
||||
"description": {
|
||||
"type": "string"
|
||||
},
|
||||
"language": {
|
||||
"type": "string",
|
||||
"nullable": true
|
||||
},
|
||||
"sourceURL": {
|
||||
"type": "string",
|
||||
"format": "uri"
|
||||
}
|
||||
}
|
||||
}
|
||||
"required": ["url"]
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"CrawlResponse": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"jobId": {
|
||||
"type": "string"
|
||||
"responses": {
|
||||
"200": {
|
||||
"description": "Successful response",
|
||||
"content": {
|
||||
"application/json": {
|
||||
"schema": {
|
||||
"$ref": "#/components/schemas/ScrapeResponse"
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"402": {
|
||||
"description": "Payment required"
|
||||
},
|
||||
"429": {
|
||||
"description": "Too many requests"
|
||||
},
|
||||
"500": {
|
||||
"description": "Server error"
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"security": [
|
||||
{
|
||||
"bearerAuth": []
|
||||
"/crawl": {
|
||||
"post": {
|
||||
"summary": "Crawl multiple URLs based on options",
|
||||
"operationId": "crawlUrls",
|
||||
"tags": ["Crawling"],
|
||||
"security": [
|
||||
{
|
||||
"bearerAuth": []
|
||||
}
|
||||
],
|
||||
"requestBody": {
|
||||
"required": true,
|
||||
"content": {
|
||||
"application/json": {
|
||||
"schema": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"url": {
|
||||
"type": "string",
|
||||
"format": "uri",
|
||||
"description": "The base URL to start crawling from"
|
||||
},
|
||||
"crawlerOptions": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"includes": {
|
||||
"type": "array",
|
||||
"items": {
|
||||
"type": "string"
|
||||
},
|
||||
"description": "URL patterns to include"
|
||||
},
|
||||
"excludes": {
|
||||
"type": "array",
|
||||
"items": {
|
||||
"type": "string"
|
||||
},
|
||||
"description": "URL patterns to exclude"
|
||||
},
|
||||
"generateImgAltText": {
|
||||
"type": "boolean",
|
||||
"description": "Generate alt text for images using LLMs (must have a paid plan)",
|
||||
"default": false
|
||||
},
|
||||
"returnOnlyUrls": {
|
||||
"type": "boolean",
|
||||
"description": "If true, returns only the URLs as a list on the crawl status. Attention: the return response will be a list of URLs inside the data, not a list of documents.",
|
||||
"default": false
|
||||
},
|
||||
"limit": {
|
||||
"type": "integer",
|
||||
"description": "Maximum number of pages to crawl"
|
||||
}
|
||||
}
|
||||
},
|
||||
"pageOptions": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"onlyMainContent": {
|
||||
"type": "boolean",
|
||||
"description": "Only return the main content of the page excluding headers, navs, footers, etc.",
|
||||
"default": false
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"required": ["url"]
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"responses": {
|
||||
"200": {
|
||||
"description": "Successful response",
|
||||
"content": {
|
||||
"application/json": {
|
||||
"schema": {
|
||||
"$ref": "#/components/schemas/CrawlResponse"
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"402": {
|
||||
"description": "Payment required"
|
||||
},
|
||||
"429": {
|
||||
"description": "Too many requests"
|
||||
},
|
||||
"500": {
|
||||
"description": "Server error"
|
||||
}
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
|
||||
},
|
||||
"/crawl/status/{jobId}": {
|
||||
"get": {
|
||||
"tags": ["Crawl"],
|
||||
"summary": "Get the status of a crawl job",
|
||||
"operationId": "getCrawlStatus",
|
||||
"security": [
|
||||
{
|
||||
"bearerAuth": []
|
||||
}
|
||||
],
|
||||
"parameters": [
|
||||
{
|
||||
"name": "jobId",
|
||||
"in": "path",
|
||||
"description": "ID of the crawl job",
|
||||
"required": true,
|
||||
"schema": {
|
||||
"type": "string"
|
||||
}
|
||||
}
|
||||
],
|
||||
"responses": {
|
||||
"200": {
|
||||
"description": "Successful response",
|
||||
"content": {
|
||||
"application/json": {
|
||||
"schema": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"status": {
|
||||
"type": "string",
|
||||
"description": "Status of the job (completed, active, failed, paused)"
|
||||
},
|
||||
"current": {
|
||||
"type": "integer",
|
||||
"description": "Current page number"
|
||||
},
|
||||
"current_url": {
|
||||
"type": "string",
|
||||
"description": "Current URL being scraped"
|
||||
},
|
||||
"current_step": {
|
||||
"type": "string",
|
||||
"description": "Current step in the process"
|
||||
},
|
||||
"total": {
|
||||
"type": "integer",
|
||||
"description": "Total number of pages"
|
||||
},
|
||||
"data": {
|
||||
"type": "array",
|
||||
"items": {
|
||||
"$ref": "#/components/schemas/ScrapeResponse"
|
||||
},
|
||||
"description": "Data returned from the job (null when it is in progress)"
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"402": {
|
||||
"description": "Payment required"
|
||||
},
|
||||
"429": {
|
||||
"description": "Too many requests"
|
||||
},
|
||||
"500": {
|
||||
"description": "Server error"
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"components": {
|
||||
"securitySchemes": {
|
||||
"bearerAuth": {
|
||||
"type": "http",
|
||||
"scheme": "bearer"
|
||||
}
|
||||
},
|
||||
"schemas": {
|
||||
"ScrapeResponse": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"success": {
|
||||
"type": "boolean"
|
||||
},
|
||||
"data": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"content": {
|
||||
"type": "string"
|
||||
},
|
||||
"markdown": {
|
||||
"type": "string"
|
||||
},
|
||||
"metadata": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"title": {
|
||||
"type": "string"
|
||||
},
|
||||
"description": {
|
||||
"type": "string"
|
||||
},
|
||||
"language": {
|
||||
"type": "string",
|
||||
"nullable": true
|
||||
},
|
||||
"sourceURL": {
|
||||
"type": "string",
|
||||
"format": "uri"
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"CrawlResponse": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"jobId": {
|
||||
"type": "string"
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"security": [
|
||||
{
|
||||
"bearerAuth": []
|
||||
}
|
||||
]
|
||||
}
|
||||
|
|
|
|||
Loading…
Reference in New Issue