{ "openapi": "3.0.3", "info": { "title": "Web Scraping API", "version": "1.0.0", "description": "Scrape any URL to raw HTML, clean text, or structured JSON using FlareSolverr for Cloudflare bypass. Two modes: scrape returns the full page content, extract returns only the fields you specify via CSS selectors. Handles JavaScript-rendered pages and bot-protection.\n", "contact": { "name": "Web Scraping API Support", "email": "api@hiroapp.cc" } }, "servers": [ { "url": "https://api.sprytools.com/v1/scraping", "description": "Production (SpryTools API Gateway)" } ], "tags": [ { "name": "Scrape", "description": "Fetch full page content" }, { "name": "Extract", "description": "Extract structured data via CSS selectors" } ], "security": [ { "ApiKeyHeader": [] }, { "RapidApiProxy": [] } ], "paths": { "/api/v1/scrape": { "post": { "operationId": "scrapeUrl", "summary": "Scrape a URL to HTML or text", "description": "Fetch a web page (with Cloudflare bypass via FlareSolverr) and return the raw HTML, clean extracted text, or both. Use `output=html` for raw HTML only, `output=text` for cleaned text only, or omit for both.\n", "tags": [ "Scrape" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ScrapeRequest" }, "example": { "url": "https://example.com", "output": "json", "maxTimeout": 30000 } } } }, "responses": { "200": { "description": "Scraped page content", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ScrapeResult" }, "example": { "url": "https://example.com", "html": "...", "text": "Example Domain This domain is for use in illustrative examples.", "statusCode": 200 } } } }, "400": { "$ref": "#/components/responses/BadRequest" }, "401": { "$ref": "#/components/responses/Unauthorized" }, "429": { "$ref": "#/components/responses/RateLimited" }, "500": { "$ref": "#/components/responses/InternalError" }, "502": { "$ref": "#/components/responses/FlareSolverrError" } } } }, "/api/v1/extract": { "post": { "operationId": "extractSelectors", "summary": "Extract structured data via CSS selectors", "description": "Scrape a URL and extract specific fields using CSS selectors. Provide a `selectors` object mapping field names to CSS selector strings. Returns a data object with one key per selector.\n", "tags": [ "Extract" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ExtractRequest" }, "example": { "url": "https://example.com", "selectors": { "title": "h1", "description": "p" }, "maxTimeout": 30000 } } } }, "responses": { "200": { "description": "Extracted data", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ExtractResult" }, "example": { "url": "https://example.com", "data": { "title": "Example Domain", "description": "This domain is for use in illustrative examples." }, "statusCode": 200 } } } }, "400": { "$ref": "#/components/responses/BadRequest" }, "401": { "$ref": "#/components/responses/Unauthorized" }, "429": { "$ref": "#/components/responses/RateLimited" }, "500": { "$ref": "#/components/responses/InternalError" }, "502": { "$ref": "#/components/responses/FlareSolverrError" } } } } }, "components": { "securitySchemes": { "ApiKeyHeader": { "type": "apiKey", "in": "header", "name": "x-api-key" }, "RapidApiProxy": { "type": "apiKey", "in": "header", "name": "x-rapidapi-proxy-secret" } }, "schemas": { "ScrapeRequest": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "format": "uri", "description": "URL to scrape (http or https only)" }, "output": { "type": "string", "enum": [ "json", "html", "text" ], "default": "json", "description": "Output mode — json returns both html and text fields, html returns only raw HTML, text returns only cleaned text\n" }, "maxTimeout": { "type": "integer", "description": "Maximum wait time in milliseconds (default 30000)", "default": 30000, "minimum": 1000, "maximum": 120000 } } }, "ScrapeResult": { "type": "object", "properties": { "url": { "type": "string", "format": "uri" }, "html": { "type": "string", "nullable": true }, "text": { "type": "string", "nullable": true }, "statusCode": { "type": "integer" } } }, "ExtractRequest": { "type": "object", "required": [ "url", "selectors" ], "properties": { "url": { "type": "string", "format": "uri", "description": "URL to scrape" }, "selectors": { "type": "object", "additionalProperties": { "type": "string" }, "description": "Mapping of field names to CSS selector strings" }, "maxTimeout": { "type": "integer", "description": "Maximum wait time in milliseconds", "default": 30000, "minimum": 1000, "maximum": 120000 } } }, "ExtractResult": { "type": "object", "properties": { "url": { "type": "string", "format": "uri" }, "data": { "type": "object", "additionalProperties": { "type": "string", "nullable": true } }, "statusCode": { "type": "integer" } } }, "Error": { "type": "object", "required": [ "error" ], "properties": { "error": { "type": "string" } } } }, "responses": { "BadRequest": { "description": "Bad request — missing or invalid parameters", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/Error" }, "example": { "error": "url is required" } } } }, "Unauthorized": { "description": "API key missing", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/Error" }, "example": { "error": "API key required" } } } }, "RateLimited": { "description": "Rate limit exceeded (100 requests per minute)", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/Error" }, "example": { "error": "Rate limit exceeded" } } } }, "InternalError": { "description": "Internal scraping error", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/Error" }, "example": { "error": "Scraping failed" } } } }, "FlareSolverrError": { "description": "FlareSolverr upstream error (Cloudflare bypass service unavailable)", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/Error" }, "example": { "error": "FlareSolverr request failed: connection refused" } } } } } } }