{ "service": "scrape_do", "displayName": "Scrape.do", "categories": [ "Developer Tools", "Data" ], "authTypes": [ "api_key" ], "auth": [ { "type": "api_key", "label": "API Token", "placeholder": "SCRAPE_DO_TOKEN", "description": "Scrape.do API token passed as the token query parameter. Create or copy it from the Scrape.do dashboard.", "extraFields": [] } ], "homepageUrl": "https://scrape.do", "actions": [ { "id": "scrape_do.fetch_html", "service": "scrape_do", "name": "fetch_html", "description": "Fetch one public URL through Scrape.do and return the synchronous response body.", "requiredScopes": [], "providerPermissions": [], "inputSchema": { "type": "object", "properties": { "url": { "type": "string", "description": "The public target URL Scrape.do should request.", "format": "uri" }, "super": { "type": "boolean", "description": "Whether Scrape.do should use residential and mobile proxy networks." }, "geoCode": { "type": "string", "minLength": 2, "maxLength": 2, "description": "The two-letter country code used for Scrape.do geo-targeting.", "pattern": "^[A-Za-z]{2}$" }, "regionalGeoCode": { "type": "string", "minLength": 2, "description": "The continent code used for Scrape.do regional geo-targeting." }, "sessionId": { "type": "integer", "minimum": 1, "description": "The sticky Scrape.do session identifier." }, "render": { "type": "boolean", "description": "Whether Scrape.do should render the page with a headless browser." }, "device": { "type": "string", "enum": [ "desktop", "mobile", "tablet" ], "description": "The browser device profile Scrape.do should emulate." }, "width": { "type": "integer", "minimum": 1, "description": "The browser viewport width in pixels." }, "height": { "type": "integer", "minimum": 1, "description": "The browser viewport height in pixels." }, "blockResources": { "type": "boolean", "description": "Whether Scrape.do should block CSS, image, and font resources while rendering." }, "timeout": { "type": "integer", "minimum": 5000, "maximum": 120000, "description": "The maximum Scrape.do request timeout in milliseconds." }, "retryTimeout": { "type": "integer", "minimum": 5000, "maximum": 55000, "description": "The maximum Scrape.do retry timeout in milliseconds." }, "disableRetry": { "type": "boolean", "description": "Whether Scrape.do should disable its retry mechanism." }, "disableRedirection": { "type": "boolean", "description": "Whether Scrape.do should disable target request redirection." }, "setCookies": { "type": "string", "minLength": 1, "description": "The Cookie header value Scrape.do should send to the target website." }, "customHeaders": { "type": "boolean", "description": "Whether Scrape.do should handle all request headers." }, "forwardHeaders": { "type": "boolean", "description": "Whether Scrape.do should forward caller headers to the target." }, "output": { "type": "string", "enum": [ "raw", "markdown" ], "description": "The Scrape.do output format for page content." } }, "additionalProperties": false, "required": [ "url" ], "description": "Common synchronous Scrape.do API parameters." }, "outputSchema": { "type": "object", "properties": { "content": { "type": "string", "description": "The response body returned by Scrape.do." }, "statusCode": { "type": "integer", "description": "The HTTP status code returned by Scrape.do." }, "headers": { "type": "object", "additionalProperties": { "type": "string", "description": "One HTTP response header value." }, "description": "The HTTP response headers returned by Scrape.do or the target website." }, "metadata": { "type": "object", "properties": { "statusCode": { "type": "integer", "description": "The HTTP status code returned by Scrape.do." }, "requestCost": { "anyOf": [ { "type": "integer", "description": "The Scrape.do credit cost reported for this request." }, { "type": "null" } ] }, "remainingCredits": { "anyOf": [ { "type": "integer", "description": "The remaining Scrape.do credits reported after this request." }, { "type": "null" } ] }, "contentType": { "anyOf": [ { "type": "string", "description": "The response Content-Type header when returned." }, { "type": "null" } ] }, "finalUrl": { "anyOf": [ { "type": "string", "description": "The final response URL observed by the connector." }, { "type": "null" } ] } }, "additionalProperties": false, "description": "Metadata collected from Scrape.do response headers." } }, "additionalProperties": false, "description": "The response returned by a synchronous Scrape.do request." } }, { "id": "scrape_do.fetch_json", "service": "scrape_do", "name": "fetch_json", "description": "Fetch one public URL through Scrape.do returnJSON mode and return the parsed JSON payload.", "requiredScopes": [], "providerPermissions": [], "inputSchema": { "type": "object", "properties": { "url": { "type": "string", "description": "The public target URL Scrape.do should request.", "format": "uri" }, "super": { "type": "boolean", "description": "Whether Scrape.do should use residential and mobile proxy networks." }, "geoCode": { "type": "string", "minLength": 2, "maxLength": 2, "description": "The two-letter country code used for Scrape.do geo-targeting.", "pattern": "^[A-Za-z]{2}$" }, "regionalGeoCode": { "type": "string", "minLength": 2, "description": "The continent code used for Scrape.do regional geo-targeting." }, "sessionId": { "type": "integer", "minimum": 1, "description": "The sticky Scrape.do session identifier." }, "render": { "type": "boolean", "description": "Whether Scrape.do should render the page with a headless browser." }, "device": { "type": "string", "enum": [ "desktop", "mobile", "tablet" ], "description": "The browser device profile Scrape.do should emulate." }, "width": { "type": "integer", "minimum": 1, "description": "The browser viewport width in pixels." }, "height": { "type": "integer", "minimum": 1, "description": "The browser viewport height in pixels." }, "blockResources": { "type": "boolean", "description": "Whether Scrape.do should block CSS, image, and font resources while rendering." }, "timeout": { "type": "integer", "minimum": 5000, "maximum": 120000, "description": "The maximum Scrape.do request timeout in milliseconds." }, "retryTimeout": { "type": "integer", "minimum": 5000, "maximum": 55000, "description": "The maximum Scrape.do retry timeout in milliseconds." }, "disableRetry": { "type": "boolean", "description": "Whether Scrape.do should disable its retry mechanism." }, "disableRedirection": { "type": "boolean", "description": "Whether Scrape.do should disable target request redirection." }, "setCookies": { "type": "string", "minLength": 1, "description": "The Cookie header value Scrape.do should send to the target website." }, "customHeaders": { "type": "boolean", "description": "Whether Scrape.do should handle all request headers." }, "forwardHeaders": { "type": "boolean", "description": "Whether Scrape.do should forward caller headers to the target." }, "output": { "type": "string", "enum": [ "raw", "markdown" ], "description": "The Scrape.do output format for page content." }, "showFrames": { "type": "boolean", "description": "Whether Scrape.do should include iframe content when render and returnJSON are enabled." }, "showWebsocketRequests": { "type": "boolean", "description": "Whether Scrape.do should include WebSocket requests when render and returnJSON are enabled." } }, "additionalProperties": false, "required": [ "url" ], "description": "The input payload for fetching a Scrape.do returnJSON response." }, "outputSchema": { "type": "object", "properties": { "data": { "description": "The parsed JSON payload returned by Scrape.do." }, "statusCode": { "type": "integer", "description": "The HTTP status code returned by Scrape.do." }, "headers": { "type": "object", "additionalProperties": { "type": "string", "description": "One HTTP response header value." }, "description": "The HTTP response headers returned by Scrape.do or the target website." }, "metadata": { "type": "object", "properties": { "statusCode": { "type": "integer", "description": "The HTTP status code returned by Scrape.do." }, "requestCost": { "anyOf": [ { "type": "integer", "description": "The Scrape.do credit cost reported for this request." }, { "type": "null" } ] }, "remainingCredits": { "anyOf": [ { "type": "integer", "description": "The remaining Scrape.do credits reported after this request." }, { "type": "null" } ] }, "contentType": { "anyOf": [ { "type": "string", "description": "The response Content-Type header when returned." }, { "type": "null" } ] }, "finalUrl": { "anyOf": [ { "type": "string", "description": "The final response URL observed by the connector." }, { "type": "null" } ] } }, "additionalProperties": false, "description": "Metadata collected from Scrape.do response headers." } }, "additionalProperties": false, "description": "The JSON response returned by Scrape.do returnJSON mode." } }, { "id": "scrape_do.get_account_info", "service": "scrape_do", "name": "get_account_info", "description": "Retrieve Scrape.do account information and usage counters for the API token.", "requiredScopes": [], "providerPermissions": [], "inputSchema": { "type": "object", "properties": {}, "additionalProperties": false, "description": "The input payload for retrieving Scrape.do account information." }, "outputSchema": { "type": "object", "properties": { "account": { "type": "object", "properties": { "is_active": { "type": "boolean", "description": "Whether the Scrape.do subscription is active." }, "concurrent_request": { "type": "integer", "description": "The maximum concurrent request count for the account." }, "max_monthly_request": { "type": "integer", "description": "The maximum monthly request count for the account." }, "remaining_concurrent_request": { "type": "integer", "description": "The remaining concurrent request count for the account." }, "remaining_monthly_request": { "type": "integer", "description": "The remaining monthly request count for the account." } }, "additionalProperties": true, "description": "The account information and usage payload returned by Scrape.do." } }, "additionalProperties": false, "description": "The output payload for Scrape.do account information." } }, { "id": "scrape_do.take_screenshot", "service": "scrape_do", "name": "take_screenshot", "description": "Render one public URL through Scrape.do and return a screenshot as base64.", "requiredScopes": [], "providerPermissions": [], "inputSchema": { "type": "object", "properties": { "url": { "type": "string", "description": "The public target URL Scrape.do should request.", "format": "uri" }, "super": { "type": "boolean", "description": "Whether Scrape.do should use residential and mobile proxy networks." }, "geoCode": { "type": "string", "minLength": 2, "maxLength": 2, "description": "The two-letter country code used for Scrape.do geo-targeting.", "pattern": "^[A-Za-z]{2}$" }, "regionalGeoCode": { "type": "string", "minLength": 2, "description": "The continent code used for Scrape.do regional geo-targeting." }, "sessionId": { "type": "integer", "minimum": 1, "description": "The sticky Scrape.do session identifier." }, "render": { "type": "boolean", "description": "Whether Scrape.do should render the page with a headless browser." }, "device": { "type": "string", "enum": [ "desktop", "mobile", "tablet" ], "description": "The browser device profile Scrape.do should emulate." }, "width": { "type": "integer", "minimum": 1, "description": "The browser viewport width in pixels." }, "height": { "type": "integer", "minimum": 1, "description": "The browser viewport height in pixels." }, "blockResources": { "type": "boolean", "description": "Whether Scrape.do should block CSS, image, and font resources while rendering." }, "timeout": { "type": "integer", "minimum": 5000, "maximum": 120000, "description": "The maximum Scrape.do request timeout in milliseconds." }, "retryTimeout": { "type": "integer", "minimum": 5000, "maximum": 55000, "description": "The maximum Scrape.do retry timeout in milliseconds." }, "disableRetry": { "type": "boolean", "description": "Whether Scrape.do should disable its retry mechanism." }, "disableRedirection": { "type": "boolean", "description": "Whether Scrape.do should disable target request redirection." }, "setCookies": { "type": "string", "minLength": 1, "description": "The Cookie header value Scrape.do should send to the target website." }, "customHeaders": { "type": "boolean", "description": "Whether Scrape.do should handle all request headers." }, "forwardHeaders": { "type": "boolean", "description": "Whether Scrape.do should forward caller headers to the target." }, "output": { "type": "string", "enum": [ "raw", "markdown" ], "description": "The Scrape.do output format for page content." }, "fullPage": { "type": "boolean", "description": "Whether Scrape.do should capture a full-page screenshot." }, "selector": { "type": "string", "minLength": 1, "description": "A CSS selector for a partial screenshot area." } }, "additionalProperties": false, "required": [ "url" ], "description": "The input payload for taking a screenshot with Scrape.do." }, "outputSchema": { "type": "object", "properties": { "imageBase64": { "type": "string", "description": "The screenshot image encoded as a base64 string." }, "contentType": { "type": "string", "description": "The screenshot response content type." }, "statusCode": { "type": "integer", "description": "The HTTP status code returned by Scrape.do." }, "headers": { "type": "object", "additionalProperties": { "type": "string", "description": "One HTTP response header value." }, "description": "The HTTP response headers returned by Scrape.do or the target website." }, "metadata": { "type": "object", "properties": { "statusCode": { "type": "integer", "description": "The HTTP status code returned by Scrape.do." }, "requestCost": { "anyOf": [ { "type": "integer", "description": "The Scrape.do credit cost reported for this request." }, { "type": "null" } ] }, "remainingCredits": { "anyOf": [ { "type": "integer", "description": "The remaining Scrape.do credits reported after this request." }, { "type": "null" } ] }, "contentType": { "anyOf": [ { "type": "string", "description": "The response Content-Type header when returned." }, { "type": "null" } ] }, "finalUrl": { "anyOf": [ { "type": "string", "description": "The final response URL observed by the connector." }, { "type": "null" } ] } }, "additionalProperties": false, "description": "Metadata collected from Scrape.do response headers." } }, "additionalProperties": false, "description": "The screenshot response returned by Scrape.do." } } ] }