{ "openapi": "3.0.1", "info": { "title": "Python Scraper", "description": "Python Scraper extracts web page data using Requests and BeautifulSoup. It collects titles, meta tags, headings, links, images, Open Graph data, text snippets, and custom CSS selector fields, with exports to JSON, CSV, Excel, XML, or HTML.", "version": "0.0", "x-build-id": "5Cxnn2sqZ9gB0Choa" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/sovanza.inc~python-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-sovanza.inc-python-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/sovanza.inc~python-scraper/runs": { "post": { "operationId": "runs-sync-sovanza.inc-python-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/sovanza.inc~python-scraper/run-sync": { "post": { "operationId": "run-sync-sovanza.inc-python-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "required": [ "startUrls" ], "properties": { "startUrls": { "title": "Start URLs", "type": "array", "description": "One or more URLs to scrape (one per line).", "items": { "type": "string" } }, "method": { "title": "HTTP method", "enum": [ "GET", "POST" ], "type": "string", "description": "HTTP method used for requests.", "default": "GET" }, "cookies": { "title": "Cookie header", "type": "string", "description": "Optional raw Cookie header value for authenticated sessions. Stored as a secret input and never written to the dataset." }, "bearerToken": { "title": "Bearer token", "type": "string", "description": "Optional API or session bearer token. Stored as a secret input; sent as an Authorization header when set." }, "headers": { "title": "Request headers", "type": "object", "description": "Optional extra HTTP headers (JSON object). Use for custom auth or API keys. Stored as a secret input. Leave empty to use the default User-Agent only." }, "timeoutSecs": { "title": "Timeout (seconds)", "minimum": 1, "maximum": 300, "type": "integer", "description": "Per-request timeout in seconds.", "default": 60 }, "selectors": { "title": "CSS selectors (optional)", "type": "object", "description": "Optional mapping of fieldName -> CSS selector. The actor will extract the first matching text for each selector.", "default": {} }, "includeLinks": { "title": "Extract links", "type": "boolean", "description": "Extract and include page links (hrefs).", "default": true }, "includeHtml": { "title": "Include raw HTML in export", "type": "boolean", "description": "If enabled, the export file will contain a 'html' field with the raw HTML (can be large).", "default": false }, "exportFormat": { "title": "Export format", "enum": [ "json", "csv", "excel", "xml", "html" ], "type": "string", "description": "Export all extracted results to the key-value store.", "default": "json" }, "exportBasename": { "title": "Export basename (KV store)", "type": "string", "description": "Basename for the combined export file in the default key-value store (extension is added from export format, e.g. EXPORT.json). Not a credential.", "default": "EXPORT" } } }, "runsResponseSchema": { "type": "object", "properties": { "data": { "type": "object", "properties": { "id": { "type": "string" }, "actId": { "type": "string" }, "userId": { "type": "string" }, "startedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "finishedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "status": { "type": "string", "example": "READY" }, "meta": { "type": "object", "properties": { "origin": { "type": "string", "example": "API" }, "userAgent": { "type": "string" } } }, "stats": { "type": "object", "properties": { "inputBodyLen": { "type": "integer", "example": 2000 }, "rebootCount": { "type": "integer", "example": 0 }, "restartCount": { "type": "integer", "example": 0 }, "resurrectCount": { "type": "integer", "example": 0 }, "computeUnits": { "type": "integer", "example": 0 } } }, "options": { "type": "object", "properties": { "build": { "type": "string", "example": "latest" }, "timeoutSecs": { "type": "integer", "example": 300 }, "memoryMbytes": { "type": "integer", "example": 1024 }, "diskMbytes": { "type": "integer", "example": 2048 } } }, "buildId": { "type": "string" }, "defaultKeyValueStoreId": { "type": "string" }, "defaultDatasetId": { "type": "string" }, "defaultRequestQueueId": { "type": "string" }, "buildNumber": { "type": "string", "example": "1.0.0" }, "containerUrl": { "type": "string" }, "usage": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "integer", "example": 1 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } }, "usageTotalUsd": { "type": "number", "example": 0.00005 }, "usageUsd": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "number", "example": 0.00005 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } } } } } } } } }