{ "openapi": "3.0.1", "info": { "title": "Web Scraper — CSS Selector & Data Extractor", "description": "Web Scraper pulls any CSS selector off any page, returning text, HTML, attributes or match counts — one row per URL, no browser required.", "version": "0.1", "x-build-id": "g9ZyGHjbmbHB9j5Gq" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/webdatatools~css-selector-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-webdatatools-css-selector-extractor", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/webdatatools~css-selector-extractor/runs": { "post": { "operationId": "runs-sync-webdatatools-css-selector-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/webdatatools~css-selector-extractor/run-sync": { "post": { "operationId": "run-sync-webdatatools-css-selector-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "selectors" ], "properties": { "urls": { "title": "URLs", "type": "array", "description": "Enter one URL per row to fetch and run the selectors against, e.g. https://example.com. Each URL gets exactly one result row, even if the fetch fails.", "default": [ "https://example.com" ], "items": { "type": "string" } }, "selectors": { "title": "Selectors", "type": "array", "description": "Enter the fields to extract as a JSON array of {\"name\", \"selector\", \"type\"} objects. \"type\" is one of text, html, attr or count; an \"attr\" entry also needs \"attribute\" (e.g. {\"name\":\"canonicalUrl\",\"selector\":\"link[rel='canonical']\",\"type\":\"attr\",\"attribute\":\"href\"}). Capped at 25 entries per run.", "default": [ { "name": "title", "selector": "h1", "type": "text" } ] }, "firstMatchOnly": { "title": "First match only", "type": "boolean", "description": "Keep this on to return only the first element each selector matches. Turn it off to return every match (up to Max matches per selector) as an array.", "default": true }, "maxMatchesPerSelector": { "title": "Max matches per selector", "minimum": 1, "maximum": 500, "type": "integer", "description": "Enter the most matches to return for one selector when First match only is off, e.g. 20. Does not limit the reported match count, only how many values are returned.", "default": 20 }, "trimWhitespace": { "title": "Trim whitespace", "type": "boolean", "description": "Keep this on to collapse runs of whitespace and trim the ends of extracted text and attribute values. Turning it off returns text and attr values exactly as found in the page.", "default": true }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 20, "type": "integer", "description": "Enter how many URLs to fetch in parallel, e.g. 5. Lower this if a target site starts returning errors under load.", "default": 5 }, "proxyMode": { "title": "Proxy mode", "enum": [ "auto", "always", "never" ], "type": "string", "description": "'auto' (recommended) requests each URL directly first and only switches to Apify Proxy for the rest of the run if a direct request gets blocked — this keeps proxy cost at $0 whenever a site isn't blocking datacenter IPs. 'always' skips the direct attempt and always uses the proxy. 'never' always requests directly, even if that means errors.", "default": "auto" }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Which Apify Proxy group to use when 'Proxy mode' above decides a request needs the proxy (either 'auto' after a block, or 'always'). Leave Residential proxy selected (the default) unless you know a datacenter group works for your target. Not needed when running locally with your own IP.", "default": { "useApifyProxy": true, "apifyProxyGroups": [ "RESIDENTIAL" ] } }, "inputDatasetId": { "title": "Input dataset ID (optional)", "type": "string", "description": "Take the items from another Actor run's dataset, e.g. \"aBcD1234\". Combined with the list above." }, "inputField": { "title": "Field to read from that dataset", "type": "string", "description": "Column holding the value, e.g. \"url\" (the default). Array columns are flattened." } } }, "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 }, "PROXY_UNBLOCKER_UNITS": { "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 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } } } } } } } } }