{ "openapi": "3.0.1", "info": { "title": "Web Fetch to Markdown with Browser Fallback", "description": "Turn up to 100 URLs into clean Markdown, text or HTML. It tries plain HTTP first, retries with browser headers, and opens a headless browser only when a page needs it. You pay $0.001 per page that comes back with content. Failed URLs are free and get a clear error code.", "version": "0.1", "x-build-id": "vncXMXInzArh316V1" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/zovo-one~web-fetch-fallback/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-zovo-one-web-fetch-fallback", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/zovo-one~web-fetch-fallback/runs": { "post": { "operationId": "runs-sync-zovo-one-web-fetch-fallback", "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/zovo-one~web-fetch-fallback/run-sync": { "post": { "operationId": "run-sync-zovo-one-web-fetch-fallback", "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", "properties": { "urls": { "title": "URLs", "maxItems": 100, "type": "array", "description": "Full URLs of the pages to read, one per line, 1 to 100 per run. A line without a scheme gets https:// in front (example.com becomes https://example.com/). Exact duplicates are fetched once. Private, local and reserved addresses are refused. Leave the two examples in place to try the Actor with one click.", "default": [ "https://en.wikipedia.org/wiki/Markdown", "https://example.com/" ], "items": { "type": "string" } }, "outputFormat": { "title": "Output format", "enum": [ "markdown", "text", "html" ], "type": "string", "description": "Format of the content field. markdown (best for LLMs): headings, links, lists, tables and code blocks as Markdown. text: plain text without link markup, the fewest tokens. html: the cleaned HTML of the extracted part, not the raw page source. Plain-text, JSON and XML responses are returned as they are in every format.", "default": "markdown" }, "extractMainContent": { "title": "Main content only", "type": "boolean", "description": "On: keep the article or main block and drop menus, headers, footers, sidebars and cookie notices (Defuddle). If that leaves almost nothing, the whole page is used and the row says extraction: full-page. Off: convert the whole page body.", "default": true }, "fetchMode": { "title": "Fetch mode", "enum": [ "auto", "http", "browser" ], "type": "string", "description": "auto (recommended): plain HTTP, then HTTP with browser-like headers, then a headless browser only when the page is blocked, needs JavaScript or comes back empty. http: the two HTTP steps only, never a browser. Fastest, but JavaScript-only pages fail with JS_REQUIRED. browser: always the headless browser. Every mode costs the same $0.001 per page with content.", "default": "auto" }, "timeoutSecs": { "title": "Timeout per step (seconds)", "minimum": 5, "maximum": 120, "type": "integer", "description": "Time limit for each step of the chain. A URL that goes through all three steps can take up to three times this.", "default": 30 }, "maxCharacters": { "title": "Max characters per page", "minimum": 500, "maximum": 1000000, "type": "integer", "description": "The content field is cut at this many characters and the row gets truncated: true. Lower it to keep pages inside an LLM context window (about 4 characters per token for English). A truncated page still counts as a fetched page.", "default": 200000 }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 10, "type": "integer", "description": "URLs fetched in parallel (1-10). Browser pages are limited separately: 1 at a time below 2 GB of memory, 2 at 2 GB or more.", "default": 5 } } }, "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 } } } } } } } } } }