{ "openapi": "3.0.1", "info": { "title": "Web Page to Markdown for LLM & RAG (No Browser)", "description": "Turn web page URLs into clean Markdown of the main content, with title, language, word and token counts and optional heading-aware RAG chunks. Plain HTTP, no browser: fast and cheap. Respects robots.txt. You pay only for pages that were read.", "version": "0.1", "x-build-id": "qF8VsTJkYtgCKCJAf" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/far003~web-page-to-markdown/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-far003-web-page-to-markdown", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/far003~web-page-to-markdown/runs": { "post": { "operationId": "runs-sync-far003-web-page-to-markdown", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/far003~web-page-to-markdown/run-sync": { "post": { "operationId": "run-sync-far003-web-page-to-markdown", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Page URLs", "type": "array", "description": "Addresses (http or https) of the pages to convert. One record per address. Fragments (#...) are ignored; a repeated address is reported once as \"duplicate\". Addresses that are not usable web addresses, or that point to private/local networks, get an \"invalid\" record (free), not a run error. Credentials written inside a URL are removed and never used.", "items": { "type": "string" } }, "datasetId": { "title": "Or: read addresses from a dataset", "type": "string", "description": "ID or name of a dataset of another run (a crawler, a sitemap reader...). Its addresses are added to the list above. Leave empty to use only the list." }, "datasetUrlField": { "title": "Field with the address in that dataset", "type": "string", "description": "Name of the field that holds the page address in each item of the dataset. A dotted path such as \"page.url\" works.", "default": "url" }, "selector": { "title": "CSS selector of the content (optional)", "type": "string", "description": "Convert only this part of the page, for example \"article\" or \"#content\". Empty: the main content is found automatically. If the selector matches nothing on a page, the automatic way is used for that page and a warning is added." }, "removeSelectors": { "title": "CSS selectors to remove first (optional)", "type": "array", "description": "Parts to cut out before the content is read, for example a cookie banner (\".cookie-banner\") or a related-posts block (\".related\").", "items": { "type": "string" } }, "includeLinks": { "title": "Keep links", "type": "boolean", "description": "Write links as Markdown links with absolute addresses. Off: only the link text.", "default": true }, "includeImages": { "title": "Keep images", "type": "boolean", "description": "Write images as Markdown images (alt text and absolute address). Off by default: for LLM input the pictures are usually noise.", "default": false }, "includeTables": { "title": "Keep tables", "type": "boolean", "description": "Write data tables as Markdown (GFM) tables. Off: tables are left out.", "default": true }, "removeReferences": { "title": "Drop references and footnote sections", "type": "boolean", "description": "On Wikipedia-style pages, leave out the reference lists, notes, bibliography, further-reading and external-links sections (footnote markers like [1] are always dropped). Saves a large share of the tokens of an encyclopedia page. Infoboxes and navigation boxes are always left out.", "default": true }, "outputLinks": { "title": "Also list the links as data", "type": "boolean", "description": "Add a \"links\" array (text and absolute address, each address once, at most 1000) to every record, for a crawl that goes on from the links of the content.", "default": false }, "chunkTokens": { "title": "RAG chunk size (estimated tokens, 0 = no chunks)", "minimum": 0, "maximum": 8000, "type": "integer", "description": "When above 0, every record gets a \"chunks\" array: pieces of about this many tokens, cut at paragraph, list, table and code-block edges, never in the middle of a code block or a table that fits. A heading starts a new chunk once the current one is at least half full, and each chunk lists the headings it sits under. Tokens are estimated (about 4 characters per token; one per CJK character), not counted with a tokenizer.", "default": 0 }, "chunkOverlapTokens": { "title": "Chunk overlap (estimated tokens)", "minimum": 0, "maximum": 4000, "type": "integer", "description": "The end of a full chunk is repeated at the start of the next one, up to this many tokens (never across a heading change). At most half of the chunk size.", "default": 0 }, "maxPages": { "title": "Maximum pages", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Pages read in this run. Addresses beyond the limit are not fetched; the SUMMARY says how many. A safety net for long lists.", "default": 1000 }, "minWords": { "title": "Minimum words of content", "minimum": 1, "maximum": 1000, "type": "integer", "description": "A page whose main content has fewer words is reported as \"empty\" (free). Raise it to skip thin pages, lower it for short notices.", "default": 10 }, "maxPageMegabytes": { "title": "Maximum page size (MB)", "minimum": 1, "maximum": 20, "type": "integer", "description": "Pages bigger than this are not read (status \"too_large\", free). Checked while the page downloads.", "default": 5 }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "Read the robots.txt of every site before the first request there and skip what it forbids to this bot (status \"robots_disallowed\", free). The Crawl-delay is honoured up to 10 seconds. Switch off only for sites you own or have permission to read.", "default": true }, "requestsPerSecond": { "title": "Requests per second, per site", "minimum": 1, "maximum": 2, "type": "integer", "description": "Spacing between two requests to the same site (1 or 2 per second). Different sites are read in parallel.", "default": 2 }, "maxConcurrency": { "title": "Pages in parallel", "minimum": 1, "maximum": 16, "type": "integer", "description": "How many pages are read at the same time, across all sites.", "default": 5 }, "timeoutSecs": { "title": "Timeout per page (seconds)", "minimum": 5, "maximum": 120, "type": "integer", "description": "Longest wait for the answer of the site, and the longest silence while the page downloads.", "default": 30 } } }, "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 } } } } } } } } } }