{ "openapi": "3.0.1", "info": { "title": "Web & PDF to Markdown API for AI Agents, Cited and Verified", "description": "Returns mainText, mainMarkdown, title, links, metadata, sourceSpans (citable paragraph offsets + SHA-256), contentSha256, fetch timestamp and an Ed25519-signed receipt per URL. Web pages, PDF, .docx. Batch or sync HTTP API. Failed URLs are free.", "version": "0.5", "x-build-id": "Or1Gw3Ainr46p4zcq" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/lmhsolutions~web-page-to-markdown-pdf-to-text/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-lmhsolutions-web-page-to-markdown-pdf-to-text", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/lmhsolutions~web-page-to-markdown-pdf-to-text/runs": { "post": { "operationId": "runs-sync-lmhsolutions-web-page-to-markdown-pdf-to-text", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/lmhsolutions~web-page-to-markdown-pdf-to-text/run-sync": { "post": { "operationId": "run-sync-lmhsolutions-web-page-to-markdown-pdf-to-text", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "mode": { "title": "Mode", "enum": [ "extract", "verify" ], "type": "string", "description": "extract: fetch each URL and return clean JSON (with a signed receipt when signedProvenance is on). verify: check receipts and/or a source-pack manifest from earlier runs.", "default": "extract" }, "urls": { "title": "URLs", "type": "array", "description": "Public http(s) URLs of web pages, PDFs or Word .docx files. One dataset item per URL. Required in extract mode.", "items": { "type": "string" } }, "markdown": { "title": "Include Markdown", "type": "boolean", "description": "Add mainMarkdown next to mainText.", "default": true }, "links": { "title": "Include links", "type": "boolean", "description": "Return the links found in the page or document.", "default": true }, "maxLinks": { "title": "Max links", "minimum": 0, "maximum": 300, "type": "integer", "description": "Cap on returned links per URL (server cap 300).", "default": 300 }, "includeDroppedText": { "title": "Include full text of dropped sections", "type": "boolean", "description": "By default each dropped section has a 160-character preview. Turn on to get its full text.", "default": false }, "jsonLd": { "title": "Include JSON-LD", "type": "boolean", "description": "Return parsed schema.org JSON-LD blocks in metadata.", "default": true }, "sourceSpans": { "title": "Include source spans (citations)", "type": "boolean", "description": "With signed provenance: paragraph-level spans (id, start/end offsets into the hashed text, SHA-256 per span) so an agent can cite and anyone can re-check a quote.", "default": true }, "injection": { "title": "Prompt-injection handling", "enum": [ "flag", "strip" ], "type": "string", "description": "flag: report suspected prompt injection in `security`. strip: also remove medium/high-risk spans from mainText and mainMarkdown.", "default": "flag" }, "useApifyProxy": { "title": "Use Apify Proxy", "type": "boolean", "description": "Fetch through Apify Proxy (datacenter by default). Recorded in each receipt's fetchProvenance. Does not unlock login walls or solve bot challenges.", "default": false }, "proxyConfiguration": { "title": "Proxy configuration (optional)", "type": "object", "description": "Optional Apify Proxy groups or country, used when Use Apify Proxy is on." }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 20, "type": "integer", "description": "URLs processed in parallel.", "default": 5 }, "signedProvenance": { "title": "Signed provenance (add-on, $0.03 per extracted item)", "type": "boolean", "description": "On (default): each extracted item also gets a completeness report (coverage score, dropped sections), a prompt-injection scan and an Ed25519-signed receipt you can verify later. Charged $0.03 per successfully extracted page or document (FREE-plan price), on top of the base price. Off: you get clean text, Markdown, metadata and links only, without the completeness, security and receipt sections, and this add-on is not charged.", "default": true }, "sourcePackManifest": { "title": "Source-pack manifest (add-on, $0.10 per run)", "type": "boolean", "description": "On: when at least one URL succeeds, add one extra signed manifest item (also saved as SOURCE_PACK_MANIFEST in the key-value store) listing every extracted item's URL, outputSha256, textSha256 and receipt id, signed with the same Ed25519 key. Verify it later with mode verify. Charged once per run ($0.10, FREE-plan price); not charged if every URL failed.", "default": false }, "receipts": { "title": "Receipts to verify", "type": "array", "description": "Verify mode: receipt objects (the `receipt` field of earlier dataset items)." }, "responses": { "title": "Full responses (optional)", "type": "array", "description": "Verify mode: the full dataset items, in the same order as receipts (or alone; the receipt is taken from each item). Also checks outputSha256 and textSha256." }, "manifest": { "title": "Manifest to verify (optional)", "type": "object", "description": "Verify mode: a source-pack manifest (the `manifest` field of the manifest item, or the SOURCE_PACK_MANIFEST record). If receipts are also given, each must be listed in the manifest." } } }, "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 } } } } } } } } } }