{ "openapi": "3.0.1", "info": { "title": "Website Content Fetcher | $0.25/1K Pages", "description": "Fetch any public web page as clean Markdown, text or HTML with title and metadata. Optional selectors and link or image summaries. One page per request. $0.25 per 1k requests, run usage included.", "version": "0.1", "x-build-id": "7Vhoz43ELIXjMKOOj" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/litescrape~web-fetch/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-litescrape-web-fetch", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/litescrape~web-fetch/runs": { "post": { "operationId": "runs-sync-litescrape-web-fetch", "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/litescrape~web-fetch/run-sync": { "post": { "operationId": "run-sync-litescrape-web-fetch", "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": { "url": { "title": "Url", "minLength": 1, "maxLength": 8192, "type": "string", "description": "Public HTTP(S) URL to capture, 1-8,192 characters. Include http:// or https://; bare domains are rejected. The host must be public, on port 80 or 443, without embedded credentials." }, "respond_with": { "title": "Respond with", "minLength": 3, "maxLength": 64, "type": "string", "description": "Output format: content (default; main content as Markdown, or the whole page when extraction keeps too little), markdown (whole page as Markdown), html, text, frontmatter (content plus front matter), or a '+' combination such as markdown+frontmatter. For screenshots use /api/web/screenshot." }, "assert_status_code": { "title": "Assert status code", "minimum": 100, "maximum": 599, "type": "integer", "description": "Expected origin HTTP status, 100-599. A different status is rejected; otherwise a rendered error page is a successful capture." }, "base": { "title": "Base", "enum": [ "initial", "final" ], "type": "string", "description": "Resolve relative links against the requested URL (initial, default) or the final URL after redirects (final)." }, "detach_invisibles": { "title": "Detach invisibles", "type": "boolean", "description": "Drop display:none elements from the page." }, "engine": { "title": "Engine", "enum": [ "auto", "browser", "curl" ], "type": "string", "description": "auto (default; lightweight HTTP first, a browser when needed), browser, or curl (no JavaScript)." }, "inject_frame_script": { "title": "Inject frame script", "minItems": 1, "maxItems": 8, "type": "array", "description": "1-8 scripts (source, or a URL to a script), up to 8,192 characters each, run in every frame.", "items": { "type": "string" } }, "inject_page_script": { "title": "Inject page script", "minItems": 1, "maxItems": 8, "type": "array", "description": "1-8 scripts (source, or a URL to a script), up to 8,192 characters each, run in the main frame.", "items": { "type": "string" } }, "keep_img_data_url": { "title": "Keep img data url", "type": "boolean", "description": "Keep inline data: images in Markdown." }, "locale": { "title": "Locale", "pattern": "^[A-Za-z]{2,8}(?:-[A-Za-z0-9]{1,8})*$", "minLength": 2, "maxLength": 64, "type": "string", "description": "Browser locale as a language tag, 2-64 characters. Defaults to the browser's own." }, "markdown": { "title": "Markdown", "type": "object", "description": "Markdown formatting options." }, "markdown_chunking": { "title": "Markdown chunking", "enum": [ "true", "h1", "h2", "h3", "h4", "h5", "structured", "s1", "s2", "s3", "s4", "s5" ], "type": "string", "description": "true, h1-h5, structured or s1-s5: split the Markdown and return chunks." }, "max_tokens": { "title": "Max tokens", "minimum": 500, "maximum": 10000000, "type": "integer", "description": "Integer 500-10,000,000. Trim content to this many tokens." }, "no_gfm": { "title": "No gfm", "type": "boolean", "description": "true, false or table: disable GitHub-flavored Markdown, or only its tables." }, "page_timeout": { "title": "Page timeout", "minimum": 1, "maximum": 180, "type": "integer", "description": "Seconds from 1 through 180 for page loading and browser operations. Cannot extend the total request budget set by timeout." }, "preset": { "title": "Preset", "enum": [ "reader", "index", "research", "agent", "spider" ], "type": "string", "description": "Option preset. Fills only the options the request leaves unset." }, "referer": { "title": "Referer", "minLength": 1, "maxLength": 8192, "type": "string", "description": "HTTP(S) URL sent as the Referer." }, "remove_overlay": { "title": "Remove overlay", "type": "boolean", "description": "Remove modal and cookie-banner overlays from the page." }, "remove_selector": { "title": "Remove selector", "minLength": 1, "maxLength": 2048, "type": "string", "description": "CSS selector removed before extraction, 1-2,048 characters; POST also accepts a list of 1-16 selectors." }, "respond_timing": { "title": "Respond timing", "enum": [ "html", "visible-content", "mutation-idle", "resource-idle", "media-idle", "network-idle" ], "type": "string", "description": "Page readiness condition to reach before responding." }, "retain_images": { "title": "Retain images", "enum": [ "none", "all", "alt" ], "type": "string", "description": "Images to keep: all (default), alt (alt text only) or none." }, "retain_links": { "title": "Retain links", "enum": [ "none", "all", "text", "gpt-oss" ], "type": "string", "description": "Links to keep: all (default), text (link text only), none, or gpt-oss (citation format with a links summary)." }, "retain_media": { "title": "Retain media", "enum": [ "none", "text", "link", "image", "html" ], "type": "string", "description": "How video, audio and embedded video appear: none, text, link (default), image or html." }, "robots_txt": { "title": "Robots txt", "minLength": 1, "maxLength": 256, "type": "string", "description": "User agent, 1-256 characters, to check against the site's robots.txt; disallowed URLs are rejected." }, "set_cookies": { "title": "Set cookies", "minItems": 1, "maxItems": 100, "type": "array", "description": "1-100 cookies in Set-Cookie syntax (name=value; Path=/; Domain=...), one line each, up to 4,096 characters.", "items": { "type": "string" } }, "target_selector": { "title": "Target selector", "minLength": 1, "maxLength": 2048, "type": "string", "description": "CSS selector to extract, 1-2,048 characters; POST also accepts a list of 1-16 selectors. Implies waiting for the selector. Match-all selectors are rejected." }, "timeout": { "title": "Timeout", "maximum": 90, "type": "number", "description": "Total request execution budget in seconds, greater than 0 and at most 90. Supply in the query string for GET or POST. page_timeout cannot extend this budget." }, "token_budget": { "title": "Token budget", "minimum": 1, "maximum": 10000000, "type": "integer", "description": "Integer 1-10,000,000. Reject the page when its token count exceeds the budget." }, "user_agent": { "title": "User agent", "minLength": 1, "maxLength": 1024, "type": "string", "description": "User-Agent for the page request, 1-1,024 characters without control characters. Defaults to the browser's own." }, "viewport": { "title": "Viewport", "type": "object", "description": "Browser viewport; width and height are required. Default: 1280 x 1280." }, "wait_for_selector": { "title": "Wait for selector", "minLength": 1, "maxLength": 2048, "type": "string", "description": "CSS selector to wait for after navigation, 1-2,048 characters. POST also accepts a list of 1-16 selectors." }, "with_iframe": { "title": "With iframe", "type": "boolean", "description": "true, false or quoted: include iframe content before extraction." }, "with_images_summary": { "title": "With images summary", "type": "boolean", "description": "Add an images list to the response." }, "with_links_summary": { "title": "With links summary", "type": "boolean", "description": "true, false or all: add a links list to the response." }, "with_shadow_dom": { "title": "With shadow dom", "type": "boolean", "description": "Include open shadow DOM content before extraction." }, "requests": { "title": "Batch requests", "minItems": 1, "maxItems": 1000, "type": "array", "description": "Optional list of parameter objects. Top-level API fields are shared defaults; each object overrides them. Maximum 1,000 inputs.", "items": { "type": "object" } }, "maxRequests": { "title": "Maximum paid requests", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Run-wide cap on successful API requests, including continuation pages. 1,000 requests cost $0.25.", "default": 100 }, "maxResults": { "title": "Maximum dataset rows", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Cap exported rows. An in-flight response can still be saved and billed in full. Complete JSON responses remain in storage.", "default": 1000 }, "maxPagesPerInput": { "title": "Maximum pages per input", "minimum": 1, "maximum": 1000, "type": "integer", "description": "1 returns the first page only. Additional pages follow source continuation links when available; every successful page is a paid request.", "default": 1 }, "maxConcurrency": { "title": "Concurrent requests", "minimum": 1, "maximum": 8, "type": "integer", "description": "Upper concurrency bound. The service may apply a lower limit for capacity or trial quotas.", "default": 2 }, "includeArtifacts": { "title": "Include source artifacts", "type": "boolean", "description": "Copy available raw source artifacts to this run. Availability varies by endpoint; unavailable artifacts do not invalidate a saved JSON response.", "default": false }, "datasetOutput": { "title": "Export dataset", "type": "boolean", "description": "Enable dataset rows and recoverable per-request storage. Leave off for the cheapest JSON output. Pagination and artifacts also enable this workflow.", "default": false } } }, "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 } } } } } } } } } }