{ "openapi": "3.0.1", "info": { "title": "Jina Scraper", "description": "Crawl any website and get clean, LLM-ready Markdown for every page. Powered by Jina Reader, so JavaScript-heavy sites that break normal scrapers just work. Handles pagination, link discovery and glob filtering in one run. No selectors to write. Perfect for RAG pipelines and AI agents.", "version": "0.0", "x-build-id": "bus7NkM74I0fy2SVu" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/sshdopey~jina-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-sshdopey-jina-scraper", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/sshdopey~jina-scraper/runs": { "post": { "operationId": "runs-sync-sshdopey-jina-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/sshdopey~jina-scraper/run-sync": { "post": { "operationId": "run-sync-sshdopey-jina-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "startUrls" ], "properties": { "startUrls": { "title": "Start URLs", "type": "array", "description": "Listing, search or index pages to start crawling from.", "default": [ "https://books.toscrape.com/" ], "items": { "type": "string" } }, "detailPageGlob": { "title": "Detail page URL structure", "type": "string", "description": "Glob matching the detail pages you want to scrape. * matches within one path segment, ** crosses segments. Example: https://site.com/article/*", "default": "https://books.toscrape.com/catalogue/*/index.html" }, "paginationUrlGlob": { "title": "Pagination URL structure", "type": "string", "description": "Glob where * is the page number, e.g. https://site.com/search?page=*", "default": "https://books.toscrape.com/catalogue/page-*.html" }, "maxPages": { "title": "Max pages", "minimum": 1, "type": "integer", "description": "How many listing pages to walk before stopping.", "default": 2 }, "maxDetailPages": { "title": "Max detail pages", "minimum": 0, "type": "integer", "description": "Hard cap on detail pages fetched per run. Set to 0 for unlimited. This is your main cost guard.", "default": 5 }, "jinaApiKey": { "title": "Jina API key", "type": "string", "description": "Your Jina Reader API key from jina.ai. Strongly recommended: anonymous requests are heavily rate limited and are rejected from many datacenter IPs. Overrides the JINA_API_KEY environment variable." }, "stripMedia": { "title": "Strip images and video from markdown", "type": "boolean", "description": "Removes images, video embeds, media links and Jina image placeholders. Leave on for clean LLM input.", "default": true }, "retainImages": { "title": "Image handling when stripping is off", "enum": [ "none", "alt", "all" ], "type": "string", "description": "Only applies when Strip media is unchecked. none removes images, alt keeps alt text, all keeps image URLs.", "default": "none" }, "targetSelector": { "title": "Results container selector", "type": "string", "description": "Optional CSS selector for the content container on listing pages. Cuts token cost significantly." }, "engine": { "title": "Jina engine", "enum": [ "browser", "direct", "cf-browser-rendering" ], "type": "string", "description": "browser handles JS-heavy sites. direct is faster and cheaper for static HTML.", "default": "direct" }, "concurrency": { "title": "Concurrency", "minimum": 1, "maximum": 20, "type": "integer", "description": "Parallel Jina requests during extraction. Lower this if you hit 429s.", "default": 2 }, "requestDelayMs": { "title": "Delay between requests (ms)", "minimum": 0, "type": "integer", "description": "Politeness delay per worker. Set to 500-1000 if a site rate limits you.", "default": 0 } } }, "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 } } }, "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 } } } } } } } } } }