{ "openapi": "3.0.1", "info": { "title": "Google Patents Scraper: Patents, Claims, Citations, Family", "description": "Search Google Patents at scale. Pulls patent metadata, inventors, assignees, full claims, patent + non-patent citations, family members across jurisdictions, legal status, and PDF links. One row per patent. Pay per row.", "version": "0.1", "x-build-id": "o83MtNAZMaFOnKXrk" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/scrapemint~google-patents-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-scrapemint-google-patents-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/scrapemint~google-patents-scraper/runs": { "post": { "operationId": "runs-sync-scrapemint-google-patents-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/scrapemint~google-patents-scraper/run-sync": { "post": { "operationId": "run-sync-scrapemint-google-patents-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "properties": { "queries": { "title": "Search queries", "type": "array", "description": "Free text Google Patents queries. Supports operators: \"exact phrase\", inventor:Smith, assignee:Apple, CPC=H04L. Example: [\"battery thermal management\", \"assignee:Tesla cathode\"].", "default": [], "items": { "type": "string" } }, "patentIds": { "title": "Patent numbers", "type": "array", "description": "Direct patent publication numbers. Example: US10000000B2, EP3000000A1, WO2022123456A1. The actor normalizes formatting.", "default": [], "items": { "type": "string" } }, "assignees": { "title": "Assignees (companies)", "type": "array", "description": "Company names to search as assignees. Example: [\"Apple Inc\", \"Tesla\", \"Samsung Electronics\"]. Returns every patent assigned to that company.", "default": [], "items": { "type": "string" } }, "inventors": { "title": "Inventors", "type": "array", "description": "Inventor names to search. Example: [\"John Smith\", \"Elon Musk\"]. Returns every patent listing the named inventor.", "default": [], "items": { "type": "string" } }, "yearFrom": { "title": "Filing date from year", "minimum": 0, "maximum": 2100, "type": "integer", "description": "Lower bound on filing year. 0 means no lower bound.", "default": 0 }, "yearTo": { "title": "Filing date to year", "minimum": 0, "maximum": 2100, "type": "integer", "description": "Upper bound on filing year. 0 means no upper bound.", "default": 0 }, "jurisdictions": { "title": "Jurisdictions", "type": "array", "description": "Patent offices to include. Empty means all.", "items": { "type": "string", "enum": [ "US", "EP", "WO", "CN", "JP", "KR", "DE", "GB", "FR", "CA", "AU", "IN" ], "enumTitles": [ "US (USPTO)", "EP (European Patent Office)", "WO (PCT / WIPO)", "CN (China)", "JP (Japan)", "KR (Korea)", "DE (Germany)", "GB (United Kingdom)", "FR (France)", "CA (Canada)", "AU (Australia)", "IN (India)" ] }, "default": [] }, "statusFilter": { "title": "Status filter", "enum": [ "any", "grant", "application" ], "type": "string", "description": "Limit results by legal status.", "default": "any" }, "cpcClasses": { "title": "CPC classifications", "type": "array", "description": "Filter to specific Cooperative Patent Classification codes. Example: [\"H04L\", \"G06N3/08\"]. Empty means no filter.", "default": [], "items": { "type": "string" } }, "language": { "title": "Language", "enum": [ "en", "de", "fr", "es", "ja", "ko", "zh" ], "type": "string", "description": "Patent text language for search and display.", "default": "en" }, "fetchClaims": { "title": "Fetch full claims", "type": "boolean", "description": "Pull the full claims text per patent. Adds claims (string) to the row. Adds one extra request per patent.", "default": false }, "fetchDescription": { "title": "Fetch full description", "type": "boolean", "description": "Pull the full description text per patent. This is the long body and can run to tens of thousands of characters.", "default": false }, "fetchCitations": { "title": "Fetch citations", "type": "boolean", "description": "For each patent, pull the cited patent list and non-patent literature (NPL). Adds citedPatents[] and citedNonPatentLiterature[] to the row.", "default": false }, "fetchCitedBy": { "title": "Fetch citing patents", "type": "boolean", "description": "For each patent, pull the list of later patents that cite this one. Adds citingPatents[] to the row.", "default": false }, "fetchFamily": { "title": "Fetch family members", "type": "boolean", "description": "Pull the patent family list (equivalents in other jurisdictions). Adds family[] to the row with publication numbers and filing offices.", "default": false }, "fetchPdf": { "title": "Include PDF URL", "type": "boolean", "description": "Resolve the direct PDF URL hosted on patentimages.storage.googleapis.com per patent.", "default": true }, "maxPatents": { "title": "Total maximum patents", "minimum": 0, "maximum": 50000, "type": "integer", "description": "Hard cap on patent rows pushed per run. 0 means unlimited.", "default": 100 }, "maxPagesPerQuery": { "title": "Max pages per query", "minimum": 1, "maximum": 100, "type": "integer", "description": "Pages of 10 results to walk per query. Google Patents caps at 100 pages.", "default": 10 }, "dedupe": { "title": "Deduplicate across runs", "type": "boolean", "description": "Skip patent numbers already pushed in previous runs. Keyed on publication number. Turn off to refresh stale rows.", "default": true }, "navigationDelayMs": { "title": "Delay between navigations (ms)", "minimum": 0, "maximum": 60000, "type": "integer", "description": "Pause between page loads. Google Patents throttles fast scraping. 3000 to 6000 ms is the safe range.", "default": 3500 }, "concurrency": { "title": "Concurrency", "minimum": 1, "maximum": 8, "type": "integer", "description": "Parallel browser pages. Keep at 1 to 2 unless you have a residential proxy pool.", "default": 2 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Apify proxy. Google Patents accepts datacenter for low volume. Switch to residential past a few hundred requests.", "default": { "useApifyProxy": true, "apifyProxyGroups": [ "RESIDENTIAL" ] } } } }, "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 } } } } } } } } } }