{ "openapi": "3.0.1", "info": { "title": "dane.gov.pl Scraper - Poland Open Data Portal API", "description": "Scrape dane.gov.pl, Poland's national open data portal: 26,922 datasets, 1.6M resources, 7,471 institutions, showcases, change history and table rows over the public JSON:API.", "version": "0.1", "x-build-id": "cPsm8Kzz9rbIjfvsZ" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/parseforge~poland-open-data-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-parseforge-poland-open-data-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/parseforge~poland-open-data-scraper/runs": { "post": { "operationId": "runs-sync-parseforge-poland-open-data-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/parseforge~poland-open-data-scraper/run-sync": { "post": { "operationId": "run-sync-parseforge-poland-open-data-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "collections": { "title": "What to scrape", "type": "array", "description": "Which dane.gov.pl records to collect. Datasets is the catalogue itself (26,989 records). Resources are the downloadable files and APIs inside them (1.6M). Institutions are the 7,476 publishing bodies. Showcases are the 119 apps built on the data. Change history is the portal audit log. Broken links is the portal's own dead-link report. News and Knowledge base are the editorial content. Search runs one cross-model query. Table rows pulls the actual rows out of a tabulated resource.", "items": { "type": "string", "enum": [ "datasets", "resources", "institutions", "showcases", "histories", "broken-links", "news", "knowledge-base", "search", "tabular-rows" ], "enumTitles": [ "Datasets (26,989)", "Resources / distributions (1.6M)", "Institutions (7,476)", "Showcases (119)", "Change history (269,810)", "Broken links report (819)", "News (159)", "Knowledge base (15)", "Cross-model search", "Table rows from a resource" ] }, "default": [ "datasets" ] }, "searchTerm": { "title": "Search term", "type": "string", "description": "Free text query applied to whichever collections are selected. On the dataset, resource and institution indexes diacritics are folded, so 'budzet' works. The cross-model search does NOT fold them: use 'budżet' there." }, "datasetIds": { "title": "Dataset IDs", "type": "array", "description": "Numeric dane.gov.pl dataset IDs, for example 1681. Given here, only these datasets are fetched, and the Resources collection is limited to their files.", "items": { "type": "string" } }, "resourceIds": { "title": "Resource IDs", "type": "array", "description": "Numeric resource IDs. Required target for the Table rows collection; leave empty there and the ten most viewed tabulated resources are used instead.", "items": { "type": "string" } }, "institutionIds": { "title": "Institution IDs", "type": "array", "description": "Numeric institution IDs, for example 26 for UOKiK. Filters datasets to those publishers, and the Institutions collection to those bodies.", "items": { "type": "string" } }, "maxItems": { "title": "Max Items", "minimum": 1, "maximum": 1000000, "type": "integer", "description": "Free users: limited to 10 items (preview). Paid users: up to 1,000,000. This is the cap for the whole run: with several collections selected each gets an even share and whatever one does not use rolls forward to the next." }, "formats": { "title": "File formats", "type": "array", "description": "Keep only records offering at least one of these formats. The index is case sensitive and stores formats in lower case.", "items": { "type": "string", "enum": [ "xlsx", "csv", "jsonld", "xml", "html", "txt", "json", "xls", "pdf", "png", "rdf", "zip", "docx", "ods", "7z", "jpeg", "doc", "geojson", "shp", "flatgeobuf", "gpkg", "parquet", "tsv", "odt", "rar", "wfs", "wms", "geotiff", "gml", "tiff" ], "enumTitles": [ "XLSX (12,319)", "CSV (10,698)", "JSON-LD (2,922)", "XML (1,783)", "HTML (951)", "TXT (642)", "JSON (591)", "XLS (562)", "PDF (481)", "PNG (385)", "RDF (230)", "ZIP (217)", "DOCX (105)", "ODS (72)", "7Z (39)", "JPEG (33)", "DOC (24)", "GeoJSON (14)", "Shapefile (11)", "FlatGeobuf (9)", "GeoPackage (9)", "Parquet (9)", "TSV (9)", "ODT (7)", "RAR (4)", "WFS (3)", "WMS (3)", "GeoTIFF (2)", "GML (1)", "TIFF (1)" ] } }, "dcatThemes": { "title": "DCAT themes", "type": "array", "description": "The 14 EU data themes the portal tags datasets with. Multiple values are OR'd.", "items": { "type": "string", "enum": [ "145", "149", "148", "144", "147", "146", "141", "140", "139", "143", "142", "150", "151", "152" ], "enumTitles": [ "Economy and finance (21,858)", "Regions and cities (2,909)", "Government and public sector (934)", "Science and technology (792)", "Health (579)", "Population and society (555)", "Environment (384)", "Education, culture and sport (237)", "Agriculture, fisheries, forestry and food (202)", "Transport (193)", "Energy (173)", "Justice, legal system and public safety (156)", "International issues (125)", "Ukraine (65)" ] } }, "legacyCategories": { "title": "Portal categories", "type": "array", "description": "The 13 original dane.gov.pl categories. Only about 1,156 datasets still carry one, so this is a narrow filter by design.", "items": { "type": "string", "enum": [ "1", "3", "9", "4", "6", "2", "138", "7", "137", "136", "8", "5", "135" ], "enumTitles": [ "Administracja Publiczna (538)", "Budżet i Finanse Publiczne (108)", "Środowisko (104)", "Nauka i Oświata (86)", "Rolnictwo (65)", "Biznes i Gospodarka (62)", "Regiony i miasta (58)", "Społeczeństwo (39)", "Zdrowie (29)", "Bezpieczeństwo (25)", "Sport i Turystyka (18)", "Praca i Pomoc Społeczna (15)", "Kultura (9)" ] } }, "datasetTypes": { "title": "Delivery type", "type": "array", "description": "How the data is delivered: a downloadable file, a live API, or a link to an external website.", "items": { "type": "string", "enum": [ "file", "api", "website" ], "enumTitles": [ "File (24,573)", "API (1,071)", "Website (832)" ] } }, "visualizationTypes": { "title": "Visualisation available", "type": "array", "description": "Keep only records the portal can render. Table means the rows are queryable through the data API, which is what the Table rows collection needs.", "items": { "type": "string", "enum": [ "table", "chart", "map", "none" ], "enumTitles": [ "Table (1,191 datasets)", "Chart (13)", "Map (14)", "None (25,714)" ] } }, "keywords": { "title": "Keywords", "type": "array", "description": "Keyword tags exactly as the portal stores them, for example 'uokik'. Multiple values are OR'd. Note the API's own 'tag' filter is documented but returns HTTP 400, so keywords are the working vocabulary.", "items": { "type": "string" } }, "titleContains": { "title": "Title contains", "type": "string", "description": "Full text match against the title only, instead of the whole record." }, "notesContains": { "title": "Description contains", "type": "string", "description": "Full text match against the description only." }, "minOpennessScore": { "title": "Minimum openness score", "enum": [ "1", "2", "3", "4", "5" ], "type": "string", "description": "The portal's 1 to 5 star openness rating, using Tim Berners-Lee's scale. 3 means a non-proprietary format such as CSV, 4 adds URIs, 5 adds links to other data." }, "createdFrom": { "title": "Published from", "type": "string", "description": "Only records first published on or after this date, as YYYY-MM-DD." }, "createdTo": { "title": "Published to", "type": "string", "description": "Only records first published on or before this date, as YYYY-MM-DD." }, "onlyHighValueData": { "title": "High value data only", "type": "boolean", "description": "Only datasets flagged as high value data under the Polish open data act (17,536 datasets).", "default": false }, "onlyEuHighValueData": { "title": "EU high value data only", "type": "boolean", "description": "Only datasets on the European Commission's high value datasets list (118 datasets).", "default": false }, "onlyDynamicData": { "title": "Dynamic data only", "type": "boolean", "description": "Only datasets the publisher marks as dynamic, meaning near real time (3,950 datasets).", "default": false }, "onlyResearchData": { "title": "Research data only", "type": "boolean", "description": "Only datasets flagged as research data (1,413 datasets).", "default": false }, "onlyPromoted": { "title": "Promoted only", "type": "boolean", "description": "Only datasets the portal editors promote on the front page (5 datasets).", "default": false }, "licenseNames": { "title": "Licence", "type": "array", "description": "Keep only datasets under one of these licences.", "items": { "type": "string", "enum": [ "CC0 1.0", "CC BY 4.0", "CC BY-SA 4.0", "CC BY-NC 4.0", "CC BY-NC-SA 4.0", "CC BY-NC-ND 4.0" ], "enumTitles": [ "CC0 1.0 (public domain)", "CC BY 4.0", "CC BY-SA 4.0", "CC BY-NC 4.0", "CC BY-NC-SA 4.0", "CC BY-NC-ND 4.0" ] } }, "updateFrequencies": { "title": "Update frequency", "type": "array", "description": "Keep only datasets the publisher refreshes at this cadence. Values are the Polish labels the portal stores.", "items": { "type": "string", "enum": [ "Codziennie", "Co tydzień", "Miesięcznie", "Kwartalnie", "Co pół roku", "Rocznie", "Nieregularnie", "Jednorazowe udostępnienie", "Nie dotyczy" ], "enumTitles": [ "Daily", "Weekly", "Monthly", "Quarterly", "Every six months", "Yearly", "Irregular", "One-off publication", "Not applicable" ] } }, "modifiedFrom": { "title": "Modified from", "type": "string", "description": "Only datasets last modified on or after this date, as YYYY-MM-DD." }, "modifiedTo": { "title": "Modified to", "type": "string", "description": "Only datasets last modified on or before this date, as YYYY-MM-DD." }, "minViews": { "title": "Minimum views", "minimum": 0, "type": "integer", "description": "Only datasets viewed at least this many times on the portal." }, "minDownloads": { "title": "Minimum downloads", "minimum": 0, "type": "integer", "description": "Only datasets downloaded at least this many times." }, "minResources": { "title": "Minimum files", "minimum": 0, "type": "integer", "description": "Only datasets carrying at least this many resources." }, "searchModels": { "title": "Search across", "type": "array", "description": "Which record types the cross-model search returns. Leave empty for all of them.", "items": { "type": "string", "enum": [ "dataset", "resource", "institution", "showcase", "news", "knowledge_base" ], "enumTitles": [ "Datasets", "Resources", "Institutions", "Showcases", "News", "Knowledge base" ] } }, "searchLicenseCodes": { "title": "Search: licence", "type": "array", "description": "Licence filter, server side, available only on the cross-model search.", "items": { "type": "string", "enum": [ "1", "2", "3", "4", "5", "7" ], "enumTitles": [ "CC0 1.0", "CC BY 4.0", "CC BY-SA 4.0", "CC BY-NC 4.0", "CC BY-NC-SA 4.0", "CC BY-NC-ND 4.0" ] } }, "searchUpdateFrequencies": { "title": "Search: update frequency", "type": "array", "description": "Update frequency filter, server side, available only on the cross-model search.", "items": { "type": "string", "enum": [ "daily", "weekly", "monthly", "quarterly", "everyHalfYear", "yearly", "irregular", "notPlanned", "notApplicable" ], "enumTitles": [ "Daily", "Weekly", "Monthly", "Quarterly", "Every six months", "Yearly", "Irregular", "One-off publication", "Not applicable" ] } }, "searchDateFrom": { "title": "Search: date from", "type": "string", "description": "Cross-model search only. Records dated on or after this day, as YYYY-MM-DD." }, "searchDateTo": { "title": "Search: date to", "type": "string", "description": "Cross-model search only. Records dated on or before this day, as YYYY-MM-DD." }, "institutionTypes": { "title": "Institution type", "type": "array", "description": "Which kind of publishing body to keep. Developer is by far the largest group because property developers are legally obliged to publish their price lists here.", "items": { "type": "string", "enum": [ "state", "local", "private", "developer", "other" ], "enumTitles": [ "Central government (188)", "Local government (452)", "Private body (193)", "Property developer (6,635)", "Other (3)" ] } }, "institutionCity": { "title": "Institution city", "type": "string", "description": "Exact city name as the register stores it, for example Warszawa (1,324 institutions) or Kraków (465)." }, "institutionRegon": { "title": "Institution REGON", "type": "string", "description": "Polish REGON statistical number, which resolves to exactly one institution." }, "historyAction": { "title": "Change action", "enum": [ "UPDATE", "INSERT", "DELETE" ], "type": "string", "description": "Which kind of audit log entry to keep. UPDATE covers 231,131 of the 269,810 entries." }, "historyChangedFrom": { "title": "Changed from", "type": "string", "description": "Only audit log entries recorded on or after this date, as YYYY-MM-DD." }, "historyChangedTo": { "title": "Changed to", "type": "string", "description": "Only audit log entries recorded on or before this date, as YYYY-MM-DD." }, "tabularQuery": { "title": "Table row search", "type": "string", "description": "Full text query inside a resource's own table, for the Table rows collection. Searching a name inside the PESEL register works this way." }, "maxRowsPerResource": { "title": "Max table rows per resource", "minimum": 1, "maximum": 1000000, "type": "integer", "description": "How many rows to pull out of each tabulated resource before moving to the next one. Also caps the table preview block." }, "language": { "title": "Language", "enum": [ "pl", "en" ], "type": "string", "description": "English translates the controlled vocabularies (themes, update frequency) and links to the English portal. Titles and descriptions are only ever written in Polish by the publishers, so they stay in Polish either way.", "default": "pl" }, "sortBy": { "title": "Sort by", "enum": [ "id", "-id", "title", "-title", "created", "-created", "modified", "-modified", "views_count", "-views_count", "verified", "-verified", "date", "-date", "data_date", "-data_date", "city", "-city", "change_timestamp", "-change_timestamp" ], "type": "string", "description": "Order the records come back in. An unsupported value falls back to the collection's default with a warning, because this API silently ignores a sort field it does not know." }, "includeDatasetResources": { "title": "Include the files of each dataset", "type": "boolean", "description": "Attach every resource of the dataset with its format, byte size, openness score, download URL and data date. One extra API call per dataset.", "default": false }, "maxResourcesPerDataset": { "title": "Max files per dataset", "minimum": 1, "maximum": 100, "type": "integer", "description": "How many resources to attach when the block above is on. The API caps a page at 100." }, "includeDatasetShowcases": { "title": "Include the apps built on each dataset", "type": "boolean", "description": "Attach the showcases, meaning the public services and apps, that reuse this dataset. Only fetched when the dataset declares at least one.", "default": false }, "includeDatasetHistory": { "title": "Include the change history of each dataset", "type": "boolean", "description": "Attach the portal audit log for the dataset: every update with its timestamp, the editor account and which fields changed.", "default": false }, "includeInstitutionProfile": { "title": "Include the full publisher profile", "type": "boolean", "description": "Attach the publishing body's full record: REGON, postal address, email, phone, fax, ePUAP inbox, website and its harvest sources.", "default": false }, "includeTabularPreview": { "title": "Include a preview of each table", "type": "boolean", "description": "For resources, attach the column schema with real header names and the first rows of the table. Only tabulated resources have any; the rest return nothing and are not billed.", "default": false }, "includeFileProbe": { "title": "Check that each file still downloads", "type": "boolean", "description": "Send one HEAD request per resource to record the HTTP status, content type and byte size of the actual file, which is how you find dead links the portal has not noticed.", "default": false }, "includeFacets": { "title": "Add catalogue breakdown rows", "type": "boolean", "description": "After the records, emit one row per facet bucket: every format, theme, category, delivery type, openness score and top publisher with its dataset count and share of the filtered catalogue.", "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 } } }, "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 } } } } } } } } } }