{ "openapi": "3.0.1", "info": { "title": "SHAB Swiss New Company Registrations Scraper", "description": "Scrape every newly registered Swiss company from the SHAB/FOSC commercial gazette (rubric HR01): name, CHE UID, full street address, canton, legal form, share capital, business purpose, cantonal register office and the named founders and officers. Filter by canton, legal form, capital or keyword.", "version": "0.1", "x-build-id": "FjCZbjswSn4Wd7opf" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/scrapersdelight~shab-new-companies-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-scrapersdelight-shab-new-companies-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/scrapersdelight~shab-new-companies-scraper/runs": { "post": { "operationId": "runs-sync-scrapersdelight-shab-new-companies-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/scrapersdelight~shab-new-companies-scraper/run-sync": { "post": { "operationId": "run-sync-scrapersdelight-shab-new-companies-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "lookbackDays": { "title": "Look back this many days", "minimum": 1, "maximum": 3000, "type": "integer", "description": "How many publication days back from today to crawl, when you have not set explicit dates below. 1 = today only. The Actor issues exactly ONE request per publication day (never offset paging, see the README for why that matters), so 30 days = 30 list requests.", "default": 1 }, "dateFrom": { "title": "Publication date from", "type": "string", "description": "YYYY-MM-DD. Overrides the lookback window. Day-granular and verified server-side. The archive starts 2018-01-01 (2017 returns 0 rows).", "default": "" }, "dateTo": { "title": "Publication date to", "type": "string", "description": "YYYY-MM-DD. Overrides the lookback window.", "default": "" }, "includeFuturePublications": { "title": "Include tomorrow's gazette (the head start)", "type": "boolean", "description": "SHAB loads a publication into the API up to ~2 days BEFORE its official publication date. With this on, the default window reaches 7 days forward, so you see registrations before they are formally gazetted. Measured 2026-09-03: the window 2026-09-04 to 2026-09-10 already returned 244 rows created 2026-09-02. That head start is the buyer's real edge. Turn it off for a strict historical export.", "default": true }, "cantons": { "title": "Cantons", "uniqueItems": true, "type": "array", "description": "Server-side filter, verified additive (ZH 73,011 + VD 39,458 = 112,469 together). Counts in brackets are that canton's total HR01 registrations since 2018, measured live 2026-09-04. Leave empty for all of Switzerland.", "items": { "type": "string", "enum": [ "ZH", "VD", "BE", "GE", "AG", "ZG", "SG", "VS", "TI", "LU", "FR", "SZ", "TG", "BL", "BS", "SO", "GR", "NE", "SH", "JU", "AR", "NW", "OW", "GL", "UR", "AI" ], "enumTitles": [ "ZH - Zurich (73,011)", "VD - Vaud (39,458)", "BE - Bern (33,458)", "GE - Geneva (33,069)", "AG - Aargau (25,612)", "ZG - Zug (23,876)", "SG - St. Gallen (21,358)", "VS - Valais (18,874)", "TI - Ticino (18,383)", "LU - Lucerne (17,820)", "FR - Fribourg (14,106)", "SZ - Schwyz (11,428)", "TG - Thurgau (11,272)", "BL - Basel-Landschaft (10,389)", "BS - Basel-Stadt (10,350)", "SO - Solothurn (10,071)", "GR - Graubuenden (8,741)", "NE - Neuchatel (6,932)", "SH - Schaffhausen (3,191)", "JU - Jura (2,929)", "AR - Appenzell Ausserrhoden (2,520)", "NW - Nidwalden (2,383)", "OW - Obwalden (1,703)", "GL - Glarus (1,632)", "UR - Uri (1,061)", "AI - Appenzell Innerrhoden (1,035)" ] }, "default": [] }, "keyword": { "title": "Keyword (full text, server-side)", "type": "string", "description": "Searched server-side across the entire publication text: company name, business purpose, address and the named officers. This is the lever that turns the gazette into a niche lead list. Measured hit counts across the whole archive: Zahnarzt 72, Softwareentwicklung 1,254, Treuhand 6,698, postcode 8001 gives 2,789, an exact CHE UID gives exactly 1.", "default": "" }, "publicationLanguage": { "title": "Publication language", "enum": [ "any", "de", "fr", "it" ], "type": "string", "description": "The language the cantonal register published in, a good proxy for the language region. Server-side. Measured archive split: German 272,438, French 112,595, Italian 19,629.", "default": "any" }, "uids": { "title": "Company UIDs", "type": "array", "description": "Swiss UIDs in the form CHE-123.456.789. Verified to resolve to exactly one publication on 12 of 12 spot checks across all 404,662 records.", "default": [], "items": { "type": "string" } }, "companyNames": { "title": "Company names", "type": "array", "description": "Exact or partial company names, resolved through the same server-side full-text search.", "default": [], "items": { "type": "string" } }, "publicationIds": { "title": "SHAB publication IDs", "type": "array", "description": "The publication UUID from a shab.ch detail URL. Fetched directly. Anything that is not an HR01 new registration is skipped with a warning rather than silently returned.", "default": [], "items": { "type": "string" } }, "startUrls": { "title": "SHAB URLs", "type": "array", "description": "Paste shab.ch publication links or raw API URLs. The publication UUID is read out of each one. A URL carrying no UUID is skipped with a warning.", "default": [], "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "legalForms": { "title": "Legal forms", "uniqueItems": true, "type": "array", "description": "Keep only these legal forms. Empty = all. The raw 4-digit register code is always emitted in the legalForm field regardless, and legalFormLabel is null for any code we have not seen in a live publication rather than guessed at (measured 99.5% labelled over 400 consecutive registrations).", "items": { "type": "string", "enum": [ "Limited liability company (GmbH/Sàrl/Sagl)", "Company limited by shares (AG/SA)", "Sole proprietorship", "General partnership", "Limited partnership", "Cooperative", "Association", "Foundation", "Branch office of a Swiss entity", "Branch office of a foreign entity", "Non-commercial power of attorney" ] }, "default": [] }, "excludeBranches": { "title": "Exclude branch registrations", "type": "boolean", "description": "On by default. A branch (Zweigniederlassung / succursale) is a new office of a company that already exists, so it carries no founders and no share capital and is a weak lead. Measured 3.6% of registrations, and all 5 records in our 250-doc sample where no person could be parsed were branches.", "default": true }, "minShareCapitalChf": { "title": "Minimum share capital (CHF)", "minimum": 0, "type": "integer", "description": "Keep only companies whose registered nominal capital is at least this. Capital is present on 62.8% of registrations. It is absent BY LAW on sole proprietorships, not missing data, so any minimum implicitly drops them." }, "maxShareCapitalChf": { "title": "Maximum share capital (CHF)", "minimum": 0, "type": "integer", "description": "Keep only companies at or below this nominal capital. Useful for targeting the CHF 20,000 GmbH floor rather than large incorporations." }, "requireCapital": { "title": "Only companies with share capital", "type": "boolean", "description": "Drops sole proprietorships and other forms that register no capital.", "default": false }, "requirePaidUpFull": { "title": "Only fully paid-up capital", "type": "boolean", "description": "Keeps only companies whose paid-in capital equals the nominal capital, a solvency signal for finance and leasing buyers.", "default": false }, "zipCodes": { "title": "Postcodes", "type": "array", "description": "Exact Swiss postcodes of the registered office, e.g. 8001. Empty = anywhere.", "default": [], "items": { "type": "string" } }, "townContains": { "title": "Town contains", "type": "string", "description": "Substring match against the registered town and the registered seat, case-insensitive.", "default": "" }, "requireStreetAddress": { "title": "Only companies with a street address", "type": "boolean", "description": "Drops the rare registration filed with no domicile address. Measured 100% street, 100% postcode and 99.2% house number on a 250-record sample, so this removes very little.", "default": false }, "purposeKeywords": { "title": "Business-purpose keywords", "type": "array", "description": "Matched case-insensitively against the statutory business purpose, the full register text and the company name. This is what turns the feed into a vertical: Zahnarzt / cabinet dentaire, Bauunternehmen, Restaurant, Immobilien, Software. Every Swiss company must file a purpose, and the field is present on 97.2% of records.", "default": [], "items": { "type": "string" } }, "purposeKeywordsMode": { "title": "Purpose keyword mode", "enum": [ "any", "all" ], "type": "string", "description": "ANY keeps a company matching at least one keyword (a vertical). ALL keeps only companies matching every keyword (a precise niche).", "default": "any" }, "excludeKeywords": { "title": "Exclude keywords", "type": "array", "description": "Drop any company whose purpose, register text or name contains one of these. Applied after the include filters.", "default": [], "items": { "type": "string" } }, "requireRegisteredPersons": { "title": "Only companies with a named founder or officer", "type": "boolean", "description": "Keeps only rows where at least one named person was parsed out of the register text. Measured on 250 records: 98.0% overall and 100.0% of non-branch registrations. See the README honest-limits section: the register does not publish persons as structured XML.", "default": false }, "registrationOfficeContains": { "title": "Cantonal register office contains", "type": "string", "description": "Substring match against the filing office name, e.g. Zurich or Geneve. Mostly redundant with the canton filter, but exposed for exact office-level exports.", "default": "" }, "includeDetail": { "title": "Fetch the full register record", "type": "boolean", "description": "ON (default): one extra request per company fetches the register XML, giving UID, address, legal form, share capital, business purpose and the named founders. OFF: list metadata only (headline, date, canton, register office) with NO UID, address, capital or persons. List-only rows are billed at a separate, much cheaper event.", "default": true }, "extractRegisteredPersons": { "title": "Extract founders and officers", "type": "boolean", "description": "Parse the named persons out of the register text into a structured array. Turn this OFF for a company-only export containing no personal data at all.", "default": true }, "personsAsSeparateRows": { "title": "One row per person", "type": "boolean", "description": "Emit one dataset row per named founder or officer, each carrying the full company columns, which is the shape a CRM import wants. You are still billed ONCE PER COMPANY, never per person.", "default": false }, "includeFullPublicationText": { "title": "Include the full register text", "type": "boolean", "description": "The complete published notice in German, French or Italian. Present on 100% of records and the honest fallback wherever person parsing is imperfect.", "default": true }, "includePurpose": { "title": "Include the business purpose", "type": "boolean", "description": "The full statutory purpose clause, often 1,000 to 2,500 characters.", "default": true }, "purposeMaxChars": { "title": "Truncate the purpose at", "minimum": 0, "type": "integer", "description": "0 keeps the whole clause. Set e.g. 300 if you are exporting to Google Sheets, where multi-thousand-character cells are painful.", "default": 0 }, "legalFormLabelLanguage": { "title": "Legal-form label language", "enum": [ "en", "de", "fr", "it" ], "type": "string", "description": "Language of the human-readable legalFormLabel. The raw 4-digit code stays in legalForm.", "default": "en" }, "includeTitleTranslations": { "title": "Include the headline in all four languages", "type": "boolean", "description": "SHAB publishes each headline in German, French, Italian and English. English is always emitted; this adds the other three.", "default": false }, "includePublicationUrl": { "title": "Include the shab.ch link", "type": "boolean", "description": "A direct link to the published notice on shab.ch. A Zefix company link is always included.", "default": true }, "includeXmlUrl": { "title": "Include the source XML link", "type": "boolean", "description": "The API URL of the underlying register XML, so you can audit any row back to the source bytes.", "default": false }, "includePdfUrl": { "title": "Include the signed-PDF link", "type": "boolean", "description": "The officially signed PDF of the notice. Not every publication has one.", "default": false }, "includeRawXml": { "title": "Include the raw register XML", "type": "boolean", "description": "Attaches the complete source XML to every row. An escape hatch for buyers who want fields we do not surface; it makes rows several kilobytes larger.", "default": false }, "fieldsToInclude": { "title": "Keep only these fields", "type": "array", "description": "Whitelist of output field names, e.g. companyName, uid, addressFull, primaryPerson. Empty keeps every field. A whitelist that matches nothing is ignored rather than emptying your rows.", "default": [], "items": { "type": "string" } }, "flattenOutput": { "title": "Flatten for CSV or Sheets", "type": "boolean", "description": "Flattens nested objects and arrays into dot-notation columns (registeredPersons.0.fullName and so on) so a CSV or Google Sheets export is readable.", "default": false }, "maxItems": { "title": "Maximum companies", "minimum": 0, "type": "integer", "description": "Hard cap on billed companies. Set 0 for no cap, bounded then only by your date window and the run timeout.", "default": 100 }, "maxDaysToCrawl": { "title": "Maximum publication days", "minimum": 0, "type": "integer", "description": "Stop after this many publication days, whatever the date window says. 0 means no limit. A safety rail for large historical backfills.", "default": 0 }, "dedupeBy": { "title": "Also collapse duplicates by", "enum": [ "publicationId", "uid", "none" ], "type": "string", "description": "The same publication is NEVER delivered or billed twice; that guard is always on. This chooses whether a second, company-level pass also collapses two publications sharing one CHE UID (rare in HR01, but possible across a wide window).", "default": "publicationId" }, "dedupeAgainstPreviousRuns": { "title": "Skip companies seen in earlier runs", "type": "boolean", "description": "Remembers every publication ID in a NAMED key-value store that survives between runs, so a daily or weekly schedule only ever returns, and only ever bills, genuinely new registrations.", "default": false }, "onlyNewSinceLastRun": { "title": "Start where the last run stopped", "type": "boolean", "description": "Begins the date window at the newest publication date any previous run delivered, instead of the lookback window. Uses the same named store.", "default": false }, "namedStateStoreKey": { "title": "Name of the memory store", "type": "string", "description": "Optional. Which named key-value store holds the run-to-run memory. Defaults to shab-new-companies-state. Give separate schedules separate names so they do not share memory.", "default": "" }, "sortOrder": { "title": "Publication date order", "enum": [ "desc", "asc" ], "type": "string", "description": "Newest publication day first, or oldest first, which is better for a chronological backfill.", "default": "desc" }, "requestConcurrency": { "title": "Concurrent requests", "minimum": 1, "maximum": 20, "type": "integer", "description": "Parallel register-XML fetches. Measured success through the Apify datacenter proxy: 5 gave 100% (15/15), 10 gave 100% (30/30), 20 gave 95% (57/60, and all 3 losses were proxy-side socket resets, never a block from shab.ch). 10 is the tested sweet spot.", "default": 10 }, "maxRequestRetries": { "title": "Retries per request", "minimum": 0, "maximum": 8, "type": "integer", "description": "Across 554 recon requests, 98.0% succeeded first try and 100% succeeded after at most one retry. Every loss was an Apify-proxy socket reset: no CAPTCHA, no 403, no rate limit.", "default": 3 }, "requestTimeoutSecs": { "title": "Request timeout (seconds)", "minimum": 5, "maximum": 300, "type": "integer", "description": "How long a single request may take before it is retried.", "default": 60 }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Apify datacenter proxy is the default and is all this Actor needs: measured 200 OK on datacenter, on residential Switzerland and on residential US, all returning identical data. Residential was 5x slower for no benefit. Pin a country only if your own policy requires it.", "default": { "useApifyProxy": true } }, "webhookUrl": { "title": "Webhook URL", "type": "string", "description": "Optional. POSTed a JSON summary at the end of the run: company count, the run and dataset IDs, and up to 50 sample companies. Pair it with the memory store for a genuine new-registration alert.", "default": "" }, "slackWebhookUrl": { "title": "Slack webhook URL", "type": "string", "description": "Optional. Posts a formatted digest of the newest registrations to a Slack incoming webhook.", "default": "" }, "notifyOnlyNew": { "title": "Alert only on genuinely new companies", "type": "boolean", "description": "Restricts the webhook and Slack alerts to publications not seen by a previous run. Uses the same named memory store.", "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 } } } } } } } } } }