{ "openapi": "3.0.1", "info": { "title": "Mentions Legales Scraper - French SIREN, RCS, TVA & Contacts", "description": "Turn French business domains into registry-grade B2B leads from each site's legally-mandated mentions legales page: SIREN, SIRET, RCS + greffe, TVA, capital social, APE, directeur de la publication, hebergeur, email, phone and address. No login, no API key.", "version": "0.1", "x-build-id": "rYJJsdnICN48NSTup" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/scrapersdelight~mentions-legales-contact-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-scrapersdelight-mentions-legales-contact-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/scrapersdelight~mentions-legales-contact-scraper/runs": { "post": { "operationId": "runs-sync-scrapersdelight-mentions-legales-contact-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/scrapersdelight~mentions-legales-contact-scraper/run-sync": { "post": { "operationId": "run-sync-scrapersdelight-mentions-legales-contact-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "domains": { "title": "French domains (or mentions-légales URLs)", "type": "array", "description": "One entry per company. Accepts all three shapes: a bare domain (\"donatek.fr\"), a homepage URL (\"https://www.sapio-arts.fr\") or a direct mentions-légales URL (\"https://x.fr/mentions-legales\"). The Actor finds each site's legal-notice page and parses the statutory fields out of it — one lead per domain. Leave empty to run the built-in French demo batch.", "items": { "type": "string" } }, "startUrls": { "title": "Start URLs (list source)", "type": "array", "description": "The same domain list handed over as URLs, so Make, Zapier, Clay or a Google Sheet can pass it natively (a link to a text/CSV file of URLs also works). Merged with \"French domains\".", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "sourceDatasetId": { "title": "Enrich an existing dataset", "type": "string", "description": "Dataset ID of a previous Actor run. Each item's domain/website column is read and enriched — the real agency workflow: run a directory or Maps scraper first, then pipe its output here." }, "domainFieldName": { "title": "Domain field / CSV column", "type": "string", "description": "Which field of the source dataset (or which CSV column of the list file) holds the domain. Leave empty to auto-detect domain / website / websiteUrl / url / site / homepage. Dotted paths like \"company.website\" work." }, "domainsFileUrl": { "title": "Domain list file URL", "type": "string", "description": "URL of a CSV, TXT, JSON or JSONL file holding the domains — for 100k-row lists that will not paste into the editor. The column is picked with \"Domain field / CSV column\"." }, "skipDomains": { "title": "Suppression list", "type": "array", "description": "Domains to skip outright — accounts you already own, competitors, do-not-contact entries. Matched on the registrable domain, so \"www.x.fr/page\" and \"x.fr\" are the same entry.", "items": { "type": "string" } }, "previousDatasetId": { "title": "Skip rows already delivered (dataset ID)", "type": "string", "description": "Dataset ID of an earlier run of THIS Actor. Its stableId / siren / domain values are loaded as a suppression list, so a monthly re-run never re-delivers — and never re-charges you for — a company you already bought." }, "maxItems": { "title": "Max results (billed rows)", "minimum": 0, "type": "integer", "description": "Hard cap on rows DELIVERED AND BILLED this run. Distinct from \"Max domains\": roughly 3 of 4 reachable French sites publish a legal notice, so 1,000 domains yield ~740 billed rows. 0 = unlimited.", "default": 1000 }, "maxDomains": { "title": "Max domains attempted", "minimum": 0, "type": "integer", "description": "Cap on domains ATTEMPTED, applied before any request. Use it to sample a big list cheaply. 0 = attempt every domain supplied.", "default": 0 }, "maxDiscoveryRequestsPerDomain": { "title": "Max discovery requests per domain", "minimum": 1, "maximum": 40, "type": "integer", "description": "Hard cap on discovery + confirmation requests per domain, counted after the homepage. This is the knob that stops one slow host burning two minutes of a run. Anchor discovery alone costs 2 requests; the full cascade can reach 14. Recon measured the yield plateau at about 10.", "default": 12 }, "perDomainTimeoutSecs": { "title": "Per-domain timeout (seconds)", "minimum": 5, "maximum": 600, "type": "integer", "description": "Wall-clock deadline for one domain, discovery included. Measured latency on delivered rows: p50 5.6 s, p90 14.0 s, max 28.8 s — 60 s leaves headroom without letting a pathological host stall the pool.", "default": 60 }, "requestConcurrency": { "title": "Request concurrency", "minimum": 1, "maximum": 30, "type": "integer", "description": "How many domains are worked in parallel. Higher is faster; keep it modest to stay polite to small business sites.", "default": 10 }, "requestTimeoutSecs": { "title": "Request timeout (seconds)", "minimum": 5, "maximum": 120, "type": "integer", "description": "Timeout for a single HTTP request.", "default": 30 }, "maxRequestRetries": { "title": "Max request retries", "minimum": 0, "maximum": 6, "type": "integer", "description": "Retries per request, each on a FRESH proxy IP (got-scraping's own retry reuses the flagged IP, which is useless against a soft block).", "default": 2 }, "discoveryChannels": { "title": "Discovery channels", "type": "array", "description": "Which channels may be used to locate the legal-notice page, tried in this order. Anchor ranking alone won 25 of 26 successful discoveries in recon, so turning the rest off is a real cost lever on a big list. wp-json is what finds WordPress sites whose footer carries no legal link at all.", "items": { "type": "string", "enum": [ "anchor", "sitemap", "wpJson", "pathGuess" ], "enumTitles": [ "Homepage footer anchors (ranked)", "XML sitemap", "WordPress REST page index", "Guessed paths" ] }, "default": [ "anchor", "sitemap", "wpJson", "pathGuess" ] }, "followWwwAndRootVariants": { "title": "Try www and apex variants", "type": "boolean", "description": "If the homepage fails, retry the other host form (www.x.fr ↔ x.fr) before declaring the domain unreachable.", "default": true }, "deepJsDiscovery": { "title": "Deep JS fallback (JS-only footers)", "type": "boolean", "description": "Last-resort channel for a footer that only exists after client-side render. No Chromium is launched — this build is deliberately browser-free, because a browser image would quadruple the compute cost of every run for a case recon measured as rare. Instead the Actor reads what a render would have read FROM: the page's inline JSON payloads and its external JavaScript bundles, searching them for a legal-notice URL. Costs up to 6 extra requests per domain and is never charged separately. (Renamed from useBrowserFallback, which read as if it launched a browser; the old key is still accepted.)", "default": false }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "Fetch and honour each site's robots.txt before requesting anything. Off by default because it costs one extra request per domain and measured 0 of 10 French sites (SME and enterprise) disallow the legal-notice path — those pages exist to be indexed.", "default": false }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Proxy settings. Apify DATACENTER is the default and is the measured winner: 98.4% usable transport on the French SME corpus, zero 403s, zero CAPTCHAs. Residential changed nothing there, so it is not the default.", "default": { "useApifyProxy": true } }, "proxyCountry": { "title": "Proxy country", "enum": [ "none", "FR", "BE", "CH", "LU", "MC", "CA" ], "type": "string", "description": "Pin the exit country for francophone sites outside France that geo-tailor their content. MEASURED: Apify datacenter proxies cannot be pinned to a country (they answer HTTP 407), so choosing a country here switches the run to RESIDENTIAL exit nodes in that country. Leave on None for the cheaper, faster datacenter path that the French SME corpus does not need a country for.", "default": "none" }, "escalateToResidentialOnBlock": { "title": "Escalate to residential on a block", "type": "boolean", "description": "On a 403 / challenge (never on a dead host or a 404), retry the request once on RESIDENTIAL + country-FR. Measured: this is what recovers CDN-fronted French brands such as blablacar.fr. Small SME lists never trigger it.", "default": true }, "customUserAgent": { "title": "Custom User-Agent", "type": "string", "description": "Override the browser User-Agent sent on every request. Leave empty for the built-in Chrome 124 fingerprint." }, "extraHttpHeaders": { "title": "Extra HTTP headers", "type": "object", "description": "Additional request headers, merged over the defaults (e.g. a From: header identifying your crawler)." }, "tldFilterMode": { "title": "TLD filter mode", "enum": [ "none", "include", "exclude" ], "type": "string", "description": "Many French SMEs are not on .fr (.com, .paris, .bzh, .eu, .alsace). Choose whether the TLD list below includes or excludes.", "default": "none" }, "tldFilter": { "title": "TLDs", "type": "array", "description": "The TLD list the mode above applies to, without the dot: fr, com, paris, bzh, eu.", "items": { "type": "string" } }, "requireRegistryId": { "title": "Only rows with a registry ID", "type": "boolean", "description": "Deliver (and bill) only companies whose legal notice carries a SIREN, SIRET or TVA number, and whose SIREN passes the Luhn checksum. A page whose registry id fails the checksum is filtered out here, never billed. Measured: 83% of parsed pages carry at least one id.", "default": false }, "requireContact": { "title": "Only rows with a contact", "type": "boolean", "description": "Deliver (and bill) only companies with an email or a phone number. Measured: 89% of parsed pages carry at least one.", "default": false }, "minFieldsRequired": { "title": "Minimum populated fields", "minimum": 0, "maximum": 17, "type": "integer", "description": "Quality floor: a row must carry at least this many of the 17 value fields (company, legal form, SIREN, SIRET, TVA, RCS city + number, capital, APE, director, representative, host, address, postcode, city, email, phone) before it is delivered and billed. 0 = no floor.", "default": 0 }, "emailPolicy": { "title": "Email policy", "enum": [ "all", "role-only", "exclude-role" ], "type": "string", "description": "Agencies split hard on whether contact@ / info@ counts as a lead. \"Role only\" keeps just those; \"Exclude role\" keeps only named mailboxes.", "default": "all" }, "dedupeBy": { "title": "Deduplicate by", "enum": [ "siren-then-domain", "domain", "siren", "none" ], "type": "string", "description": "Which key collapses duplicates BEFORE anything is pushed or charged. The default uses a Luhn-valid SIREN when the page carries one and the registrable domain otherwise, so two domains owned by the same company collapse to one billed row — and a repeated input line is dropped at queue time, before it costs a request. \"No deduplication\" genuinely means none: you get, and pay for, one row per input line.", "default": "siren-then-domain" }, "validateSiren": { "title": "Luhn-check the SIREN", "type": "boolean", "description": "Verify every SIREN against the Luhn checksum and emit sirenValid. A failure is FLAGGED, never dropped — La Poste (356000000) is a legitimate national exception.", "default": true }, "deriveSirenFromVat": { "title": "Derive the SIREN from the TVA number", "type": "boolean", "description": "A French TVA number is FR + a 2-character key + the 9-digit SIREN, so the TVA is an exact container for it. Keeping this on fixes a real cross-field bug: on one probe site an RCS regex pulled a DIFFERENT 9-digit window out of the TVA string and produced a wrong SIREN.", "default": true }, "extractHostingProvider": { "title": "Extract the hébergeur", "type": "boolean", "description": "The site's host (OVH, o2switch, Wix, Shopify, Cloudflare…) plus its address. 87% fill — a technographic signal hosting resellers and agencies buy on its own.", "default": true }, "extractDpo": { "title": "Extract the DPO contact", "type": "boolean", "description": "Délégué à la protection des données / data protection officer contact, for GDPR and KYB buyers.", "default": true }, "extractSocials": { "title": "Extract social profiles", "type": "boolean", "description": "LinkedIn, Facebook, Instagram, X, YouTube and TikTok links present on the legal-notice page.", "default": true }, "extractPolicyUrls": { "title": "Extract CGV & privacy-policy URLs", "type": "boolean", "description": "The site's terms (CGV/CGU) and privacy-policy URLs, linked from the legal notice.", "default": true }, "includeRawText": { "title": "Include the cleaned legal-notice text", "type": "boolean", "description": "Attach the parsed page as plain text (capped at 40,000 characters) so you can audit a field or re-parse it with your own LLM.", "default": false }, "includeRawHtml": { "title": "Include the raw HTML", "type": "boolean", "description": "Attach the legal-notice page's raw HTML (capped at 200,000 characters). Makes the dataset much larger.", "default": false }, "includeMissRows": { "title": "Include unbilled miss rows", "type": "boolean", "description": "Emit a row for every domain that produced no lead — dead host, blocked, publishes no legal notice, filtered out, a duplicate, or suppressed by skipDomains / previousDatasetId — with its status and missReason, so you can do coverage accounting. These rows are NEVER charged.", "default": false }, "flattenOutput": { "title": "Flat columns", "type": "boolean", "description": "On: one flat row, ready for Google Sheets, Clay or a CSV export. Off: fields grouped into registry {}, people {}, contact {}, hosting {} and policies {} objects.", "default": true } } }, "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 } } } } } } } } } }