{ "openapi": "3.0.1", "info": { "title": "Justia Lawyer Directory Scraper - Attorney Data & Leads", "description": "Scrape lawyers from the Justia Lawyer Directory by location and practice area, or from listing / profile URLs. One row per attorney: name, phone, firm, address, practice areas, years of experience, education, bar memberships, website and social links. Optional full-profile enrichment. JSON/CSV out.", "version": "0.1", "x-build-id": "lgjAF81bjczXzLmPL" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/memo23~justia-lawyer-directory-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-memo23-justia-lawyer-directory-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/memo23~justia-lawyer-directory-scraper/runs": { "post": { "operationId": "runs-sync-memo23-justia-lawyer-directory-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/memo23~justia-lawyer-directory-scraper/run-sync": { "post": { "operationId": "run-sync-memo23-justia-lawyer-directory-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "locations": { "title": "Locations", "type": "array", "description": "Locations to scrape, as Justia path segments: `state/city` or just `state`. Examples: `california/los-angeles`, `new-york/new-york`, `texas`. Each is paginated. Combined with any practice areas below.", "items": { "type": "string" } }, "practiceAreas": { "title": "Practice areas (optional)", "type": "array", "description": "Optional practice-area filters, as Justia slugs: `personal-injury`, `criminal-law`, `family-law`, `bankruptcy`, `business-law`, `divorce`, `dui-dwi`, `estate-planning`, `immigration-law`, `real-estate-law`. Each location × practice area builds one listing. Leave empty to scrape all lawyers in the location.", "items": { "type": "string" } }, "startUrls": { "title": "Listing & profile URLs", "type": "array", "description": "Direct listing URLs (`https://www.justia.com/lawyers/california/los-angeles`) and/or lawyer profile URLs (`https://lawyers.justia.com/lawyer/{slug}-{id}`). Auto-classified.", "items": { "type": "string" } }, "scrapeDetails": { "title": "Scrape full profile pages", "type": "boolean", "description": "For each lawyer found in a listing, also fetch their profile page to add the firm name, full street address, geo coordinates, all bar memberships, education, job titles, social links, fax, opening hours and profile FAQ. Richer rows, but ~2× the requests. Off = the listing-card fields (already ~20 per lawyer). Profile URLs you paste are always fully detailed.", "default": false }, "maxItems": { "title": "Max results (whole run)", "minimum": 1, "type": "integer", "description": "Hard cap on rows across the entire run. Each row is one paid `lawyer` event. Default 1000. Free-tier users are additionally capped at 100.", "default": 1000 }, "maxItemsPerSearch": { "title": "Max lawyers per listing", "minimum": 1, "type": "integer", "description": "Cap per location / listing URL. Justia returns ~40-50 lawyers per page. Default 1000.", "default": 1000 }, "maxConcurrency": { "title": "Max parallel requests", "minimum": 1, "maximum": 15, "type": "integer", "description": "Parallel HTTP requests. Justia is protected by Cloudflare — keep this moderate (4-8). Default 6.", "default": 6 }, "maxRequestRetries": { "title": "Max request retries", "minimum": 0, "type": "integer", "description": "Per-request retry budget on Cloudflare challenges (403), 429 and network errors. Each retry rotates to a fresh residential IP. Default 20 (the Cloudflare challenge is flaky — more retries help break through).", "default": 20 }, "proxy": { "title": "Proxy configuration (optional override)", "type": "object", "description": "Leave empty — the actor already routes all traffic through its own built-in residential proxy at no extra cost to you. Only set this if you want to use your own proxies." } } }, "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 } } } } } } } } } }