{ "openapi": "3.0.1", "info": { "title": "Justia Lawyer Scraper [Only $0.9/1KšŸ’°] | Leads | Legal Data", "description": "Scrape lawyer profiles and attorney leads from the Justia Lawyer Directory: name, firm, phone, practice areas, Justia rating, peer reviews and credentials. For legal lead generation and law firm databases. From $0.0009 per lawyer.", "version": "0.4", "x-build-id": "Fil8Tt2sgEgno9iRq" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/ahmed_jasarevic~lawyers-justia-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-ahmed_jasarevic-lawyers-justia-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/ahmed_jasarevic~lawyers-justia-scraper/runs": { "post": { "operationId": "runs-sync-ahmed_jasarevic-lawyers-justia-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/ahmed_jasarevic~lawyers-justia-scraper/run-sync": { "post": { "operationId": "run-sync-ahmed_jasarevic-lawyers-justia-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": { "startUrls": { "title": "Start URLs", "type": "array", "description": "Specific Justia URLs to scrape. Can be lawyer profile URLs (https://lawyers.justia.com/lawyer/...) or directory listing URLs (https://www.justia.com/lawyers/...). If provided, the filters below are ignored.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "states": { "title": "States", "type": "array", "description": "US state codes to scrape (e.g. CA, NY, TX). Leave empty to scrape all states.", "items": { "type": "string" } }, "practiceAreas": { "title": "Practice Areas", "type": "array", "description": "Practice-area slugs to filter by (e.g. personal-injury, family-law, criminal-law). Leave empty for all practice areas.", "items": { "type": "string" } }, "city": { "title": "City", "type": "string", "description": "City name to filter by (e.g. Los Angeles). Only used together with a state." }, "maxItems": { "title": "Max Items", "minimum": 1, "type": "integer", "description": "Maximum number of lawyer profiles to save to the dataset.", "default": 100 }, "maxRequestsPerCrawl": { "title": "Max Requests per Crawl", "minimum": 1, "type": "integer", "description": "Maximum number of pages (listing + profile) the crawler may load. Protects against runaway runs.", "default": 200 }, "maxConcurrency": { "title": "Max Concurrency", "minimum": 1, "maximum": 20, "type": "integer", "description": "How many pages (listing + profile) to download at the same time. Default 10. Measured on Justia: a request through the Unblocker takes ~33 s when Cloudflare challenges it (~1.5 s when it doesn't) and total throughput plateaus at 8ā€“14 pages/min ā€” above ~10 parallel requests the proxy just queues them (higher latency, more HTTP 502 retries, no extra speed). Raise only up to ~12; lower to 6 if you see repeated HTTP 502/403 retries.", "default": 10 }, "maxRequestRetries": { "title": "Max Request Retries", "minimum": 1, "maximum": 50, "type": "integer", "description": "How many times to retry a failed or blocked request before giving up (exponential backoff between attempts).", "default": 4 }, "scrapeDetails": { "title": "Scrape Full Profiles", "type": "boolean", "description": "true (default): visit every lawyer profile page for complete data ā€” full bio, review text, awards, associations, languages, jurisdictions. false: listing-only mode ā€” one request per ~50 lawyers, saving the listing row directly (name, firm, phone, address, city/state/zip, Justia rating, peer-review count, claimed flag, education, practice areas, years of experience, bio, website, avatar). Listing-only is ~50x faster and cheaper per row and is the right choice for bulk contact lists.", "default": true }, "proxy": { "title": "Proxy configuration", "type": "object", "description": "Proxy settings. Justia is behind a Cloudflare challenge, so keep the proxy enabled and use the UNBLOCKER group ā€” it bypasses the challenge for plain HTTP requests (no browser needed). The proxy is used even when this field is omitted; only set useApifyProxy to false to disable it (most requests will then fail with HTTP 403).", "default": { "useApifyProxy": true, "apifyProxyGroups": [ "UNBLOCKER" ] } } } }, "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 }, "PROXY_UNBLOCKER_UNITS": { "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 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } } } } } } } } }