{ "openapi": "3.0.1", "info": { "title": "ZocDoc + Healthgrades Doctors & Reviews Scraper", "description": "Scrape physicians, specialists, ratings, reviews, accepted insurance, locations, and bio data from ZocDoc.com and Healthgrades.com. Single actor with platform switch (zocdoc | healthgrades). No login required.", "version": "1.0", "x-build-id": "c7AKPSJymfjR2irwa" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/crawlerbros~zocdoc-healthgrades-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-crawlerbros-zocdoc-healthgrades-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/crawlerbros~zocdoc-healthgrades-scraper/runs": { "post": { "operationId": "runs-sync-crawlerbros-zocdoc-healthgrades-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/crawlerbros~zocdoc-healthgrades-scraper/run-sync": { "post": { "operationId": "run-sync-crawlerbros-zocdoc-healthgrades-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "required": [ "platform", "mode" ], "properties": { "platform": { "title": "Platform", "enum": [ "healthgrades", "zocdoc" ], "type": "string", "description": "Which provider directory to scrape. Healthgrades is recommended (works from Apify datacenter IPs without proxy). ZocDoc is fronted by aggressive DataDome anti-bot that blocks even residential proxies most of the time — use only when you have a clean residential IP pool.", "default": "healthgrades" }, "mode": { "title": "Mode", "enum": [ "search", "byProvider", "bySpecialty", "byCity", "byInsurance", "byUrl" ], "type": "string", "description": "What to scrape. `search` accepts city + specialty; `byProvider` takes a provider URL or slug; `bySpecialty` browses a single specialty hub; `byCity` lists every specialty in a city; `byInsurance` filters by an accepted plan (ZocDoc-only); `byUrl` accepts arbitrary listing URLs.", "default": "search" }, "specialty": { "title": "Specialty", "enum": [ "primary-care-doctor", "family-physician", "internist", "pediatrician", "obstetrician-gynecologist", "dermatologist", "ophthalmologist", "optometrist", "ent-doctor", "dentist", "orthodontist", "endodontist", "periodontist", "oral-surgeon", "pediatric-dentist", "prosthodontist", "psychiatrist", "psychologist", "therapist-counselor", "marriage-counselor", "psychotherapist", "child-psychiatrist", "addiction-medicine", "cardiologist", "gastroenterologist", "endocrinologist", "rheumatologist", "pulmonologist", "neurologist", "nephrologist", "hematologist", "infectious-disease", "allergist", "immunologist", "geriatrician", "oncologist", "radiation-oncologist", "surgical-oncologist", "general-surgeon", "vascular-surgeon", "plastic-surgeon", "neurosurgeon", "cardiothoracic-surgeon", "colon-rectal-surgeon", "hand-surgeon", "orthopedic-surgeon", "podiatrist", "urologist", "sports-medicine", "physical-therapist", "occupational-therapist", "speech-therapist", "chiropractor", "acupuncturist", "massage-therapist", "naturopath", "midwife", "nurse-practitioner", "physician-assistant", "audiologist", "dietitian-nutritionist", "anesthesiologist", "pain-management-specialist", "sleep-medicine", "emergency-medicine", "hospice-palliative-care", "preventive-medicine", "physiatrist", "radiologist", "pathologist", "neonatologist", "perinatologist", "reproductive-endocrinologist", "fertility-specialist", "urogynecologist", "maternal-fetal-medicine", "gynecologic-oncologist", "pediatric-cardiologist", "pediatric-neurologist", "pediatric-orthopedic-surgeon", "pediatric-endocrinologist", "pediatric-allergist" ], "type": "string", "description": "Medical specialty slug. Used by `search` and `bySpecialty`." }, "city": { "title": "City slug or 'city, ST'", "type": "string", "description": "City for `search`, `byCity`. ZocDoc format: `new-york-ny`, `los-angeles-ca`. Healthgrades format: `New York, NY` or `Boston, MA`. The actor accepts either form and normalizes per platform." }, "state": { "title": "US state code", "enum": [ "AL", "AK", "AZ", "AR", "CA", "CO", "CT", "DE", "DC", "FL", "GA", "HI", "ID", "IL", "IN", "IA", "KS", "KY", "LA", "ME", "MD", "MA", "MI", "MN", "MS", "MO", "MT", "NE", "NV", "NH", "NJ", "NM", "NY", "NC", "ND", "OH", "OK", "OR", "PA", "RI", "SC", "SD", "TN", "TX", "UT", "VT", "VA", "WA", "WV", "WI", "WY" ], "type": "string", "description": "Two-letter US state code (used for disambiguation when city alone is ambiguous)." }, "gender": { "title": "Provider gender", "enum": [ "any", "female", "male" ], "type": "string", "description": "Filter providers by gender (best-effort — not all providers expose this).", "default": "any" }, "language": { "title": "Language spoken", "enum": [ "any", "en", "es", "fr", "de", "it", "pt", "ru", "zh", "ja", "ko", "vi", "ar", "hi", "bn", "pa", "ur", "fa", "tr", "pl", "uk", "nl", "sv", "da", "no", "fi", "el", "he", "th", "tl", "id", "ms", "sw", "ro", "hu", "cs", "sk", "bg", "hr", "sr", "ta", "te", "ml", "mr", "gu", "kn", "yo", "ig", "ha", "am", "so", "ps" ], "type": "string", "description": "Filter providers who speak this language (ISO 639-1 code).", "default": "any" }, "acceptsNewPatients": { "title": "Accepting new patients only", "type": "boolean", "description": "Drop providers not currently accepting new patients.", "default": false }, "minRating": { "title": "Minimum rating", "minimum": 1, "maximum": 5, "type": "integer", "description": "Drop providers with star rating below this threshold (1-5)." }, "minReviewCount": { "title": "Minimum review count", "minimum": 0, "maximum": 100000, "type": "integer", "description": "Drop providers with fewer reviews than this." }, "insurance": { "title": "Insurance plan (ZocDoc only)", "enum": [ "any", "aetna", "anthem-blue-cross", "blue-cross-blue-shield", "cigna", "humana", "united-healthcare", "kaiser-permanente", "medicare", "medicaid", "tricare", "ambetter", "amerigroup", "centene", "molina", "wellcare", "fidelis", "emblemhealth", "healthfirst", "metroplus", "carefirst", "horizon-bcbs", "highmark", "premera", "regence", "florida-blue", "blue-shield-california", "empire-bcbs", "independence-blue-cross", "anthem-bcbs", "hcsc", "molina-healthcare", "oscar", "magellan", "beacon-health-options", "optum", "evernorth", "meritain", "healthnet", "bright-health", "guardian", "delta-dental", "metlife-dental", "principal", "vsp", "eyemed", "mvp-healthcare", "tufts", "harvard-pilgrim", "blueshield-northeastern-ny", "geha", "fep-blue", "uhc-community-plan" ], "type": "string", "description": "Filter providers who accept this insurance plan. ZocDoc-only — Healthgrades doesn't expose plan-level filtering.", "default": "any" }, "providerUrlsOrSlugs": { "title": "Provider URLs or slugs (mode=byProvider)", "type": "array", "description": "Provider profile URLs (e.g. `https://www.zocdoc.com/doctor/john-smith-md-12345`, `https://www.healthgrades.com/physician/dr-john-smith-xyz`) or just the slug.", "default": [], "items": { "type": "string" } }, "urls": { "title": "Listing URLs (mode=byUrl)", "type": "array", "description": "Raw ZocDoc or Healthgrades listing/search URLs to scrape.", "default": [], "items": { "type": "string" } }, "fetchProviderDetails": { "title": "Fetch full provider details", "type": "boolean", "description": "Whether to follow each search-result URL to fetch the full provider profile (bio, ratings, languages, insurance, locations, reviews). Disable for faster but lighter listing-only output.", "default": true }, "maxReviewsPerProvider": { "title": "Max reviews per provider", "minimum": 0, "maximum": 500, "type": "integer", "description": "Cap on reviews emitted per provider (0 = no reviews).", "default": 20 }, "maxItems": { "title": "Max items", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Hard cap on emitted provider records.", "default": 25 }, "maxPagesPerListing": { "title": "Max listing pages to crawl", "minimum": 1, "maximum": 50, "type": "integer", "description": "How many search-result pages to walk per seed.", "default": 3 }, "autoEscalateOnBlock": { "title": "Auto-escalate to Apify proxy on block", "type": "boolean", "description": "When a fetch returns 403/anti-bot block, automatically engage Apify Proxy (datacenter US → residential US fallback). Both ZocDoc (DataDome) and Healthgrades (geo-block) require US-egress proxy from cloud datacenters.", "default": true }, "proxyGroups": { "title": "Apify proxy groups (used on auto-escalation)", "type": "array", "description": "Proxy groups to try on the first block. Empty = datacenter (default), then residential fallback automatically.", "default": [], "items": { "type": "string" } } } }, "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 } } } } } } } } } }