{ "openapi": "3.0.1", "info": { "title": "MSHA Mine Data Scraper - Violations, Inspections, Accidents", "description": "Streams all 20 MSHA Open Government Data files, 17.8 million rows on US mines, violations, inspections, accidents, penalties, production and health samples.", "version": "0.1", "x-build-id": "iHTq7M5OYv7gG2fZi" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/parseforge~msha-mine-data-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-parseforge-msha-mine-data-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/parseforge~msha-mine-data-scraper/runs": { "post": { "operationId": "runs-sync-parseforge-msha-mine-data-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/parseforge~msha-mine-data-scraper/run-sync": { "post": { "operationId": "run-sync-parseforge-msha-mine-data-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "datasets": { "title": "Datasets", "type": "array", "description": "Which MSHA Open Government Data files to read. Each selected dataset is downloaded and streamed in turn, and every dataset bills its own event. Row counts are from the 2026-08-21 publication.", "items": { "type": "string", "enum": [ "mines", "violations", "assessedViolations", "contestedViolations", "inspections", "accidents", "penaltyDockets", "conferences", "orders107a", "mineAddresses", "controllerHistory", "productionQuarterly", "productionYearly", "contractorProductionQuarterly", "contractorProductionYearly", "coalDustSamples", "quartzSamples", "areaSamples", "personalHealthSamples", "noiseSamples" ], "enumTitles": [ "Mines - mine master, 91,979 rows", "Violations - citations and orders, 3,096,400 rows", "Assessed violations - penalties, 3,029,093 rows", "Contested violations - FMSHRC dockets, 451,718 rows", "Inspections, 1,156,532 rows", "Accidents, injuries and illnesses, 274,448 rows", "Civil penalty dockets and decisions, 481,753 rows", "Safety and health conferences, 162,065 rows", "107(a) imminent danger orders, 3,861 rows", "Mine addresses of record, 91,684 rows", "Controller and operator history, 169,809 rows", "Mine employment and production, quarterly, 2,761,063 rows", "Mine employment and production, yearly, 658,798 rows", "Contractor employment and production, quarterly, 1,361,752 rows", "Contractor employment and production, yearly, 281,183 rows", "Coal respirable dust samples, 3,016,910 rows", "Coal quartz samples, 168,465 rows", "Metal/nonmetal area samples, 8,714 rows", "Metal/nonmetal personal health samples, 314,473 rows", "Noise samples, 275,881 rows" ] }, "default": [ "mines" ] }, "maxItems": { "title": "Max Items", "minimum": 1, "maximum": 1000000, "type": "integer", "description": "Free users: limited to 10 items (preview). Paid users: up to 1,000,000. This is the total across every selected dataset." }, "maxItemsPerDataset": { "title": "Max items per dataset", "minimum": 1, "maximum": 1000000, "type": "integer", "description": "Cap for each selected dataset. Leave empty and the Max Items budget is split evenly across the datasets you selected." }, "mineIds": { "title": "Mine IDs", "type": "array", "description": "Seven digit MSHA mine IDs, for example 0100003. Shorter IDs are zero padded for you. Applies to every dataset that carries a mine ID; contractor production and conferences do not, so they return nothing when this is set.", "items": { "type": "string" } }, "companyIds": { "title": "Company IDs", "type": "array", "description": "Controller, operator, contractor or violator IDs, for example 0041044 or L13586. A row matches when any of the dataset's company ID columns equals one of these.", "items": { "type": "string" } }, "states": { "title": "States", "type": "array", "description": "Two letter state or territory. Datasets without a state column are matched through the mine master, which is loaded once and not billed.", "items": { "type": "string", "enum": [ "AK", "AL", "AR", "AS", "AZ", "CA", "CO", "CT", "DC", "DE", "FL", "GA", "GU", "HI", "IA", "ID", "IL", "IN", "KS", "KY", "LA", "MA", "MD", "ME", "MI", "MN", "MO", "MP", "MS", "MT", "NC", "ND", "NE", "NH", "NJ", "NM", "NV", "NY", "OH", "OK", "OR", "PA", "PR", "RI", "SC", "SD", "TN", "TX", "UT", "VA", "VI", "VT", "WA", "WI", "WV", "WY" ], "enumTitles": [ "AK - Alaska", "AL - Alabama", "AR - Arkansas", "AS - American Samoa", "AZ - Arizona", "CA - California", "CO - Colorado", "CT - Connecticut", "DC - District of Columbia", "DE - Delaware", "FL - Florida", "GA - Georgia", "GU - Guam", "HI - Hawaii", "IA - Iowa", "ID - Idaho", "IL - Illinois", "IN - Indiana", "KS - Kansas", "KY - Kentucky", "LA - Louisiana", "MA - Massachusetts", "MD - Maryland", "ME - Maine", "MI - Michigan", "MN - Minnesota", "MO - Missouri", "MP - Northern Mariana Islands", "MS - Mississippi", "MT - Montana", "NC - North Carolina", "ND - North Dakota", "NE - Nebraska", "NH - New Hampshire", "NJ - New Jersey", "NM - New Mexico", "NV - Nevada", "NY - New York", "OH - Ohio", "OK - Oklahoma", "OR - Oregon", "PA - Pennsylvania", "PR - Puerto Rico", "RI - Rhode Island", "SC - South Carolina", "SD - South Dakota", "TN - Tennessee", "TX - Texas", "UT - Utah", "VA - Virginia", "VI - U.S. Virgin Islands", "VT - Vermont", "WA - Washington", "WI - Wisconsin", "WV - West Virginia", "WY - Wyoming" ] } }, "coalOrMetal": { "title": "Coal or metal/nonmetal", "enum": [ "any", "C", "M" ], "type": "string", "description": "Restrict to coal mines or to metal and nonmetal mines.", "default": "any" }, "searchText": { "title": "Search text", "type": "string", "description": "Case insensitive substring matched against the dataset's name columns: mine, operator, controller, contractor and violator names, plus the accident narrative. Datasets with no name column match their identifier columns instead." }, "dateFrom": { "title": "Date from", "type": "string", "description": "Inclusive lower bound on the dataset's main date, in YYYY-MM-DD. On the four employment and production files, which only carry a calendar year, the year part is compared instead." }, "dateTo": { "title": "Date to", "type": "string", "description": "Inclusive upper bound on the dataset's main date, in YYYY-MM-DD." }, "mineStatuses": { "title": "Mine statuses", "type": "array", "description": "Current mine status. Applies to the mines, addresses and controller history datasets directly, and to the rest through the mine master.", "items": { "type": "string", "enum": [ "Active", "Abandoned", "Abandoned and Sealed", "Intermittent", "Temporarily Idled", "NonProducing", "New Mine" ], "enumTitles": [ "Active", "Abandoned", "Abandoned and sealed", "Intermittent", "Temporarily idled", "Non-producing", "New mine" ] } }, "mineTypes": { "title": "Mine types", "type": "array", "description": "Underground, surface or facility.", "items": { "type": "string", "enum": [ "Underground", "Surface", "Facility" ], "enumTitles": [ "Underground", "Surface", "Facility" ] } }, "commodities": { "title": "Commodities", "type": "array", "description": "Primary canvass commodity from the mine master.", "items": { "type": "string", "enum": [ "Coal", "SandAndGravel", "Stone", "Metal", "Nonmetal" ], "enumTitles": [ "Coal", "Sand and gravel", "Stone", "Metal", "Nonmetal" ] } }, "subunits": { "title": "Subunits", "type": "array", "description": "Location or operation within the mine. Applies to accidents and to the four employment and production datasets.", "items": { "type": "string", "enum": [ "UNDERGROUND", "SURFACE AT UNDERGROUND", "STRIP, QUARY, OPEN PIT", "AUGER", "CULM BANK/REFUSE PILE", "DREDGE", "OTHER MINING", "INDEPENDENT SHOPS OR YARDS", "MILL OPERATION/PREPARATION PLANT", "OFFICE WORKERS AT MINE SITE" ], "enumTitles": [ "01 Underground", "02 Surface at underground", "03 Strip, quarry, open pit", "04 Auger", "05 Culm bank / refuse pile", "06 Dredge", "12 Other mining", "17 Independent shops or yards", "30 Mill operation / preparation plant", "99 Office workers at mine site" ] } }, "documentTypes": { "title": "Document types", "type": "array", "description": "Citation, order, safeguard or notice. Applies to the violations, assessed violations, contested violations and penalty docket datasets.", "items": { "type": "string", "enum": [ "Citation", "Order", "Safeguard", "Notice", "WrittenNo" ], "enumTitles": [ "Citation", "Order", "Safeguard", "Notice", "Written notice" ] } }, "significantAndSubstantial": { "title": "Significant and substantial", "enum": [ "any", "yes", "no" ], "type": "string", "description": "S&S designation on the citation or order.", "default": "any" }, "negligenceLevels": { "title": "Negligence", "type": "array", "description": "Inspector's negligence finding.", "items": { "type": "string", "enum": [ "NoNegligence", "LowNegligence", "ModNegligence", "HighNegligence", "Reckless" ], "enumTitles": [ "None", "Low", "Moderate", "High", "Reckless disregard" ] } }, "likelihoodLevels": { "title": "Likelihood of injury", "type": "array", "description": "Gravity likelihood recorded on the citation.", "items": { "type": "string", "enum": [ "NoLikelihood", "Unlikely", "Reasonably", "Highly", "Occurred" ], "enumTitles": [ "No likelihood", "Unlikely", "Reasonably likely", "Highly likely", "Occurred" ] } }, "injuryIllnessLevels": { "title": "Expected injury or illness", "type": "array", "description": "Gravity injury or illness that could reasonably be expected.", "items": { "type": "string", "enum": [ "NoLostDays", "LostDays", "Permanent", "Fatal" ], "enumTitles": [ "No lost days", "Lost workdays or restricted duty", "Permanently disabling", "Fatal" ] } }, "minPenaltyUsd": { "title": "Minimum proposed penalty (USD)", "minimum": 0, "type": "number", "description": "Keep only rows whose proposed penalty is at least this much. Decimals are allowed." }, "maxPenaltyUsd": { "title": "Maximum proposed penalty (USD)", "minimum": 0, "type": "number", "description": "Keep only rows whose proposed penalty is at most this much. Decimals are allowed." }, "degreesOfInjury": { "title": "Degree of injury", "type": "array", "description": "Degree of injury recorded on MSHA form 7000-1.", "items": { "type": "string", "enum": [ "DAYS AWAY FROM WORK ONLY", "NO DYS AWY FRM WRK,NO RSTR ACT", "DAYS RESTRICTED ACTIVITY ONLY", "ACCIDENT ONLY", "DYS AWY FRM WRK & RESTRCTD ACT", "OCCUPATNAL ILLNESS NOT DEG 1-6", "PERM TOT OR PERM PRTL DISABLTY", "ALL OTHER CASES (INCL 1ST AID)", "INJURIES DUE TO NATURAL CAUSES", "FATALITY", "INJURIES INVOLVNG NONEMPLOYEES", "NO VALUE FOUND" ], "enumTitles": [ "Days away from work only", "No days away, no restricted activity", "Days of restricted activity only", "Accident only, no injury", "Days away from work and restricted activity", "Occupational illness not degree 1-6", "Permanent total or partial disability", "All other cases including first aid", "Injuries due to natural causes", "Fatality", "Injuries involving non-employees", "No value found" ] } }, "accidentClassifications": { "title": "Accident classification", "type": "array", "description": "MSHA accident classification, the 29 values that appear in the file.", "items": { "type": "string", "enum": [ "HANDLING OF MATERIALS", "SLIP OR FALL OF PERSON", "HANDTOOLS (NONPOWERED)", "MACHINERY", "FALL OF ROOF OR BACK", "POWERED HAULAGE", "DISORDERS (REPEATED TRAUMA)", "HOISTING", "STEPPING OR KNEELING ON OBJECT", "STRIKING OR BUMPING", "FALL OF FACE/RIB/PILLAR/SIDE/HIGHWALL", "FIRE", "DUST DISEASE OF LUNGS", "ELECTRICAL", "IGNITION OR EXPLOSION OF GAS OR DUST", "EXPLODING VESSELS UNDER PRESSURE", "DISORDERS (PHYSICAL AGENTS)", "FALLING/SLIDING/ROLLING MATERIALS", "ENTRAPMENT", "ALL OTHER OCCUPATIONAL ILLNESSES", "NONPOWERED HAULAGE", "INUNDATION", "OCCUPATIONAL SKIN DISEASES", "EXPLOSIVES AND BREAKING AGENTS", "POISONING (TOXIC MATERIALS)", "RESPIRATORY CONDITIONS (TOXIC AGENTS)", "IMPOUNDMENT", "OTHER", "NO VALUE FOUND" ], "enumTitles": [ "Handling of materials", "Slip or fall of person", "Handtools (nonpowered)", "Machinery", "Fall of roof or back", "Powered haulage", "Disorders (repeated trauma)", "Hoisting", "Stepping or kneeling on object", "Striking or bumping", "Fall of face/rib/pillar/side/highwall", "Fire", "Dust disease of lungs", "Electrical", "Ignition or explosion of gas or dust", "Exploding vessels under pressure", "Disorders (physical agents)", "Falling/sliding/rolling materials", "Entrapment", "All other occupational illnesses", "Nonpowered haulage", "Inundation", "Occupational skin diseases", "Explosives and breaking agents", "Poisoning (toxic materials)", "Respiratory conditions (toxic agents)", "Impoundment", "Other", "No value found" ] } }, "fatalitiesOnly": { "title": "Fatalities only", "type": "boolean", "description": "Shortcut for degree of injury FATALITY. There are 1,210 fatal records in the file.", "default": false }, "activityContains": { "title": "Inspection activity contains", "type": "string", "description": "Case insensitive substring of the inspection activity, for example \"regular\" or \"103(i)\". The file uses 86 activity spellings, so a substring beats an exact list. Applies to the inspections dataset only." }, "sortBy": { "title": "Sort by", "enum": [ "fileOrder", "newestFirst", "oldestFirst", "highestPenalty", "lowestPenalty" ], "type": "string", "description": "File order streams and stops early, which is by far the fastest. Any other order has to read the whole file before it can answer, so it costs the full download of every selected dataset and is capped at 50,000 rows per dataset.", "default": "fileOrder" }, "includeMineDetails": { "title": "Add mine master details", "type": "boolean", "description": "Join the mine master onto every row that carries a mine ID, adding mine name, type, status, state, county, commodity, SIC, controller, operator, employee count and coordinates. Billed per row actually enriched. Skipped on the mines dataset, which already has these columns.", "default": false }, "includeOperatorContact": { "title": "Add operator contact address", "type": "boolean", "description": "Join the mine addresses of record, adding business name, contact title, street, PO box, city, state, ZIP and country. Billed per row actually enriched.", "default": false }, "includeProductionSummary": { "title": "Add latest production summary", "type": "boolean", "description": "Join the latest reported calendar year from the yearly employment file, summed across subunits: hours, coal production in short tons and average employees. Billed per row actually enriched.", "default": false }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "MSHA serves these files without any bot protection, so no proxy is needed. Turn one on only if your own network cannot reach arlweb.msha.gov.", "default": { "useApifyProxy": 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 } } } } } } } } } }