{ "openapi": "3.0.1", "info": { "title": "7-Zip Recursive Archive Extractor: Enterprise-Grade Automation", "description": "High-performance 7-Zip extractor supporting 30+ formats (ZIP, RAR, 7Z, TAR, ISO, GZIP, BZIP2, XZ, CAB & more). Features recursive nested archive extraction, CRC-based incremental updates to skip unchanged files, security filtering, and dual KV Store + Dataset output. Saves up to 90% compute costs.", "version": "1.1", "x-build-id": "DPDUIJLfLlqrTRahQ" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/roach-sama~universal-archive-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-roach-sama-universal-archive-extractor", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/roach-sama~universal-archive-extractor/runs": { "post": { "operationId": "runs-sync-roach-sama-universal-archive-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/roach-sama~universal-archive-extractor/run-sync": { "post": { "operationId": "run-sync-roach-sama-universal-archive-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "url": { "title": "Single archive URL", "type": "string", "description": "Direct URL to one archive file. Use this OR \"Multiple URLs\" OR \"Dataset source\" (choose exactly one input method)." }, "urls": { "title": "Multiple archive URLs", "minItems": 1, "type": "array", "description": "List of archive URLs to process in parallel. Use this OR \"Single URL\" OR \"Dataset source\" (choose exactly one input method).", "items": { "type": "string" }, "default": [ "https://github.com/RoachxD/ScheduleOne.BunnyHopper/archive/refs/heads/main.zip", "https://github.com/RoachxD/ScheduleOne.HonestMainMenu/archive/refs/heads/main.zip" ] }, "datasetId": { "title": "Source dataset", "type": "string", "description": "Apify Dataset ID containing archive URLs (e.g., output from a crawler). Combine with \"URL field name\" below. Use this OR \"Single URL\" OR \"Multiple URLs\"." }, "urlField": { "title": "URL field name in dataset", "type": "string", "description": "Field name in dataset items containing archive URL(s). Accepts both single strings and arrays of URLs for batch processing." }, "outputMode": { "title": "Output destination strategy", "enum": [ "kv_store", "dataset", "both" ], "type": "string", "description": "Control where results go: KV Store = raw extracted files for download; Dataset = searchable per-file metadata index. \"Both\" provides maximum flexibility.", "default": "both" }, "outputOptions": { "title": "Custom output destinations", "required": [], "type": "object", "description": "Override default storage names to organize multiple extraction runs or integrate with existing workflows.", "properties": { "storeName": { "title": "Custom KV store name", "type": "string", "editor": "textfield", "description": "Named KV store for extracted files and summary. Leave empty to use the run's default store." }, "datasetName": { "title": "Custom dataset name", "type": "string", "editor": "textfield", "description": "Named dataset for the file index. Leave empty to use the run's default dataset." }, "summaryKey": { "title": "Summary record key", "type": "string", "editor": "textfield", "default": "SUMMARY", "description": "KV store key for the final run statistics (total files, errors, extensions, etc.)." }, "flattenPaths": { "title": "Flatten file paths in KV", "type": "boolean", "editor": "checkbox", "default": false, "description": "Convert nested paths to flat keys (e.g., \"report.pdf-a1b2c3d4\") to avoid deep folder structures and potential key collisions." } }, "additionalProperties": false }, "concurrency": { "title": "Parallel archive processing", "minimum": 1, "maximum": 50, "type": "integer", "description": "Number of archives to download and extract simultaneously. Higher values = faster completion but more memory usage. Reduce if hitting rate limits.", "default": 10 }, "httpOptions": { "title": "Download & network settings", "required": [], "type": "object", "description": "Fine-tune HTTP behavior: timeouts, retries, authentication headers, and proxy routing for archive downloads.", "properties": { "timeoutMillis": { "title": "Request timeout (milliseconds)", "type": "integer", "editor": "number", "minimum": 1000, "default": 120000, "description": "Maximum wait time for each HTTP request. Increase for slow servers or large files; decrease to fail fast on unresponsive sources." }, "maxRetries": { "title": "Maximum retry attempts", "type": "integer", "editor": "number", "minimum": 0, "default": 3, "description": "Number of automatic retries for failed downloads. Helps overcome transient network issues." }, "maxRedirects": { "title": "Maximum HTTP redirects", "type": "integer", "editor": "number", "minimum": 0, "default": 5, "description": "How many redirect hops to follow before aborting. Protects against redirect loops." }, "skipHeadPrecheck": { "title": "Skip HEAD pre-check", "type": "boolean", "editor": "checkbox", "default": false, "description": "Bypass preliminary HEAD request for file size. Enable if servers block HEAD methods; streaming guard still enforces size limits." }, "headers": { "title": "Custom HTTP headers", "type": "array", "editor": "keyValue", "description": "Add authentication tokens, API keys, or custom User-Agent strings. Example: Authorization: Bearer YOUR_TOKEN", "placeholderKey": "Header name", "placeholderValue": "Header value", "default": [], "items": { "type": "object", "properties": { "key": { "type": "string", "title": "Header name", "description": "HTTP header name (e.g., Authorization, User-Agent)" }, "value": { "type": "string", "title": "Header value", "description": "Header value, such as token or custom user agent string" } }, "required": [ "key", "value" ], "additionalProperties": false } }, "useApifyProxy": { "title": "Enable Apify Proxy", "type": "boolean", "editor": "checkbox", "default": false, "description": "Route downloads through Apify's residential/datacenter proxy network. Requires appropriate plan subscription." }, "proxyUrl": { "title": "Custom proxy URL", "type": "string", "editor": "textfield", "description": "Alternative proxy endpoint (ignored if Apify Proxy is enabled). Format: http://user:pass@proxy.example.com:8080" }, "apifyProxyGroups": { "title": "Apify Proxy groups", "type": "array", "editor": "stringList", "description": "Target specific proxy groups when using Apify Proxy (e.g., RESIDENTIAL, GOOGLE_SERP).", "items": { "type": "string" } }, "apifyProxyCountry": { "title": "Apify Proxy country", "type": "string", "editor": "textfield", "description": "Two-letter country code for geo-targeted proxy exit nodes (e.g., US, GB, DE)." } }, "additionalProperties": false }, "limits": { "title": "Size & volume safeguards", "required": [], "type": "object", "description": "Prevent runaway processing by capping download sizes, file counts, and individual file sizes. Protects compute credits and memory.", "properties": { "maxDownloadBytes": { "title": "Max archive download size (bytes)", "type": "integer", "editor": "number", "minimum": 1, "default": 524288000, "description": "Hard cap on archive file size (default: 500 MB). Archives exceeding this limit are rejected before extraction. Set higher for large datasets." }, "maxFiles": { "title": "Max files per archive", "type": "integer", "editor": "number", "minimum": 0, "default": 1000, "description": "Stop processing after this many files per archive (including nested archives). 0 = unlimited. Prevents infinite-loop archives." }, "maxFilesOverflowMode": { "title": "Behavior after max files reached", "type": "string", "editor": "select", "enum": [ "summary_only", "dataset_rows" ], "enumTitles": [ "Summary only (no dataset rows after cap)", "Dataset rows for all skipped files" ], "default": "summary_only", "description": "When more files exist than maxFiles, keep counting in SUMMARY. By default dataset rows are not written for overflow; switch to dataset_rows to keep per-file skip records." }, "maxFileSizeBytes": { "title": "Max individual file size (bytes)", "type": "integer", "editor": "number", "minimum": 0, "default": 524288000, "description": "Skip files larger than this limit (default: 500 MB). 0 = no per-file limit. Useful for filtering out large media files." } }, "additionalProperties": false }, "filters": { "title": "Security & data selection (filters)", "required": [], "type": "object", "description": "Control which files are extracted using extension allowlists/blocklists and path pattern exclusions. Blocks executables by default for security.", "properties": { "allowedExtensions": { "title": "Allowed extensions (allowlist)", "type": "array", "editor": "stringList", "description": "If set, ONLY these extensions will be extracted (e.g., .pdf, .csv, .json). Leave empty to allow all except blocked types.", "items": { "type": "string" } }, "blockedExtensions": { "title": "Blocked extensions (security)", "type": "array", "editor": "stringList", "description": "Never extract these file types. Default blocks executables and scripts to prevent malware execution.", "default": [ ".exe", ".dll", ".bat", ".cmd", ".sh", ".ps1", ".msi" ], "items": { "type": "string" } }, "excludedPatterns": { "title": "Excluded path patterns", "type": "array", "editor": "stringList", "description": "Skip files whose paths contain these substrings. Default removes macOS metadata folders and system files.", "default": [ "__MACOSX/", ".DS_Store" ], "items": { "type": "string" } } }, "additionalProperties": false }, "formats": { "title": "Archive types & nested extraction", "required": [], "type": "object", "description": "Specify which archive formats to accept and how deep to recurse into nested archives. Supports ZIP, RAR, 7Z, TAR, ISO, CAB, and 30+ more formats.", "properties": { "archiveTypes": { "title": "Allowed archive formats", "type": "array", "editor": "stringList", "description": "\"auto\" accepts any 7-Zip-supported format (30+ types). Or specify exact formats: zip, rar, 7z, tar, gz, bz2, xz, iso, cab, arc, zipx, etc.", "default": [ "auto" ], "items": { "type": "string" } }, "extractNestedArchives": { "title": "Enable recursive extraction", "type": "boolean", "editor": "checkbox", "default": true, "description": "Automatically detect and extract archives found inside archives. Example: process data.zip containing backup.tar.gz containing files.7z." }, "nestedArchiveDepth": { "title": "Maximum nesting depth", "type": "integer", "editor": "number", "default": 2, "description": "How many archive layers to recurse (0=top-level only, 1=one layer deep, 2=two layers, etc.). Prevents infinite recursion attacks." }, "nestedBeyondDepthBehavior": { "title": "Behavior for too-deep nesting", "type": "string", "editor": "select", "enum": [ "skip", "extract_as_file" ], "enumTitles": [ "Skip entirely (mark as SKIPPED_NESTED_TOO_DEEP)", "Extract as regular file (don't recurse)" ], "default": "skip", "description": "When an archive is found beyond the max depth: either skip it completely or treat it as a normal file without recursion." }, "followSymlinks": { "title": "Follow symlinks when target exists", "type": "boolean", "editor": "checkbox", "default": false, "description": "When enabled, symbolic links inside the archive are resolved if their target exists within the extracted temp directory; otherwise they are recorded as metadata-only (status SYMLINK)." }, "listTimeoutMillis": { "title": "7-Zip listing timeout (ms)", "type": "integer", "editor": "number", "default": 0, "description": "Abort 7-Zip directory listing after this many milliseconds. 0 = no timeout. Use for archives that hang during inspection." } }, "additionalProperties": false }, "incremental": { "title": "Incremental extraction (compute saver)", "required": [], "type": "object", "description": "Skip unchanged files between runs using CRC+size signatures. Saves compute credits and bandwidth by only processing new or modified files.", "properties": { "enabled": { "title": "Enable incremental extraction", "type": "boolean", "editor": "checkbox", "default": true, "description": "Track file signatures per archive URL. On subsequent runs, unchanged files are automatically skipped. Reduces compute costs by up to 90% for repeat processing." }, "indexKeyPrefix": { "title": "Index storage key prefix", "type": "string", "editor": "textfield", "default": "INCR--", "description": "KV store key prefix for incremental state records. Only use letters, numbers, and !-_.'() to keep keys KV-safe." }, "strategy": { "title": "Change detection method", "type": "string", "editor": "select", "enum": [ "crc+size", "sizeOnly" ], "enumTitles": [ "CRC32 + File Size (recommended, accurate)", "File Size Only (faster, less precise)" ], "default": "crc+size", "description": "CRC+size detects content changes even when file size stays the same. Size-only is faster but can miss modifications." }, "onlyNewOrChanged": { "title": "Extract only new/changed files", "type": "boolean", "editor": "checkbox", "default": true, "description": "Skip extraction for unchanged files (they still appear in the dataset index with SKIPPED_UNCHANGED status). Disable to always re-extract everything." } }, "additionalProperties": false }, "errorHandling": { "title": "Failure tolerance & recovery", "required": [], "type": "object", "description": "Choose between strict fail-fast behavior or lenient continue-on-error mode. Strict mode aborts immediately on any failure; lenient mode logs errors and continues.", "properties": { "mode": { "title": "Error handling strategy", "type": "string", "editor": "select", "enum": [ "lenient", "strict" ], "enumTitles": [ "Lenient (log errors, continue processing)", "Strict (abort run on first error)" ], "default": "lenient", "description": "Lenient mode processes all archives even when some fail. Strict mode aborts immediately on the first download or extraction error, ensuring no partial results." }, "maxPerArchiveErrors": { "title": "Max file errors per archive", "type": "integer", "editor": "number", "default": 20, "description": "In lenient mode, treat an archive as failed after this many file-level errors. Prevents endless processing of corrupted archives." } }, "additionalProperties": false }, "webhook": { "title": "Completion webhook notification", "required": [], "type": "object", "description": "POST a signed JSON payload with run statistics to your endpoint when extraction completes. Useful for pipeline automation and monitoring.", "properties": { "url": { "title": "Webhook endpoint URL", "type": "string", "editor": "textfield", "description": "POST target for the final run summary. Payload includes timestamps, file counts, errors, and per-archive breakdowns." }, "secret": { "title": "HMAC signing secret", "type": "string", "editor": "textfield", "description": "Optional secret for HMAC-SHA256 payload signing. Signature appears in x-universal-archive-signature header for verification." } }, "additionalProperties": false }, "textOptions": { "title": "Text encoding normalization", "required": [], "type": "object", "description": "Best-effort UTF-8 verification for text-like files. Attempts to decode as UTF-8 and store normalized bytes; falls back to original bytes if decoding fails.", "properties": { "convertTextToUtf8": { "title": "Normalize text to UTF-8", "type": "boolean", "editor": "checkbox", "default": false, "description": "Attempt to decode text files as UTF-8 and re-store them in UTF-8 form. If decoding fails, the original bytes are kept." }, "textExtensions": { "title": "Text file extensions", "type": "array", "editor": "stringList", "description": "Extensions to treat as text for normalization (e.g., .txt, .csv, .json, .xml, .html, .md, .log, .ini, .yaml). Empty = use built-in defaults.", "items": { "type": "string" } } }, "additionalProperties": false }, "debug": { "title": "Enable debug logging", "type": "boolean", "description": "Switch to DEBUG log level for detailed diagnostics: HTTP traffic, archive contents, 7-Zip output, and full summary object. Use for troubleshooting.", "default": 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 } } } } } } } } } }