{ "openapi": "3.0.1", "info": { "title": "Extract ZIP Files: Unzip Archives & Email Attachments", "description": "Extract every file inside ZIP, 7z, TAR/GZ archives, emails (.eml/.msg attachments), PDFs (attachments and images) and Office files (embedded media). Each file gets a direct download URL plus name, path, size, MIME type and SHA-256. Zip-bomb and path-traversal safe.", "version": "0.1", "x-build-id": "HxLoSgINDZPegj9w9" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/data-done-right~extract-zip-files/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-data-done-right-extract-zip-files", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/data-done-right~extract-zip-files/runs": { "post": { "operationId": "runs-sync-data-done-right-extract-zip-files", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/data-done-right~extract-zip-files/run-sync": { "post": { "operationId": "run-sync-data-done-right-extract-zip-files", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "urls" ], "properties": { "urls": { "title": "File URLs", "type": "array", "description": "Links to archives (zip, 7z, tar, tar.gz/tgz, tar.bz2, tar.xz, gz), emails (.eml, .msg), PDFs, or Office files (docx, xlsx, pptx, odt). Everything inside is extracted.", "items": { "type": "string" } }, "includeExtensions": { "title": "Only these extensions", "type": "array", "description": "Deliver only files with these extensions, e.g. pdf, jpg, png, csv. Empty = everything. Nested archives are still opened.", "items": { "type": "string" } }, "excludeExtensions": { "title": "Skip these extensions", "type": "array", "description": "Never deliver files with these extensions, e.g. exe, dll, js.", "items": { "type": "string" } }, "maxFiles": { "title": "Max files (whole run)", "minimum": 1, "type": "integer", "description": "Stop after this many extracted files. Also caps the cost (you pay per extracted file).", "default": 1000 }, "maxTotalSizeMb": { "title": "Max total extracted size (MB, whole run)", "minimum": 1, "type": "integer", "description": "Files that would push the run past this many extracted megabytes are skipped.", "default": 1024 }, "nestedDepth": { "title": "Nested archive depth", "minimum": 0, "maximum": 3, "type": "integer", "description": "How many levels of archives/emails inside the source to open (a zip inside a zip, an email attached to an email). 0 = deliver inner archives as files.", "default": 1 }, "keepNestedArchives": { "title": "Also deliver opened inner archives", "type": "boolean", "description": "When an inner archive/email is opened, also deliver the archive file itself.", "default": false }, "flattenPaths": { "title": "Unique flat file names", "type": "boolean", "description": "Make every fileName unique across the run (report.pdf, report (2).pdf), so all files can be saved into one folder. 'path' becomes the flat name too; the original folder path stays in 'originalPath'.", "default": false }, "skipDuplicates": { "title": "Skip duplicate files", "type": "boolean", "description": "Skip files whose content (SHA-256) was already delivered in this run, e.g. the same logo in every email.", "default": false }, "skipJunkFiles": { "title": "Skip junk files", "type": "boolean", "description": "Skip __MACOSX folders, ._ resource forks, .DS_Store, Thumbs.db and desktop.ini.", "default": true }, "emailInlineImages": { "title": "Email: include inline images", "type": "boolean", "description": "Deliver inline images (signature logos, embedded pictures). Turn off to get only real attachments.", "default": true }, "emailMetadataRows": { "title": "Email: output headers and body", "type": "boolean", "description": "Add one row per email with from, to, cc, date, subject and the text/HTML body (free, not charged).", "default": true }, "pdfAttachments": { "title": "PDF: embedded file attachments", "type": "boolean", "description": "Extract files attached to PDFs (e.g. ZUGFeRD/Factur-X invoice XML, portfolios).", "default": true }, "pdfImages": { "title": "PDF: embedded images", "type": "boolean", "description": "Extract images embedded in PDF pages (saved as PNG/JPG; identical images are extracted once).", "default": true }, "pdfMinImageSize": { "title": "PDF: minimum image size (px)", "minimum": 0, "type": "integer", "description": "Skip PDF images narrower or shorter than this (removes tiny icons, lines and masks).", "default": 32 }, "officeEmbeddedFiles": { "title": "Office: include embedded files", "type": "boolean", "description": "Besides media (images, video), also deliver embedded objects from docx/xlsx/pptx (e.g. an Excel sheet inside a Word file).", "default": true }, "maxFileSizeMb": { "title": "Max size per extracted file (MB)", "minimum": 1, "type": "integer", "description": "Larger inner files are skipped (listed in the summary).", "default": 200 }, "maxDownloadSizeMb": { "title": "Max source download size (MB)", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Source files larger than this are not downloaded.", "default": 200 }, "maxCompressionRatio": { "title": "Zip-bomb guard: max compression ratio", "minimum": 10, "type": "integer", "description": "Entries or archives that expand more than this many times their compressed size are refused (only checked above 1 MB uncompressed). Normal files compress 2-20x; zip bombs 1000x+.", "default": 200 }, "maxEntriesPerSource": { "title": "Zip-bomb guard: max entries per source", "minimum": 1, "type": "integer", "description": "Stop reading a source after this many entries (all nesting levels).", "default": 10000 }, "timeoutSecondsPerSource": { "title": "Timeout per source (seconds)", "minimum": 10, "type": "integer", "description": "Stop extracting a source after this long; files found so far are kept.", "default": 300 }, "keyValueStoreName": { "title": "Save files to named key-value store", "type": "string", "description": "Optional. Save extracted files into this named store (kept until you delete it) instead of the run's default store (deleted after your plan's data retention period)." }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Only needed if the file host blocks datacenter IPs.", "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 }, "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 } } } } } } } } } }