{ "openapi": "3.0.1", "info": { "title": "Pastebin Scraper", "description": "Collect public Pastebin, GitHub Gist, Ideone and Paste.org data. Search keywords, extract regex matches and full text, build URL indexes, and resume interrupted collections. No paid data APIs.", "version": "0.10", "x-build-id": "T88ScOVpCvubyrEW6" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/thescrapelab~pastebin-osint-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-thescrapelab-pastebin-osint-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/thescrapelab~pastebin-osint-scraper/runs": { "post": { "operationId": "runs-sync-thescrapelab-pastebin-osint-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/thescrapelab~pastebin-osint-scraper/run-sync": { "post": { "operationId": "run-sync-thescrapelab-pastebin-osint-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "sources": { "title": "Paste sites", "minItems": 1, "maxItems": 5, "uniqueItems": true, "type": "array", "description": "Public sites to discover. Failed sites are reported separately. Textbin is experimental and may be unavailable. Omit this field in API calls to retain Pastebin-only discovery.", "items": { "type": "string", "enum": [ "pastebin", "github_gist", "ideone", "pasteorg", "textbin" ], "enumTitles": [ "Pastebin", "GitHub Gist", "Ideone", "Paste.org", "Textbin (experimental)" ] }, "default": [ "pastebin" ] }, "startUrls": { "title": "Direct paste URLs", "maxItems": 500, "type": "array", "description": "Optional public paste or Gist URLs from supported sites. Direct URLs infer their site, merge with legacy pasteUrls, and skip discovery. One Gist produces one record even when it contains multiple files.", "items": { "type": "object", "properties": { "url": { "type": "string", "title": "Paste URL", "description": "Public page or raw URL on a supported paste site." } }, "required": [ "url" ] }, "default": [] }, "runMode": { "title": "Run mode", "enum": [ "scrape", "url_index" ], "type": "string", "description": "URL index mode collects live public paste URLs without downloading contents. Scrape mode fetches paste contents for keyword filtering and regex extraction.", "default": "scrape" }, "maxPastesPerRun": { "title": "Maximum archive entries to inspect", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Upper limit for Pastebin archive and optional search-engine entries inspected before filters and result limits are applied. The actor can inspect up to 5,000 entries per run across the selected discovery sources, but public sources may expose fewer entries.", "default": 10 }, "maxResults": { "title": "Maximum dataset items to save", "minimum": 1, "maximum": 500, "type": "integer", "description": "Upper limit for matching paste records saved in scrape mode. URL index mode uses urlIndexMaxRecordsPerRun instead.", "default": 3 }, "urlIndexMaxRecordsPerRun": { "title": "URL records per index run", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Maximum new paste_url records to save in URL index mode. Use this with Apify Schedules to build a cumulative low-storage URL history over time.", "default": 10 }, "urlIndexDatasetName": { "title": "URL index dataset name", "type": "string", "description": "Named Apify dataset where URL index mode appends cumulative paste_url records across scheduled runs.", "default": "pastebin-url-index" }, "urlIndexStateStoreName": { "title": "URL index state store name", "type": "string", "description": "Named key-value store used to remember recently indexed paste IDs and avoid saving duplicate URL records across scheduled runs.", "default": "pastebin-url-index-state" }, "urlIndexDeduplicate": { "title": "Skip already indexed URLs", "type": "boolean", "description": "Skip IDs already saved in your named URL index. The prefilled preview disables this so repeated previews return current live URLs. Enable it for cumulative indexing.", "default": true }, "urlIndexRecentIdLimit": { "title": "Remember recent URL IDs", "minimum": 1, "maximum": 1000000, "type": "integer", "description": "Number of recent paste IDs retained for cross-run URL deduplication. Increase this for longer-running cumulative indexes.", "default": 10 }, "urlIndexSaveToDefaultDataset": { "title": "Also save URL records to run dataset", "type": "boolean", "description": "When enabled, URL index mode writes each new paste_url record to both the cumulative named dataset and the current run's default dataset for easier run-by-run inspection.", "default": true }, "useUrlIndex": { "title": "Search collected URL index", "type": "boolean", "description": "In normal scrape mode, search previously collected paste_url records from the named URL index dataset only after the live archive search finds no keyword matches. This lets client runs go further back while avoiding extra raw paste fetches when live data already matched.", "default": true }, "maxUrlIndexEntriesToSearch": { "title": "Indexed URLs to search", "minimum": 0, "maximum": 5000, "type": "integer", "description": "Maximum recently collected URL index records to search as a fallback after live keyword search finds no matches. Higher values go further back, but increase raw paste fetches and runtime.", "default": 100 }, "fetchDetailMetadata": { "title": "Fetch author and date", "type": "boolean", "description": "When enabled, the actor makes one extra Pastebin page request for each saved item to enrich it with author and publication timestamp. Leave this off for the cheapest high-volume runs.", "default": false }, "keywords": { "title": "Keywords", "maxItems": 100, "type": "array", "description": "Optional words or phrases to search for in discovered public paste text. If you enter keywords, the actor saves only pastes that contain at least one of them. Up to 100 keywords are accepted.", "items": { "type": "string", "maxLength": 256 }, "default": [] }, "discoveryMode": { "title": "Discovery depth", "enum": [ "recent", "expanded", "deep" ], "type": "string", "description": "How far to look for public paste IDs before keyword filtering. Recent checks only the rolling public archive. Expanded adds common syntax archives when you request more than the main archive usually exposes. Deep fetches Pastebin's public language archive list and scans up to the configured syntax archive limit. Deep is broader and slower, but it is still not a complete historical Pastebin search.", "default": "recent" }, "syntaxArchives": { "title": "Syntax archives", "maxItems": 25, "type": "array", "description": "Optional Pastebin syntax archives to include in discovery. These pages can expose additional and sometimes older public paste IDs than the main rolling archive. Choose suggested values or type another Pastebin syntax slug.", "items": { "type": "string", "enumSuggestedValues": [ "bash", "python", "javascript", "json", "xml", "sql", "yaml", "php", "java", "cpp", "c", "csharp", "go", "rust", "powershell", "text" ], "enumTitles": [ "Bash", "Python", "JavaScript", "JSON", "XML", "SQL", "YAML", "PHP", "Java", "C++", "C", "C#", "Go", "Rust", "PowerShell", "Text" ] }, "default": [] }, "maxSyntaxArchivesToScan": { "title": "Maximum syntax archives to scan", "minimum": 1, "maximum": 266, "type": "integer", "description": "Only used for deep discovery. Pastebin currently exposes hundreds of language archive pages, so this cap controls how many of those pages are fetched before paste IDs are deduplicated and selected for processing.", "default": 5 }, "autoExpandSyntaxArchives": { "title": "Automatically search more archive pages", "type": "boolean", "description": "Backwards-compatible switch for automatic archive expansion. Leave enabled for expanded and deep discovery. Turn it off only when you want the actor to inspect the main rolling archive unless syntaxArchives are provided manually.", "default": false }, "saveNoMatchSummary": { "title": "Save a no-match summary result", "type": "boolean", "description": "Save a SEARCH_SUMMARY key-value record when a keyword search finds no matching paste. Diagnostics are not written as paid paste results.", "default": true }, "searchEngineDiscovery": { "title": "Add search-engine discovery", "type": "boolean", "description": "Optional best-effort fallback that searches externally indexed Pastebin URLs for each keyword and adds discovered paste IDs to the run. This can find older public pastes, but search engines may throttle, omit, or change results.", "default": false }, "maxSearchResultsPerKeyword": { "title": "Search results per keyword", "minimum": 1, "maximum": 50, "type": "integer", "description": "Maximum externally indexed Pastebin URLs to add per keyword when searchEngineDiscovery is enabled.", "default": 5 }, "noMatchStopAfterPastes": { "title": "Stop if no matches after", "minimum": 0, "maximum": 5000, "type": "integer", "description": "Cost guard for keyword searches. If zero matching paste records have been saved after this many processed pastes, the actor stops early and writes a summary. Set to 0 to disable and scan the full maxPastesPerRun budget.", "default": 10 }, "stopAfterPastesWithoutNewMatch": { "title": "Stop after no new matches", "minimum": 0, "maximum": 5000, "type": "integer", "description": "Cost guard for sparse keyword searches. After the first matching paste is saved, the actor stops if this many additional processed pastes do not produce another saved match. Set to 0 to disable and scan the full maxPastesPerRun budget.", "default": 10 }, "regexPatterns": { "title": "Regex patterns", "maxItems": 25, "type": "array", "description": "Optional Python-compatible regex patterns used to extract emails, keys, URLs, or other structured matches from saved pastes. Up to 25 patterns are accepted.", "items": { "type": "string", "maxLength": 1000 }, "default": [] }, "pasteUrls": { "title": "Paste URLs (optional)", "maxItems": 500, "type": "array", "description": "Fetch specific Pastebin page or raw URLs instead of discovering archive URLs. Duplicate IDs are collapsed. Keywords and regex extraction still apply in scrape mode. Up to 500 URLs; private, removed or password-protected pastes cannot be fetched.", "items": { "type": "string" }, "default": [] }, "includeRawText": { "title": "Include full paste text", "type": "boolean", "description": "Include complete text in raw_text, up to the per-paste size cap. Off returns a 240-character preview plus length and extracted matches, reducing output size.", "default": false }, "keywordCaseSensitive": { "title": "Case-sensitive keywords", "type": "boolean", "description": "Require exact letter case when matching keywords. Off matches keywords without regard to letter case. Regex flags are controlled within each pattern.", "default": false }, "resumeFromRunId": { "title": "Continue a previous run", "type": "string", "description": "Optional terminal run ID of this Actor. Continue its pending work with the same sources, keywords and extraction settings. New results go to this run dataset; earlier results are not billed again. Per-run time, request and result limits may change." }, "maxRunTimeSecs": { "title": "Maximum collection time", "minimum": 30, "maximum": 1800, "type": "integer", "description": "Wall-clock collection budget in seconds; also stops before the platform timeout to persist pending work.", "default": 240 }, "maxRequestsPerRun": { "title": "Maximum web requests", "minimum": 1, "maximum": 20000, "type": "integer", "description": "Total public web HTTP attempts, including retries and redirects. Storage operations are not source requests.", "default": 200 }, "maxDiscoveryTimeSecs": { "title": "Discovery time budget", "minimum": 5, "maximum": 120, "type": "integer", "description": "Maximum wall-clock discovery time. Available documents can be processed while other sources are still discovering.", "default": 45 }, "maxDiscoveryRequests": { "title": "Discovery request budget", "minimum": 1, "maximum": 500, "type": "integer", "description": "Maximum HTTP attempts used for discovery across all sites, within the overall web-request budget.", "default": 20 }, "maxPagesPerSource": { "title": "Listing pages per source", "minimum": 1, "maximum": 100, "type": "integer", "description": "Maximum pagination depth for each public listing or HTML search. Pastebin syntax archives retain their own explicit cap.", "default": 3 }, "maxFilesPerGist": { "title": "Files per Gist", "minimum": 1, "maximum": 100, "type": "integer", "description": "Maximum raw files fetched per Gist. Additional or failed files are reported as incomplete coverage, never as a complete negative search.", "default": 20 } } }, "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 } } } } } } } } } }