{ "openapi": "3.0.1", "info": { "title": "Anghami Scraper - Songs, Albums, Artists & Playlists", "description": "Scrape Anghami's public catalog by keyword or player URL. Rows carry their kind (song, album, artist, playlist, tag) with title, artist, plays, followers, podcast flags and artwork. Detail views add the description and a podcast episode list, one per-record toggle.", "version": "0.1", "x-build-id": "nJy6lsY3D8umckDGC" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/abotapi~anghami-catalog-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-abotapi-anghami-catalog-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/abotapi~anghami-catalog-scraper/runs": { "post": { "operationId": "runs-sync-abotapi-anghami-catalog-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/abotapi~anghami-catalog-scraper/run-sync": { "post": { "operationId": "run-sync-abotapi-anghami-catalog-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "mode" ], "properties": { "mode": { "title": "Mode", "enum": [ "search", "url" ], "type": "string", "description": "How to start the scrape. 'search' runs catalog searches. 'url' processes the player URLs you paste: each URL's own kind decides the scope, paginated kinds walk forward, and a pasted song or album URL is the one exception and returns that single object in full. The kind filter below applies to the rows this run reads in both modes.", "default": "search" }, "searchTerms": { "title": "Search terms", "type": "array", "description": "One or more things to search Anghami's catalog for, for example 'Sherine', 'Amr Diab', a podcast name or an audiobook title. Each term is scraped independently. Search mode only: in URL mode the scope is read out of each pasted URL instead.", "default": [ "Sherine" ], "items": { "type": "string" } }, "urls": { "title": "Anghami URLs", "type": "array", "description": "Paste player URLs: artist pages (https://play.anghami.com/artist/000000, the /artist// form works too), song pages, album pages, playlist pages (https://play.anghami.com/playlist/-), and category tag pages (https://play.anghami.com/tag/, the curated collections behind genre and chart tags). A pasted URL decides its own scope. Add &page=3 to start a paginated walk further in; songs and albums are single detail objects and ignore paging.", "items": { "type": "string" } }, "kinds": { "title": "Kinds to keep", "type": "array", "description": "Only keep records of these kinds (song, album, artist, playlist, tag), one per line. Leave empty for all kinds. Applied to the rows this run reads, in BOTH search mode and URL mode. A pasted song or album URL is the one exception: the object you pasted is returned in full regardless of this filter.", "items": { "type": "string" } }, "excludePodcasts": { "title": "Exclude podcasts", "type": "boolean", "description": "Off by default. On: rows flagged as podcast episodes are dropped from the results, in BOTH search mode and URL mode. Podcast episodes arrive both as song rows carrying the podcast flag and as the podcast object itself (an album-kind row with its own podcast flag); this filter drops both. A pasted song or album URL is the one exception: the object you pasted is returned in full regardless of this filter.", "default": false }, "fetchDetails": { "title": "Fetch record details", "type": "boolean", "description": "Fetch each song's or album's own detail view: the store page title and description, the curator of a playlist-style album object, and for an album object the full song/episode id list (a podcast object's episodes). Slower, and charged once per record. One exception: a pasted song or album URL in URL mode is NOT charged this fee, since its object's own page was read because you pasted it. Leave off for a fast crawl: the listing fields are included either way.", "default": false }, "maxItems": { "title": "Max items", "minimum": 0, "type": "integer", "description": "The single cap on this run: stop after collecting this many records across all search terms and URLs. Set 0 for unlimited.", "default": 20 }, "maxPages": { "title": "Max pages per source", "minimum": 0, "type": "integer", "description": "Safety bound on how many result pages to walk per search term or URL. Leave empty (0) for no page limit: the run then stops at Max items, not here. Does not impose a separate cap below Max items.", "default": 0 }, "resumeFromRunId": { "title": "Resume from a previous run", "type": "string", "description": "Paste a previous run ID or dataset ID to continue a large crawl without returning or charging for records already collected there. Use this after an interrupted or capped run. For recurring monitoring of the same search, use Incremental mode below instead." }, "incrementalMode": { "title": "Incremental changes for scheduled runs", "type": "boolean", "description": "Turn this on for daily or weekly recurring monitoring of the same search, for example a new-release watch. The first run returns everything matching as NEW. Later runs normally return only NEW, UPDATED and REAPPEARED records. Play counts, likes and follower moves ARE reported as UPDATED: on a live streaming catalog they are the signal, not noise. Turn on Emit unchanged or Emit expired only when you also want those rows returned (and billed). State is kept separately per search, URL and filter setup; use State key to name or deliberately share a monitoring campaign. To continue one specific interrupted run instead, use Resume from a previous run above.", "default": false }, "stateKey": { "title": "State key (optional, incremental mode only)", "type": "string", "description": "Optional. Name this monitoring campaign to keep its state stable, or to deliberately share state across differently configured runs. Leave empty to let the actor derive a key automatically from the search terms, URLs and filters, so two different searches never mix state." }, "emitUnchanged": { "title": "Emit unchanged records (incremental mode only)", "type": "boolean", "description": "Off by default. Turn on to also return records that have not changed since the last run, marked UNCHANGED. This returns, and bills, extra rows you already have, so leave it off unless you specifically want a full snapshot every run.", "default": false }, "emitExpired": { "title": "Emit expired records (incremental mode only)", "type": "boolean", "description": "Off by default. Turn on to also return records that were present in a previous run but are no longer found, marked EXPIRED. Only produced once a run has fully scanned the tracked search: not when Max items capped it, not when Resume was used, and not when the run was refused. This returns, and bills, extra synthetic rows, so leave it off unless you need expiry tracking.", "default": false }, "mcpConnectors": { "title": "Pipe results into your apps (optional)", "type": "array", "description": "Optionally send results into the apps you already use, via Model Context Protocol (MCP) connectors. Authorize one under Apify, Settings, API & Integrations, then select it here. Notion gets a page per record; other connectors get a best-effort write or digest. Each connector receives a condensed summary per record, not the full record; the complete record always stays in the dataset. Leave empty to skip; this never changes the dataset output. Supported: Notion (https://mcp.notion.com/mcp), Linear (https://mcp.linear.app/sse), Airtable (https://mcp.airtable.com/mcp), Apify (https://mcp.apify.com)." }, "notionParentPageUrl": { "title": "Notion parent page (Notion connector only)", "type": "string", "description": "URL or id of the Notion page under which record pages are created. Required to enable the Notion export; ignored by other connectors." }, "maxNotifyListings": { "title": "Max items to export per connector", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Cap on records written to each connector per run. Does not affect the dataset.", "default": 50 }, "proxy": { "title": "Proxy configuration", "type": "object", "description": "Leave the default for the cheapest run. The catalog gateway serves ordinary shared connections, so the default pool is enough. Change it only if a run reports that it could not read any results.", "default": { "useApifyProxy": true } } } }, "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 } } } } } } } } } }