{ "openapi": "3.0.1", "info": { "title": "Lemon8 Media Scraper: Images, Videos & Downloads", "description": "Lightweight Lemon8 scraper for extracting image and video URLs from posts, with optional media downloads. Built for fast, clean media collection without comments, captions, or other post details.", "version": "2.0", "x-build-id": "08GbmREkA44Zeet2Y" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/abotapi~lemon8-media-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-abotapi-lemon8-media-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/abotapi~lemon8-media-scraper/runs": { "post": { "operationId": "runs-sync-abotapi-lemon8-media-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/abotapi~lemon8-media-scraper/run-sync": { "post": { "operationId": "run-sync-abotapi-lemon8-media-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "mode": { "title": "Mode", "enum": [ "auto", "post", "discover", "profile", "feed" ], "type": "string", "description": "What to scrape. auto (default): your own Post URLs if set, otherwise the Search Term. The example Post URLs run only when you set none of: a Search Term other than fashion, Keywords, Profile URLs, Incremental mode, State key, Resume, or a region other than us. post: the Post URLs list. discover: Keywords (or Search Term). profile: Profile URLs. feed: Feed categories. In a chosen mode only that mode's input is used.", "default": "auto" }, "postUrls": { "title": "Post URLs", "type": "array", "description": "Lemon8 URLs to scrape: post pages (/@user/), discovery pages (/discover/ or /experience/, region taken from ?region=), profile pages (/@user, lists the profile's posts) and topic pages (/topic/). Tracking parameters are ignored. Unsupported URLs are skipped with a warning. When postUrls holds your own URLs, searchTerm is ignored. The example list is dropped when you set a different Search Term, Keywords, Profile URLs, Incremental mode, State key, Resume or a region other than us (clear the list to search by keyword).", "items": { "type": "string" }, "default": [ "https://www.lemon8-app.com/@05luvlee/7535454724489986574?region=us", "https://www.lemon8-app.com/discover/fashion?region=us", "https://www.lemon8-app.com/experience/fashion?region=us", "https://www.lemon8-app.com/discover/fashion?region=jp", "https://www.lemon8-app.com/@05luvlee?region=us" ] }, "searchTerm": { "title": "Search Term", "type": "string", "description": "Search keyword to find posts on Lemon8 discovery page. Used only if postUrls is empty (or still holds the example list while you set a different keyword).", "default": "fashion" }, "feedCategories": { "title": "Feed categories (feed mode)", "type": "array", "description": "Category feeds to read in feed mode (the first page of each, about 10 posts). Defaults to For you when empty.", "items": { "type": "string", "enum": [ "foryou", "food", "beauty", "fashion", "home", "fitness", "health", "relationship", "travel", "photography", "pet", "reading", "cars", "outdoors" ] } }, "keywords": { "title": "Keywords (discover mode)", "type": "array", "description": "Keywords to search on Lemon8 in discover mode (about 50 posts per keyword). Also used in auto mode when Post URLs is cleared. The Limit / Max results cap applies in order across keywords.", "items": { "type": "string" } }, "profileUrls": { "title": "Profile URLs (profile mode)", "type": "array", "description": "Lemon8 profile pages or @usernames to list in profile mode (the posts shown on the profile page).", "items": { "type": "string" } }, "region": { "title": "Region", "type": "string", "description": "Region code for Lemon8. Common codes: us, uk, jp, th, id, ph, vn, my, sg (any other code, e.g. au, is passed through as typed).", "default": "us" }, "limit": { "title": "Limit", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Maximum number of posts to return (1 to 1000 per run)", "default": 2 }, "saveImages": { "title": "Save Images", "type": "boolean", "description": "Extract image URLs from posts", "default": true }, "saveVideos": { "title": "Save Videos", "type": "boolean", "description": "Extract video URLs from posts", "default": true }, "downloadMedia": { "title": "Download Media", "type": "boolean", "description": "Download media files to key-value store (increases run time and storage)", "default": false }, "highQuality": { "title": "High Quality URLs", "type": "boolean", "description": "Convert thumbnail URLs to high quality versions", "default": true }, "proxy": { "title": "Proxy Configuration", "type": "object", "description": "Proxy for requests. Defaults to Apify datacenter (US); if the datacenter tunnel is unavailable or gets blocked, the actor automatically falls back to a backup proxy pool." }, "resumeFromRunId": { "title": "Resume from a previous run", "type": "string", "description": "Paste a previous run ID or dataset ID to continue a large pull of posts without returning or charging for posts already collected there. Use this after an interrupted run, or when continuing a pull in another run. For recurring monitoring of the same posts/search, use Incremental mode below instead." }, "incrementalMode": { "title": "Incremental changes for scheduled runs", "type": "boolean", "description": "Turn this on for daily or recurring monitoring. The first run returns all matching posts as NEW. Later runs normally return only NEW, UPDATED, and REAPPEARED posts. Turn on \"Emit unchanged\" or \"Emit expired\" only when you also want those posts returned (and billed). State is kept separately for each postUrls/searchTerm, region, and media-option combination; use State key when you want 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 mode and its inputs (postUrls/searchTerm, keywords, profileUrls or feedCategories), region, and the media options — different setups then never mix state with each other." }, "emitUnchanged": { "title": "Emit unchanged posts (incremental mode only)", "type": "boolean", "description": "Off by default. Turn on to also return posts 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 the full snapshot every run.", "default": false }, "emitExpired": { "title": "Emit expired posts (incremental mode only)", "type": "boolean", "description": "Off by default. Turn on to also return posts that were present in a previous run but are no longer found, marked EXPIRED. Only produced once a run has fully scanned every tracked post — not when Limit capped it, or when Resume was used. This returns — and bills — extra synthetic rows, so leave it off unless you need expiry tracking.", "default": false }, "ignoreFieldsForChanges": { "title": "Ignore fields when detecting changes (incremental mode only)", "type": "array", "description": "Optional. Field names that must not make a post UPDATED or appear in Changed fields, for example imageCount when you do not care about that movement. Use a dotted path such as images.alt to ignore one key inside every item of a list. The fields still appear in the output; they are only left out of the comparison. Changing this list never marks the whole baseline as updated.", "default": [], "items": { "type": "string" } }, "mcpConnectors": { "title": "Pipe results into your apps (optional)", "type": "array", "description": "Optionally send the scraped results into the apps you already use, via Model Context Protocol (MCP) connectors. Authorize a connector once under Apify → Settings → Integrations, then select it here. The connector receives a condensed, human-readable summary per item (title + key fields), not the full JSON — the complete record stays in the dataset. Leave empty to skip. 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 item 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 items written to each connector per run. Does not affect the dataset.", "default": 50 } } }, "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 } } } } } } } } } }