LangChain · RAG · Apple Podcasts · MCP

How to use Apple Podcasts Scraper with LangChain and RAG

Apple Podcasts Scraper (taroyamada/apple-podcast-scraper) feeds LangChain RAG by calling any Store Actor through langchain-apify: ApifyWrapper.call_actor maps dataset items into Document objects, or ApifyActorsTool wraps the Actor for an agent. Optional: connect Apify’s MCP server at https://mcp.apify.com and use call-actor + get-dataset-items. Listing first search with limit 3 is about $0.0125; from $2.50 / 1,000 results.

Open Apple Podcasts Scraper Input on Apify Store

Last updated: 2026-10-30 (Asia/Tokyo). Integration steps verified on Apify docs the same day.

What this path does

You pull public Apple Podcasts search, chart, or lookup rows (optional recent episode titles) into LangChain documents for retrieval or agent tools. The Actor uses official iTunes Search / Lookup plus RSS when episodes are on. No Apple ID, no proxy, no review text on this Actor — reviews belong on Apple Podcasts Reviews Scraper.

PieceRole
Packagepip install langchain-apify (Python; docs.apify.com/integrations/langchain)
Actortaroyamada/apple-podcast-scraper
First proof inputsearchTerm + limit 3; includeEpisodes false
Document fieldsMap showName, publisher, sourceUrl, optional episodeTitle
MCP (optional)https://mcp.apify.com — call-actor then get-dataset-items

Load podcast rows into a vector index

Apify’s LangChain doc states you can use all Apify Actors as document loaders via ApifyWrapper.call_actor. Token goes in APIFY_TOKEN (Console → API & Integrations). Pattern verified on 2026-10-30:

import os
from langchain_apify import ApifyWrapper
from langchain_core.documents import Document
from langchain_core.vectorstores import InMemoryVectorStore
from langchain_openai.embeddings import OpenAIEmbeddings

os.environ["APIFY_TOKEN"] = "Your Apify API token"

apify = ApifyWrapper()
loader = apify.call_actor(
    actor_id="taroyamada/apple-podcast-scraper",
    run_input={
        "searchTerm": "technology",
        "country": "us",
        "limit": 3,
        "includeEpisodes": False,
    },
    dataset_mapping_function=lambda item: Document(
        page_content=(item.get("showName") or "")
        + " — "
        + (item.get("publisher") or ""),
        metadata={
            "source": item.get("sourceUrl"),
            "collectionId": item.get("collectionId"),
            "country": item.get("country"),
        },
    ),
)
vector_store = InMemoryVectorStore.from_documents(
    loader.load(), OpenAIEmbeddings()
)
retriever = vector_store.as_retriever()

Raise limit, add chartRequests, or set includeEpisodes true only after three search rows look right. Chart snapshots on this Actor do not compute rank movement.

Call the Actor as a LangChain tool

For agents, Apify documents ApifyActorsTool for any Store Actor without a dedicated wrapper:

from langchain_apify import ApifyActorsTool

tool = ApifyActorsTool("taroyamada/apple-podcast-scraper")
result = tool.invoke({
    "run_input": {
        "searchTerm": "technology",
        "country": "us",
        "limit": 3,
        "includeEpisodes": False,
    }
})

Core helpers such as ApifyRunActorAndGetDatasetTool also run any Actor by ID. Dedicated YouTube/search tools in APIFY_SEARCH_TOOLS wrap other Actors — not this podcast scraper — so use ApifyActorsTool or call_actor here.

Optional: Apify MCP server

From Apify’s MCP doc (2026-10-30): add https://mcp.apify.com to your MCP client (OAuth recommended, or Bearer token). Default tools include search-actors, fetch-actor-details, and call-actor. call-actor returns run status and storage IDs; read rows with get-dataset-items and the run’s datasetId. You can pin tools, for example https://mcp.apify.com?tools=actors,docs,taroyamada/apple-podcast-scraper.

Not this path

Related pages

Actor facts on this page come from this site’s published listing pages. Integration steps come from Apify’s public docs read on 2026-10-30 (Asia/Tokyo): n8n, Make, LangChain, and MCP. Confirm live Store input and pricing before you run.