Package com.tnsai.tools.scraping

Class ScrapingTools

java.lang.Object

com.tnsai.tools.scraping.ScrapingTools

public class ScrapingTools
extends Object

Function-shape Apify scraping tools — universal web-scraping platform with 2,600+ pre-built actors. Replaces the legacy ApifyTool (single dispatched tool).

Method	Endpoint	Idempotent
apifyRunActor(java.lang.String, java.util.Map<java.lang.String, java.lang.Object>)	POST /v2/acts/{id}/run-sync-get-dataset-items	false (executes a scrape)
apifySearchActors(java.lang.String, int)	GET /v2/store	true (read-only catalog)
apifyActorInfo(java.lang.String)	GET /v2/acts/{id}	true (read-only metadata)

Requires APIFY_API_KEY. Sign up at apify.com.

Popular actor IDs (LLM can pass these directly to apifyRunActor(java.lang.String, java.util.Map<java.lang.String, java.lang.Object>)):

• junglee/amazon-crawler — Amazon products
• streamers/youtube-scraper — YouTube videos / channels
• apify/website-content-crawler — generic site crawl
• compass/crawler-google-places — Google Maps places
• clockworks/tiktok-scraper — TikTok posts
• apify/instagram-scraper — Instagram profiles

Since:

0.5.7 (Phase 2 batch 17a — built-in tool migration to function shape, see #188)

Constructor Summary

Constructors

Constructor	Description
ScrapingTools()	Default constructor — picks APIFY_API_KEY from env.
ScrapingTools(String apiKey)	Explicit-key constructor.
ScrapingTools(String apiKey, okhttp3.OkHttpClient http, com.fasterxml.jackson.databind.ObjectMapper mapper)	Full constructor for tests / shared HTTP.

Method Summary

Modifier and Type	Method	Description
String	apifyActorInfo(String actorId)
String	apifyRunActor(String actorId, Map<String,Object> input)
String	apifySearchActors(String query, int limit)

Methods inherited from class java.lang.Object

equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Details

ScrapingTools

public ScrapingTools()

Default constructor — picks APIFY_API_KEY from env.

ScrapingTools

public ScrapingTools(String apiKey)

Explicit-key constructor.

ScrapingTools

public ScrapingTools(String apiKey,
 okhttp3.OkHttpClient http,
 com.fasterxml.jackson.databind.ObjectMapper mapper)

Full constructor for tests / shared HTTP.

Method Details

apifyRunActor

@Tool(name="apify_run_actor",
      description="Run an Apify actor synchronously and return its dataset items as JSON. {actorId} is the actor\'s full id (e.g. \"junglee/amazon-crawler\", \"apify/website-content-crawler\"). {input} is the actor-specific JSON input map (see the actor\'s input schema). Returns the dataset items array. Read-timeout is 180s \u2014 pick a different actor (or use the async pattern) for long-running scrapes. Requires APIFY_API_KEY.",
      keywords={"apify","scrape","scraper","crawl","actor"},
      idempotent=false)
public String apifyRunActor(@ToolParam(description="Apify actor id (e.g. \"junglee/amazon-crawler\")")
 String actorId,
 @ToolParam(description="Actor input as a JSON map (consult the actor\'s input schema)",required=false)
 Map<String,Object> input)
                     throws IOException

Throws:

IOException

apifySearchActors

@Tool(name="apify_search_actors",
      description="Search the Apify Store for actors by free-text {query}. {limit} clamps to [1, 100]. Returns the raw JSON store listing. Use this when the LLM doesn\'t already know an actor id and needs to discover one for a particular site / task. Requires APIFY_API_KEY.",
      keywords={"apify","search","actors","store","discovery"},
      idempotent=true)
public String apifySearchActors(@ToolParam(description="Free-text actor search query (e.g. \"linkedin profile\")")
 String query,
 @ToolParam(description="Max results (1..100); 0 \u2192 default 10",required=false,defaultValue="0")
 int limit)
                         throws IOException

Throws:

IOException

apifyActorInfo

@Tool(name="apify_actor_info",
      description="Fetch metadata + input schema for a single Apify actor by id. Useful when the LLM needs to know what fields an actor\'s input map accepts before calling apify_run_actor. Requires APIFY_API_KEY.",
      keywords={"apify","actor","info","schema"},
      idempotent=true)
public String apifyActorInfo(@ToolParam(description="Apify actor id")
 String actorId)
                      throws IOException

Throws:

IOException