Capterra Products Scraper

curl -X POST "https://api.apify.com/v2/acts/arcadium~capterra-products/run-sync-get-dataset-items" \
  -H "Authorization: Bearer $APIFY_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"startUrls":[{"url":"https://www.capterra.com/project-management-software/"}],"maxResultsPerCategory":50}'

// npm install apify-client
import { ApifyClient } from 'apify-client';

const client = new ApifyClient({ token: process.env.APIFY_TOKEN });
const run = await client.actor('arcadium/capterra-products').call({
  "startUrls": [
    {
      "url": "https://www.capterra.com/project-management-software/"
    }
  ],
  "maxResultsPerCategory": 50
});
const { items } = await client.dataset(run.defaultDatasetId).listItems();
console.log(items);

# pip install apify-client
import os
from apify_client import ApifyClient

client = ApifyClient(os.environ["APIFY_TOKEN"])
run = client.actor("arcadium/capterra-products").call(run_input={
    "startUrls": [{
        "url": "https://www.capterra.com/project-management-software/",
    }],
    "maxResultsPerCategory": 50,
})
items = client.dataset(run["defaultDatasetId"]).list_items().items
print(items)

{
  "mcpServers": {
    "apify": {
      "url": "https://mcp.apify.com/?tools=arcadium/capterra-products",
      "headers": {
        "Authorization": "Bearer <APIFY_TOKEN>"
      }
    }
  }
}

# pip install langchain-apify   (reads APIFY_API_TOKEN from the environment)
from langchain_apify import ApifyActorsTool

tool = ApifyActorsTool("arcadium/capterra-products")
rows = tool.invoke({"run_input": {
    "startUrls": [{
        "url": "https://www.capterra.com/project-management-software/",
    }],
    "maxResultsPerCategory": 50,
}})
# or give `tool` to an agent: create_react_agent(llm, [tool])

# pip install llama-index-readers-apify
import os
from llama_index.core import Document, VectorStoreIndex
from llama_index.readers.apify import ApifyActor

reader = ApifyActor(os.environ["APIFY_TOKEN"])
documents = reader.load_data(
    actor_id="arcadium/capterra-products",
    run_input={
        "startUrls": [{
            "url": "https://www.capterra.com/project-management-software/",
        }],
        "maxResultsPerCategory": 50,
    },
    dataset_mapping_function=lambda item: Document(text=str(item.get("description") or ""), metadata={"url": item.get("url")}),
)
index = VectorStoreIndex.from_documents(documents)

# pip install crewai crewai-tools langchain-apify   (reads APIFY_API_TOKEN from the environment)
from crewai import Agent
from crewai_tools import ApifyActorsTool

tool = ApifyActorsTool(actor_name="arcadium/capterra-products")
researcher = Agent(
    role="Research analyst",
    goal="Answer with data collected by the tool",
    backstory="Uses public web data.",
    tools=[tool],
)

{
  "nodes": [
    {
      "name": "Run arcadium/capterra-products",
      "type": "n8n-nodes-base.httpRequest",
      "typeVersion": 4,
      "position": [
        0,
        0
      ],
      "parameters": {
        "method": "POST",
        "url": "https://api.apify.com/v2/acts/arcadium~capterra-products/run-sync-get-dataset-items",
        "authentication": "genericCredentialType",
        "genericAuthType": "httpHeaderAuth",
        "sendBody": true,
        "specifyBody": "json",
        "jsonBody": "{\"startUrls\":[{\"url\":\"https://www.capterra.com/project-management-software/\"}],\"maxResultsPerCategory\":50}",
        "options": {
          "timeout": 300000
        }
      }
    }
  ],
  "connections": {}
}

// Extensions > Apps Script. Store your token once: Project Settings > Script properties > APIFY_TOKEN.
function importLastRun() {
  const token = PropertiesService.getScriptProperties().getProperty('APIFY_TOKEN');
  const url = 'https://api.apify.com/v2/acts/arcadium~capterra-products/runs/last/dataset/items?status=SUCCEEDED&clean=true&format=json';
  const res = UrlFetchApp.fetch(url, { headers: { Authorization: 'Bearer ' + token } });
  const rows = JSON.parse(res.getContentText());
  if (!rows.length) return;
  const keys = Object.keys(rows[0]);
  const values = rows.map((r) => keys.map((k) => (typeof r[k] === 'object' ? JSON.stringify(r[k]) : r[k])));
  const sheet = SpreadsheetApp.getActiveSheet();
  sheet.clearContents();
  sheet.getRange(1, 1, 1, keys.length).setValues([keys]);
  sheet.getRange(2, 1, values.length, keys.length).setValues(values);
}