# Article Summarizer (Claude — TL;DR + Bullets + Topics) (`gochujang/article-summarizer`) Actor

Pass any URL or text — get back a tight summary in your chosen style (TL;DR / bullets / executive / tweet) plus topic tags + sentiment. Article body auto-extracted via trafilatura. BYO Anthropic API key. $0.005 per summary, Claude tokens billed by Anthropic.

- **URL**: https://apify.com/gochujang/article-summarizer.md
- **Developed by:** [Hojun Lee](https://apify.com/gochujang) (community)
- **Categories:** AI
- **Features:** Limited permissions
- **Stats:** 2 total users, 0 monthly users, 100.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

from $5.00 / 1,000 article summarizeds

This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events.

Learn more: https://docs.apify.com/actors/running/actors-in-store.md#pay-per-event

## What's an Apify Actor?

An Actor is a serverless cloud program that runs on the Apify platform. It has two run modes.
In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours,
and optionally produces a well-defined JSON output, datasets with results, or files in key-value store.
In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server.

Apify vocabulary and the platform model are defined once, in the agent quickstart at https://apify.com/agents.md.

## How to integrate an Actor?

If asked about integration, you help developers integrate Actors into their projects.
You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready.

Do not guess an integration path. Every one of them is in the agent quickstart at https://apify.com/agents.md: the Apify MCP server, Agent Skills with the Apify CLI, the JavaScript and Python clients, the REST API, and the account-free path for an agent with no human to sign in. It also carries the rule on stating cost before the first paid run.

For examples already wired to this Actor's own input schema, see the [API](#api) section below.

Each client library has reference documentation the quickstart does not restate: [JavaScript/TypeScript](https://docs.apify.com/api/client/js/docs.md) (`npm install apify-client`) and [Python](https://docs.apify.com/api/client/python/docs.md) (`pip install apify-client`).

# README

## Article Summarizer (Claude)

> Pass any URL or text — get back a tight summary in your chosen style (**TL;DR / bullets / executive / tweet**) plus topic tags + sentiment. Article body auto-extracted via trafilatura. **BYO Anthropic API key. $0.005 per summary.**

***

### Input Parameters

| Parameter | Type | Default | Description |
|---|---|---|---|
| `url` | string | ``| URL of the article (used if 'text' is empty). |
| `text` | string |`` | Pass article text directly to skip URL fetch. |
| `style` | string | `both` | Output format. |
| `maxWords` | integer | `250` | Soft cap on summary length. |
| `language` | string | `en` | ISO code or language name (e.g. en, ko, es, French). |
| `extractTopics` | boolean | `true` | Append a JSON block with 3-5 topic tags + sentiment. |
| `model` | string | `claude-opus-4-7` | Claude model to use. Opus is highest-quality; Haiku is fastest/cheapes |
| `anthropicApiKey` | string | `—` | Get one at console.anthropic.com. Saved encrypted by Apify. |
| `userAgent` | string | \`\` | Custom UA. |

***

### Why this exists

Summarizing 50 articles a day by hand is dead time. Hiring a summarization SaaS (e.g. Lex.page, Glasp, Summari) costs $20-100/month per seat. This actor wraps trafilatura (article extraction) + Claude (summarization) in one call:

1. URL → clean article body (no nav, ads, comments)
2. Body → Claude with your chosen output style
3. Optional: topic tags + sentiment

You pay Apify $0.005 per summary; Anthropic bills you for tokens (typically $0.001-0.01 per summary at Opus 4.7 prices).

***

### What you get

```json
{
  "url": "https://...",
  "title": "Bitcoin tops $70K",
  "author": "Jane Doe",
  "date_published": "2026-06-09",
  "sitename": "TechCrunch",
  "char_count_input": 4820,
  "summary": "**TL;DR**: BTC ...\n\n- Key 1\n- Key 2\n- Key 3\n...",
  "style": "both",
  "model": "claude-opus-4-7",
  "language": "en",
  "claude_usage": {"input_tokens": 2580, "output_tokens": 360}
}
```

***

### Output styles

| `style` | What you get |
|---|---|
| `tldr` | Single paragraph TL;DR |
| `bullets` | 5–7 key bullet points |
| `both` | TL;DR + bullets (default) |
| `twitter` | 280-char tweet of the most surprising idea |
| `executive` | TL;DR + key implications + recommended action |

***

### Quick start

#### Summarize a URL

```json
{
  "url": "https://en.wikipedia.org/wiki/Bitcoin",
  "style": "both",
  "anthropicApiKey": "sk-ant-..."
}
```

#### Summarize pasted text

```json
{
  "text": "Long article text here...",
  "style": "tldr",
  "maxWords": 100,
  "anthropicApiKey": "sk-ant-..."
}
```

#### Executive briefing in Korean

```json
{
  "url": "https://...",
  "style": "executive",
  "language": "ko",
  "anthropicApiKey": "sk-ant-..."
}
```

***

### Setting your Anthropic API key

You can:

1. **Paste in input** — secure (marked `isSecret`, encrypted at rest, hidden in logs)
2. **Save as Apify Task** — input including key is saved, click to re-run
3. **Account-level Secret** — register `MY_ANTHROPIC_KEY` in Apify Integrations, reference as `@MY_ANTHROPIC_KEY` in task input

Get a key at [console.anthropic.com](https://console.anthropic.com).

***

### Pricing

**Pay-Per-Event**: `$0.005 per article` (Apify-side).

Anthropic charges separately for tokens. Typical totals:

| Article length | Input tokens | Anthropic cost (Opus 4.7) | Total |
|---|---|---|---|
| 1K words | ~1300 | ~$0.007 | $0.012 |
| 3K words | ~4000 | ~$0.020 | $0.025 |
| 8K words | ~10500 | ~$0.053 | $0.058 |

Use Sonnet (~5x cheaper) or Haiku (~10x cheaper) for cost savings.

***

### Use cases

1. **Newsletter automation** — Daily Top-50 feed → bullet summaries
2. **Research aggregation** — Build a topic-tagged knowledge base
3. **Slack/Discord digests** — Daily summary of #blog-feed channel
4. **Personal read-it-later** — Long articles → 30-second TL;DR
5. **SEO content audit** — Compare summaries of competitor posts

***

### Related actors (same author)

- [Web Page → Markdown Converter](https://apify.com/gochujang/web-to-markdown) — Same extraction without LLM
- [Web Structured Data Extractor](https://apify.com/gochujang/web-structured-extractor) — Extract JSON, not summary
- [Tweet Thread → Article](https://apify.com/gochujang/tweet-thread-to-article)
- [HTML Metadata Extractor](https://apify.com/gochujang/html-metadata-extractor)

***

### Feedback

A short review helps content engineers find it: [Leave a review on Apify Store](https://apify.com/gochujang/article-summarizer#reviews)

**Keywords:** article summarizer, AI summary, Claude AI, TL;DR generator, text summarization, content summary, news summarizer, sentiment analysis, topic tags, multilingual summary, executive brief, research automation, content pipeline, URL summarizer

# Actor input Schema

## `url` (type: `string`):

URL of the article (used if 'text' is empty).

## `text` (type: `string`):

Pass article text directly to skip URL fetch.

## `summaryFormat` (type: `string`):

Output format for the summary.

## `summaryMode` (type: `string`):

abstractive uses Claude to rephrase and condense (requires API key). extractive selects the most important original sentences — fully offline, no API key needed.

## `extractKeyPoints` (type: `boolean`):

Extract 3-7 key takeaway bullet points from the article (returned as `key_points` array). Uses Claude — adds a small amount of tokens.

## `readingLevel` (type: `boolean`):

Classify text complexity as 'elementary', 'intermediate', or 'advanced' using Flesch-Kincaid heuristics (no AI cost). Returned as `reading_level`.

## `summaryLanguage` (type: `string`):

Language for the summary output (ISO code or full name, e.g. 'ko', 'ja', 'French'). Overrides outputLanguage if both are set. Leave empty for English.

## `extractKeywords` (type: `boolean`):

Return a list of the top 10 keywords extracted via TF-IDF from the article body.

## `analyzeSentiment` (type: `boolean`):

Return sentiment (positive/neutral/negative) and a score from -1.0 to 1.0.

## `maxWords` (type: `integer`):

Soft cap on summary length.

## `outputLanguage` (type: `string`):

ISO code or language name for the summary output (e.g. en, ko, ja, zh, es, French).

## `extractTopics` (type: `boolean`):

Append 3-5 topic tags to the output.

## `model` (type: `string`):

Claude model to use. Opus is highest-quality; Haiku is fastest/cheapest.

## `anthropicApiKey` (type: `string`):

Get one at console.anthropic.com. Saved encrypted by Apify.

## `userAgent` (type: `string`):

Custom UA string.

## `language` (type: `string`):

Optional parameter: language

## `style` (type: `string`):

Optional parameter: style

## Actor input object example

```json
{
  "url": "",
  "text": "",
  "summaryFormat": "both",
  "summaryMode": "abstractive",
  "extractKeyPoints": false,
  "readingLevel": false,
  "summaryLanguage": "",
  "extractKeywords": false,
  "analyzeSentiment": false,
  "maxWords": 250,
  "outputLanguage": "en",
  "extractTopics": true,
  "model": "claude-opus-4-7",
  "userAgent": ""
}
```

# Actor output Schema

## `dataset` (type: `string`):

No description

## `summary` (type: `string`):

No description

# API

You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup.

## JavaScript example

```javascript
import { ApifyClient } from 'apify-client';

// Initialize the ApifyClient with your Apify API token
// Replace the '<YOUR_API_TOKEN>' with your token
const client = new ApifyClient({
    token: '<YOUR_API_TOKEN>',
});

// Prepare Actor input
const input = {};

// Run the Actor and wait for it to finish
const run = await client.actor("gochujang/article-summarizer").call(input);

// Fetch and print Actor results from the run's dataset (if any)
console.log('Results from dataset');
console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`);
const { items } = await client.dataset(run.defaultDatasetId).listItems();
items.forEach((item) => {
    console.dir(item);
});

// 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs

```

## Python example

```python
from apify_client import ApifyClient

# Initialize the ApifyClient with your Apify API token
# Replace '<YOUR_API_TOKEN>' with your token.
client = ApifyClient("<YOUR_API_TOKEN>")

# Prepare the Actor input
run_input = {}

# Run the Actor and wait for it to finish
run = client.actor("gochujang/article-summarizer").call(run_input=run_input)

# Fetch and print Actor results from the run's dataset (if there are any)
print(f"💾 Check your data here: https://console.apify.com/storage/datasets/{run.default_dataset_id}")
for item in client.dataset(run.default_dataset_id).iterate_items():
    print(item)

# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start

```

## CLI example

```bash
echo '{}' |
apify call gochujang/article-summarizer --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,gochujang/article-summarizer"
        }
    }
}
```

The hosted server signs you in with OAuth on first connect, so no API token belongs in this config. Clients without OAuth support can send an `Authorization: Bearer <APIFY_API_TOKEN>` header instead, using a token from API & Integrations in Apify Console (https://console.apify.com/settings/integrations).

## OpenAPI specification

Download the OpenAPI definition: https://api.apify.com/v2/actors/StDq4MKYhfkZczDv1/builds/62ySS9uh2Exv0vMj0/openapi.json