# Diffbot Article Extraction

> Diffbot Article Extraction is a paid API for AI agents from Diffbot at diffbot.mpp.paywithlocus.com, paid per call via MPP, $0.0042/call, status unknown (last checked 2026-10-11, last successful call 2026-05-10).

Extracts structured article content (title, text, author, date, tags, comments) from any article URL using Diffbot's AI parsing

## Facts

- Endpoint: POST https://diffbot.mpp.paywithlocus.com/diffbot/article?utm_source=zero.xyz
- Price: $0.0042/call
- Payment: MPP
- Status: unknown
- Last checked: 2026-10-11
- Last successful call: 2026-05-10
- Success rate: 100% of calls made through Zero
- Activations on Zero: 1
- Provider: Diffbot
- Docs: https://docs.diffbot.com
- Website: https://www.diffbot.com
- Tags: web-scraping, extraction, articles, products, web, data
- Canonical page: https://www.zero.xyz/c/diffbot-article-6a01bd1d
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_HtqS8yr7gCG3kx7VvshKi

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability diffbot-article-6a01bd1d -d '<json body>'
```

Example prompt: Pull the full article from https://www.nytimes.com/2024/01/15/technology/ai-regulation.html — extract the title, author, publish date, body text, and up to 15 tags, and also run NLP to get entities and sentiment.

## When to prefer this

Use this endpoint when you need to extract structured data specifically from article or news pages, including NLP enrichment like entities, sentiment, and summaries. Prefer this over the generic Analyze endpoint when you know the page is an article. Choose it over manual HTML parsing when you need clean, normalized fields like author, publish date, and body text without boilerplate.

## Known failure modes

- URL is behind a hard paywall or login wall — returns empty or partial content
- URL is not an article page — returns low-confidence or mismatched content
- Timeout exceeded for slow-loading pages — returns timeout error
- Invalid or unreachable URL — returns HTTP error or connection failure
- Multi-page article not fully concatenated if paging param not set
- NLP features not available for non-English content

## How this service works

Extract clean article text, author, date, images, tags, and sentiment from news/blog pages.

## Output

Returns a structured JSON object containing the parsed article's title, full text content, author name(s), publication date, primary image, tags (up to maxTags), NLP-derived entities/sentiment/summary if requested, and optionally comment threads — all extracted cleanly from the raw HTML of the given URL.

## Example request

```json
{
 "url": "https://www.bbc.com/news/world",
 "fields": "links,meta,breadcrumb",
 "paging": true,
 "maxTags": 10,
 "timeout": 30000,
 "discussion": true,
 "naturalLanguage": "entities,sentiment"
}
```

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "url"
 ],
 "properties": {
  "url": {
   "type": "string",
   "description": "URL of the article page"
  },
  "fields": {
   "type": "string",
   "description": "Comma-separated extra fields to return (e.g. links, meta, breadcrumb)"
  },
  "paging": {
   "type": "boolean",
   "description": "Concatenate multi-page articles"
  },
  "maxTags": {
   "type": "number",
   "description": "Max tags to return (default 10)"
  },
  "timeout": {
   "type": "number",
   "description": "Request timeout in ms (default 30000)"
  },
  "discussion": {
   "type": "boolean",
   "description": "Extract comments/discussion threads (default true for article)"
  },
  "naturalLanguage": {
   "type": "string",
   "description": "NLP features to apply (e.g. entities, sentiment, summary, facts, categories)"
  }
 },
 "additionalProperties": true
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/diffbot-article-6a01bd1d/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from diffbot.mpp.paywithlocus.com](https://www.zero.xyz/host/diffbot.mpp.paywithlocus.com/llms.txt)