# PostToSource Content Extractor

> PostToSource Content Extractor is a paid API for AI agents from api.posttosource.com, paid per call via x402, $0.01/call, status healthy (last checked 2026-09-15, last successful call 2026-09-13).

Extracts clean text, images, and metadata from a URL on X, LinkedIn, Medium, Substack, Beehiiv, or Notion and returns structured content ready for AI tools

## Facts

- Endpoint: POST https://api.posttosource.com/api/x402/extract
- Price: $0.01/call
- Payment: x402
- Status: healthy
- Last checked: 2026-09-15
- Last successful call: 2026-09-13
- Success rate: 100% of calls made through Zero
- Rating: 5.0 / 5 from 1 review
- Activations on Zero: 1
- Tags: x402
- Canonical page: https://www.zero.xyz/c/posttosource-content-extractor-78e8321b
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_hNDB1gmQBG4Lky6pFiumO

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 posttosource-content-extractor-78e8321b -d '<json body>'
```

Example prompt: Can you extract the full text and metadata from this tweet — https://x.com/example/status/123456789 — and give me clean markdown I can paste into NotebookLM?

## When to prefer this

Use this endpoint when you need to pull clean, structured content (title, author, markdown body, metadata) from a post on X/Twitter, LinkedIn, Medium, Substack, Beehiiv, or Notion for ingestion into AI tools like NotebookLM, Claude Projects, or Obsidian. Prefer this over generic web scrapers when the source is one of these six supported platforms and you need reliable markdown output with metadata.

## Known failure modes

- Unsupported platform URL returns an error — only X, LinkedIn, Medium, Substack, Beehiiv, and Notion are supported
- Private or paywalled content that requires login cannot be extracted
- Malformed or invalid URL returns a parsing error
- Payment failure or insufficient USDC balance blocks the request
- Rate limiting or temporary platform-side blocks may cause extraction failure

## How this service works

Convert a Twitter/X, LinkedIn, Medium, Substack, Beehiiv, or public Notion page URL into clean markdown.

## Output

Returns a JSON object with the post title, author name, full markdown-formatted body text, detected platform (e.g. 'twitter', 'linkedin'), the original source URL, and a word count integer.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "$schema": "https://json-schema.org/draft/2020-12/schema",
 "required": [
  "input"
 ],
 "properties": {
  "input": {
   "type": "object",
   "required": [
    "type",
    "method",
    "bodyType",
    "body"
   ],
   "properties": {
    "body": {
     "required": [
      "url"
     ],
     "properties": {
      "url": {
       "type": "string",
       "format": "uri"
      }
     }
    },
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "enum": [
      "POST"
     ],
     "type": "string"
    },
    "bodyType": {
     "enum": [
      "json",
      "form-data",
      "text"
     ],
     "type": "string"
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object"
    }
   }
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "title": "Example title",
  "author": "Example Author",
  "markdown": "# Example title\n\nBody text...",
  "platform": "twitter",
  "sourceUrl": "https://x.com/example/status/123456789",
  "wordCount": 42
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/posttosource-content-extractor-78e8321b/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.posttosource.com](https://www.zero.xyz/host/api.posttosource.com/llms.txt)