diffbot_x_extract-article $0.001495 per call
Extract article text, author and date from a URL. Extracts clean article text, author, date, images, tags, sentiment and NLP facts from a news or blog page (Diffbot · Open web & SEO data)
For AI agents: call diffbot_x_extract-article
POST https://toll402.dev/v1/p/diffbot.x.extract-article
{
"url": "https://www.technologyreview.com/2020/09/04/1008156/knowledge-graph-ai-reads-web-machine-learning-natural-language-processing/",
"paging": true,
"maxTags": 10,
"tagConfidence": 0.5,
"categoryConfidence": 0.5,
"discussion": true,
"summaryNumSentences": 3,
"timeout": 30000
}Answers 402 with x402 payment requirements; pay with any x402 client (@x402/fetch, x402 for Python, toll402-client, toll402-mcp) or send a prepaid-credits key as x-toll402-key (https://toll402.dev/credits). Paid per call via x402 (USDC on Base) or with a prepaid-credits key (x-toll402-key, card at /credits); charged only on success. Start at /llms.txt or connect the MCP server:
npx -y toll402-mcp · remote https://toll402.dev/mcp.Input schema
{
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "target URL to extract",
"examples": [
"https://www.technologyreview.com/2020/09/04/1008156/knowledge-graph-ai-reads-web-machine-learning-natural-language-processing/"
]
},
"fields": {
"type": "string",
"description": "comma-delimited optional fields: links, extlinks, meta, querystring, breadcrumb, quotes"
},
"paging": {
"type": "boolean",
"description": "pass false to disable automatic concatenation of multi-page articles",
"examples": [
true
]
},
"maxTags": {
"type": "integer",
"description": "max automatically-generated tags to return",
"examples": [
10
]
},
"tagConfidence": {
"type": "number",
"description": "minimum tag relevance score 0.0-1.0",
"examples": [
0.5
]
},
"categoryConfidence": {
"type": "number",
"description": "minimum category relevance score 0.0-1.0",
"examples": [
0.5
]
},
"discussion": {
"type": "boolean",
"description": "pass false to disable automatic comment extraction",
"examples": [
true
]
},
"naturalLanguage": {
"type": "string",
"description": "run text through the NLP API: entities, sentiment, summary, facts, etc."
},
"summaryNumSentences": {
"type": "integer",
"description": "max sentences in the generated summary",
"examples": [
3
]
},
"renderDelay": {
"type": "integer",
"description": "extra rendering ms before DOM extraction, max 180000"
},
"scroll": {
"type": "string",
"description": "'slow' or 'fast' — triggers lazy-loaded content"
},
"timeout": {
"type": "integer",
"examples": [
30000
]
},
"proxy": {
"type": "string"
},
"proxyAuth": {
"type": "string"
},
"useProxy": {
"type": "string",
"description": "'default' = datacenter proxy (2 credits/page); 'none' disables"
},
"callback": {
"type": "string"
}
},
"additionalProperties": true,
"required": [
"url"
],
"description": "different HOST than base_url — api.diffbot.com, not kg.diffbot.com"
}
MCP
{"mcpServers":{"toll402":{"command":"npx","args":["-y","toll402-mcp"],"env":{"TOLL402_WALLET_KEY":"0x..."}}}}