Extract article text
diffbot.x.extract-articleExtracts clean article text, author, date, images, tags, sentiment and NLP facts from a news or blog page
- Price
- $0.001196/callAl precio del proveedor
- Success rate
- 100 %Last 30 days · 57 calls
- Latency p50
- 3.6 sp95 6.6 s
- Last verified
- 28 jul 2026Verified working
GEThttps://toolswitch.dev/v1/tools/diffbot.x.extract-article?url=https%3A%2F%2Fwww.technologyreview.com%2F2020%2F09%2F04%2F1008156%2Fknowledge-graph-ai-reads-web-machine-learning-natural-language-processing%2FPreview- Uses platform quota
- Synchronous response
- Reads public data
Parámetros
different HOST than base_url — api.diffbot.com, not kg.diffbot.com
| Parámetro | Tipo | Obligatorio | Descripción | Ejemplo |
|---|---|---|---|---|
| Parámetros de consulta | ||||
url | cadena | Obligatorio | target URL to extract | https://www.technologyreview.com/2020/09/04/1008156/knowledge-graph-ai-reads-web-machine-learning-natural-language-processing/ |
proxy | cadena | Opcional | ||
fields | cadena | Opcional | comma-delimited optional fields: links, extlinks, meta, querystring, breadcrumb, quotes | |
paging | booleano | Opcional | pass false to disable automatic concatenation of multi-page articles | true |
scroll | cadena | Opcional | 'slow' or 'fast' — triggers lazy-loaded content | |
maxTags | entero | Opcional | max automatically-generated tags to return | 10 |
timeout | entero | Opcional | 30000 | |
callback | cadena | Opcional | ||
useProxy | cadena | Opcional | 'default' = datacenter proxy (2 credits/page); 'none' disables | |
proxyAuth | cadena | Opcional | ||
discussion | booleano | Opcional | pass false to disable automatic comment extraction | true |
renderDelay | entero | Opcional | extra rendering ms before DOM extraction, max 180000 | |
tagConfidence | número | Opcional | minimum tag relevance score 0.0-1.0 | 0.5 |
naturalLanguage | cadena | Opcional | run text through the NLP API: entities, sentiment, summary, facts, etc. | |
categoryConfidence | número | Opcional | minimum category relevance score 0.0-1.0 | 0.5 |
summaryNumSentences | entero | Opcional | max sentences in the generated summary | 3 |
- Parámetros de consulta
urlcadenaObligatoriotarget URL to extract
Ejemplo:
https://www.technologyreview.com/2020/09/04/1008156/knowledge-graph-ai-reads-web-machine-learning-natural-language-processing/proxycadenaOpcionalfieldscadenaOpcionalcomma-delimited optional fields: links, extlinks, meta, querystring, breadcrumb, quotes
pagingbooleanoOpcionalpass false to disable automatic concatenation of multi-page articles
Ejemplo:
truescrollcadenaOpcional'slow' or 'fast' — triggers lazy-loaded content
maxTagsenteroOpcionalmax automatically-generated tags to return
Ejemplo:
10timeoutenteroOpcionalEjemplo:
30000callbackcadenaOpcionaluseProxycadenaOpcional'default' = datacenter proxy (2 credits/page); 'none' disables
proxyAuthcadenaOpcionaldiscussionbooleanoOpcionalpass false to disable automatic comment extraction
Ejemplo:
truerenderDelayenteroOpcionalextra rendering ms before DOM extraction, max 180000
tagConfidencenúmeroOpcionalminimum tag relevance score 0.0-1.0
Ejemplo:
0.5naturalLanguagecadenaOpcionalrun text through the NLP API: entities, sentiment, summary, facts, etc.
categoryConfidencenúmeroOpcionalminimum category relevance score 0.0-1.0
Ejemplo:
0.5summaryNumSentencesenteroOpcionalmax sentences in the generated summary
Ejemplo:
3
Ejemplos de código
Sustituye $TOOLSWITCH_KEY por la clave que creaste en la consola.
curl -X GET 'https://toolswitch.dev/v1/tools/diffbot.x.extract-article?url=https%3A%2F%2Fwww.technologyreview.com%2F2020%2F09%2F04%2F1008156%2Fknowledge-graph-ai-reads-web-machine-learning-natural-language-processing%2F' \
-H "X-Toolswitch-Key: $TOOLSWITCH_KEY"import os
import requests
response = requests.request(
"GET",
"https://toolswitch.dev/v1/tools/diffbot.x.extract-article?url=https%3A%2F%2Fwww.technologyreview.com%2F2020%2F09%2F04%2F1008156%2Fknowledge-graph-ai-reads-web-machine-learning-natural-language-processing%2F",
headers={"X-Toolswitch-Key": os.environ["TOOLSWITCH_KEY"]},
)
response.raise_for_status()
print(response.text)const response = await fetch("https://toolswitch.dev/v1/tools/diffbot.x.extract-article?url=https%3A%2F%2Fwww.technologyreview.com%2F2020%2F09%2F04%2F1008156%2Fknowledge-graph-ai-reads-web-machine-learning-natural-language-processing%2F", {
method: "GET",
headers: {
"X-Toolswitch-Key": process.env.TOOLSWITCH_KEY ?? "",
},
});
if (!response.ok) throw new Error(`Request failed: ${response.status}`);
console.log(await response.text());La API de la pasarela está en versión preliminar; su URL y autenticación pueden cambiar. Los parámetros del ejemplo son datos de muestra. Las llamadas se facturan a $0.001196/call, incluida la tarifa de servicio.