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/callZum Anbieterpreis
- Success rate
- 100 %Last 30 days · 57 calls
- Latency p50
- 3.6 sp95 6.6 s
- Last verified
- 28.07.2026Verified 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
Parameter
different HOST than base_url — api.diffbot.com, not kg.diffbot.com
| Parameter | Typ | Erforderlich | Beschreibung | Beispiel |
|---|---|---|---|---|
| Abfrageparameter | ||||
url | Zeichenkette | Erforderlich | target URL to extract | https://www.technologyreview.com/2020/09/04/1008156/knowledge-graph-ai-reads-web-machine-learning-natural-language-processing/ |
proxy | Zeichenkette | Optional | ||
fields | Zeichenkette | Optional | comma-delimited optional fields: links, extlinks, meta, querystring, breadcrumb, quotes | |
paging | Boolean | Optional | pass false to disable automatic concatenation of multi-page articles | true |
scroll | Zeichenkette | Optional | 'slow' or 'fast' — triggers lazy-loaded content | |
maxTags | Ganzzahl | Optional | max automatically-generated tags to return | 10 |
timeout | Ganzzahl | Optional | 30000 | |
callback | Zeichenkette | Optional | ||
useProxy | Zeichenkette | Optional | 'default' = datacenter proxy (2 credits/page); 'none' disables | |
proxyAuth | Zeichenkette | Optional | ||
discussion | Boolean | Optional | pass false to disable automatic comment extraction | true |
renderDelay | Ganzzahl | Optional | extra rendering ms before DOM extraction, max 180000 | |
tagConfidence | Zahl | Optional | minimum tag relevance score 0.0-1.0 | 0.5 |
naturalLanguage | Zeichenkette | Optional | run text through the NLP API: entities, sentiment, summary, facts, etc. | |
categoryConfidence | Zahl | Optional | minimum category relevance score 0.0-1.0 | 0.5 |
summaryNumSentences | Ganzzahl | Optional | max sentences in the generated summary | 3 |
- Abfrageparameter
urlZeichenketteErforderlichtarget URL to extract
Beispiel:
https://www.technologyreview.com/2020/09/04/1008156/knowledge-graph-ai-reads-web-machine-learning-natural-language-processing/proxyZeichenketteOptionalfieldsZeichenketteOptionalcomma-delimited optional fields: links, extlinks, meta, querystring, breadcrumb, quotes
pagingBooleanOptionalpass false to disable automatic concatenation of multi-page articles
Beispiel:
truescrollZeichenketteOptional'slow' or 'fast' — triggers lazy-loaded content
maxTagsGanzzahlOptionalmax automatically-generated tags to return
Beispiel:
10timeoutGanzzahlOptionalBeispiel:
30000callbackZeichenketteOptionaluseProxyZeichenketteOptional'default' = datacenter proxy (2 credits/page); 'none' disables
proxyAuthZeichenketteOptionaldiscussionBooleanOptionalpass false to disable automatic comment extraction
Beispiel:
truerenderDelayGanzzahlOptionalextra rendering ms before DOM extraction, max 180000
tagConfidenceZahlOptionalminimum tag relevance score 0.0-1.0
Beispiel:
0.5naturalLanguageZeichenketteOptionalrun text through the NLP API: entities, sentiment, summary, facts, etc.
categoryConfidenceZahlOptionalminimum category relevance score 0.0-1.0
Beispiel:
0.5summaryNumSentencesGanzzahlOptionalmax sentences in the generated summary
Beispiel:
3
Codebeispiele
Ersetze $TOOLSWITCH_KEY durch den in der Konsole erstellten Schlüssel.
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());Diese Gateway-API ist eine Vorschauversion; URL und Authentifizierung können sich ändern. Die Beispielparameter sind Musterdaten. Aufrufe werden mit $0.001196/call einschließlich Servicegebühr abgerechnet.