Diffbot웹·SEO 데이터SEO/AEO

Extract article text

diffbot.x.extract-article

Extracts clean article text, author, date, images, tags, sentiment and NLP facts from a news or blog page

Price
$0.001196/call제공업체 원가
Success rate
100%Last 30 days · 57 calls
Latency p50
3.6 sp95 6.6 s
Last verified
2026. 7. 28.Verified 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
Try online출시 예정Provider docs ↗
  • Uses platform quota
  • Synchronous response
  • Reads public data

파라미터

different HOST than base_url — api.diffbot.com, not kg.diffbot.com

파라미터유형필수설명예시
쿼리 파라미터
url문자열필수target URL to extracthttps://www.technologyreview.com/2020/09/04/1008156/knowledge-graph-ai-reads-web-machine-learning-natural-language-processing/
proxy문자열선택
fields문자열선택comma-delimited optional fields: links, extlinks, meta, querystring, breadcrumb, quotes
paging불리언선택pass false to disable automatic concatenation of multi-page articlestrue
scroll문자열선택'slow' or 'fast' — triggers lazy-loaded content
maxTags정수선택max automatically-generated tags to return10
timeout정수선택30000
callback문자열선택
useProxy문자열선택'default' = datacenter proxy (2 credits/page); 'none' disables
proxyAuth문자열선택
discussion불리언선택pass false to disable automatic comment extractiontrue
renderDelay정수선택extra rendering ms before DOM extraction, max 180000
tagConfidence숫자선택minimum tag relevance score 0.0-1.00.5
naturalLanguage문자열선택run text through the NLP API: entities, sentiment, summary, facts, etc.
categoryConfidence숫자선택minimum category relevance score 0.0-1.00.5
summaryNumSentences정수선택max sentences in the generated summary3
  • 쿼리 파라미터
  • url문자열필수

    target URL to extract

    예시: https://www.technologyreview.com/2020/09/04/1008156/knowledge-graph-ai-reads-web-machine-learning-natural-language-processing/

  • proxy문자열선택
  • fields문자열선택

    comma-delimited optional fields: links, extlinks, meta, querystring, breadcrumb, quotes

  • paging불리언선택

    pass false to disable automatic concatenation of multi-page articles

    예시: true

  • scroll문자열선택

    'slow' or 'fast' — triggers lazy-loaded content

  • maxTags정수선택

    max automatically-generated tags to return

    예시: 10

  • timeout정수선택

    예시: 30000

  • callback문자열선택
  • useProxy문자열선택

    'default' = datacenter proxy (2 credits/page); 'none' disables

  • proxyAuth문자열선택
  • discussion불리언선택

    pass false to disable automatic comment extraction

    예시: true

  • renderDelay정수선택

    extra rendering ms before DOM extraction, max 180000

  • tagConfidence숫자선택

    minimum tag relevance score 0.0-1.0

    예시: 0.5

  • naturalLanguage문자열선택

    run text through the NLP API: entities, sentiment, summary, facts, etc.

  • categoryConfidence숫자선택

    minimum category relevance score 0.0-1.0

    예시: 0.5

  • summaryNumSentences정수선택

    max sentences in the generated summary

    예시: 3

코드 예제

$TOOLSWITCH_KEY를 콘솔에서 생성한 키로 바꾸세요.

Preview
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"

게이트웨이 API는 미리보기 버전이며 URL과 인증 방식이 변경될 수 있습니다. 예제 매개변수는 샘플 데이터입니다. 호출 요금은 $0.001196/call이며 서비스 수수료가 포함되어 있습니다.