Extract article text

From Diffbot, through Joshu Data Bodega.

Price: $0.00132 per call$1.32 per 1,000 calls

No calls measured in the last 30 days.

Prices include the router's 10% markup and are paid from the usage wallet. Checked on November 11, 2026.

Inputs

urlstring, required
target URL to extract
proxystring, optional
fieldsstring, optional
comma-delimited optional fields: links, extlinks, meta, querystring, breadcrumb, quotes
pagingboolean, optional
pass false to disable automatic concatenation of multi-page articles
scrollstring, optional
'slow' or 'fast' — triggers lazy-loaded content
maxTagsinteger, optional
max automatically-generated tags to return
timeoutinteger, optional
callbackstring, optional
useProxystring, optional
'default' = datacenter proxy (2 credits/page); 'none' disables
proxyAuthstring, optional
discussionboolean, optional
pass false to disable automatic comment extraction
renderDelayinteger, optional
extra rendering ms before DOM extraction, max 180000
tagConfidencenumber, optional
minimum tag relevance score 0.0-1.0
naturalLanguagestring, optional
run text through the NLP API: entities, sentiment, summary, facts, etc.
categoryConfidencenumber, optional
minimum category relevance score 0.0-1.0
summaryNumSentencesinteger, optional
max sentences in the generated summary

Call it

curl https://hello.joshu.me/api/router/call \
  -H "Authorization: Bearer $JOSHU_ROUTER_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "endpoint": "diffbot.x.extract-article",
    "params": {
      "url": "https://www.technologyreview.com/1234/09/04/1234567/knowledge-graph-ai-reads-web-machine-learning-natural-language-processing/"
    }
  }'