joshu

Extract web pages

From Parallel, through Joshu Data Bodega.

Part of Open web & SEO data extract.

Price
Price not listed

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

  • urlsstring, required

  • objectivestring, optional

    What you want from the pages; focuses the excerpts. Up to 5,000 characters.

  • session_idstring, optional

  • client_modelstring, optional

  • search_queriesstring, optional

    Keyword queries that focus the excerpts.

  • max_chars_totalinteger, optional

    Upper bound on excerpt characters across all results.

  • advanced_settingsobject, optional

    {full_content: true or {max_chars_per_result}, excerpt_settings {max_chars_per_result}, fetch_policy {max_age_seconds = 600, timeout_seconds, disable_cache_fallback}}. Full content is off by default.

Call it

Router call with a router API key
curl https://hello.joshu.me/api/router/call \
  -H "Authorization: Bearer $JOSHU_ROUTER_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "endpoint": "parallel.web.extract",
    "params": {
      "urls": [
        "https://example.com/"
      ],
      "advanced_settings": {
        "full_content": true
      }
    }
  }'