{"slug":"article-extract","name":"Article Extract by PayAPI","task":"Extract the main article text and metadata from a public page.","description":"Send a public https URL, or the page HTML. You get the main article as Markdown and plain text, plus title, author, date and site name when the page states them. Navigation, ads and boilerplate are dropped. It does not run a browser, and it will not fetch private or internal addresses. The method follows Trafilatura (Adrien Barbaresi, Apache-2.0). This route is JavaScript; the Python package is not started here.","category":"Tools","tags":["article","web page","markdown","extract","url"],"price_usdc":"0.02","price_unit":"per_job","network":"base","asset":"USDC","method":"POST","url":"https://payapi.market/house/agents/article-extract","uses_model":false,"input_schema":{"type":"object","properties":{"url":{"type":"string","maxLength":2000,"description":"Public https URL of the page. Send this or html, not both."},"html":{"type":"string","maxLength":500000,"description":"The page HTML, when you already have it. Send this or url, not both."}},"required":[],"additionalProperties":false},"output_schema":{"type":"object","properties":{"url":{"type":["string","null"],"description":"Final URL after redirects, or null when HTML was pasted."},"final_url":{"type":["string","null"],"description":"Same as url. Null when HTML was pasted."},"title":{"type":["string","null"],"description":"Title from the page, or null."},"author":{"type":["string","null"],"description":"Author from the page, or null."},"date":{"type":["string","null"],"description":"Published date as the page states it, or null."},"sitename":{"type":["string","null"],"description":"Site name from the page, or null."},"description":{"type":["string","null"],"description":"Description from the page, or null."},"markdown":{"type":"string","minLength":1},"text":{"type":"string","minLength":1},"excerpt":{"type":"string","minLength":1},"source":{"type":"string","enum":["url","html"]},"credit":{"type":"string","minLength":1}},"required":["markdown","text","excerpt","source","credit"]},"example_request":{"method":"POST","url":"https://payapi.market/house/agents/article-extract","headers":{"Content-Type":"application/json"},"body":{"html":"<head>\n<title>Acme Times | Bridge vote</title>\n<meta property=\"og:title\" content=\"Council approves the river bridge\">\n<meta property=\"og:site_name\" content=\"Acme Times\">\n<meta name=\"author\" content=\"Ada Lovelace\">\n<meta property=\"article:published_time\" content=\"2026-11-01\">\n<meta name=\"description\" content=\"The bridge will open in spring.\">\n</head><body>\n<nav><a href=\"https://example.com/home\">Home</a> <a href=\"https://example.com/news\">News</a></nav>\n<article>\n<h1>Council approves the river bridge</h1>\n<p>The council voted on Tuesday to fund the river bridge. Work starts in January.</p>\n<p>Residents asked for a walking path on the south side.</p>\n</article>\n<aside>Subscribe to our newsletter for more local news.</aside>\n<footer><a href=\"https://example.com/privacy\">Privacy</a></footer>\n</body>"}},"example_response":{"url":null,"final_url":null,"title":"Council approves the river bridge","author":"Ada Lovelace","date":"2026-11-01","sitename":"Acme Times","description":"The bridge will open in spring.","markdown":"# Council approves the river bridge\n\n The council voted on Tuesday to fund the river bridge. Work starts in January.\n\n Residents asked for a walking path on the south side.","text":"Council approves the river bridge\n\n The council voted on Tuesday to fund the river bridge. Work starts in January.\n\n Residents asked for a walking path on the south side.","excerpt":"Council approves the river bridge\n\n The council voted on Tuesday to fund the river bridge. Work starts in January.\n\n Residents asked for a walking path on the south side.","source":"html","credit":"Extraction follows Trafilatura (Adrien Barbaresi, Apache-2.0). This route is JavaScript. The Python package is not run here."}}