sd-paper-detail

ScienceDirect Paper Detail Extraction

Extract complete metadata from a ScienceDirect article page.

Steps

Step 1: Navigate to article

Determine the article URL from $ARGUMENTS:

• If a PII is given (e.g. S0957417426005245): URL is {BASE_URL}/science/article/pii/{PII}
• If a full URL is given: use that URL directly
• If a DOI is given: URL is https://doi.org/{DOI} (will redirect to ScienceDirect)

Use navigate_page with initScript to prevent bot detection:

navigate_page({
  url: "{article_url}",
  initScript: "Object.defineProperty(navigator, 'webdriver', {get: () => undefined})"
})

If the article is already open in the current tab, you can skip this and go directly to Step 3.

Step 2: Check access

After navigation, verify:

• If the page shows "Are you a robot" or captcha: auto-click the Cloudflare Turnstile checkbox using the procedure below. If auto-click fails after 2 attempts, tell the user "请在浏览器中完成验证后告知我。"
• If the page URL no longer points to a ScienceDirect article, the user may need to log in. Tell the user: "页面被重定向，请在浏览器中完成登录或认证后告知我。" Then wait.

Cloudflare Turnstile auto-click procedure

When a captcha page is detected (title "请稍候…" or body contains "Are you a robot"):

1. Wait for the Turnstile iframe to load — use evaluate_script to poll for #captcha-box (up to 8s).
2. Take a snapshot — use take_snapshot to get the a11y tree. The checkbox is inside a cross-origin iframe but Chrome DevTools MCP can see it:

   Iframe "包含 Cloudflare 安全质询的小组件"
     checkbox "确认您是真人"   ← target uid
   

3. Click the checkbox — use click(uid) on the checkbox element.
4. Wait and verify — wait 3-5s, then check if document.contentType changed or the page URL changed (indicating success). If still on captcha, retry once or fall back to asking the user.

Step 3: Extract metadata

Use evaluate_script with built-in waiting. Do NOT use wait_for — it returns oversized snapshots on article pages.