From 9beb223a0d29278141c822fdee7ba43994ec4192 Mon Sep 17 00:00:00 2001
From: "copilot-swe-agent[bot]" <198982749+Copilot@users.noreply.github.com>
Date: Mon, 9 Mar 2026 11:12:57 +0000
Subject: [PATCH 1/2] Initial plan


From 5393962c7d3a15c3c824b2da7e4f6673a8eb944e Mon Sep 17 00:00:00 2001
From: "copilot-swe-agent[bot]" <198982749+Copilot@users.noreply.github.com>
Date: Mon, 9 Mar 2026 11:15:03 +0000
Subject: [PATCH 2/2] Add OECD scraper (scrapers/oecd.org.js)

Co-authored-by: susannaanas <4725416+susannaanas@users.noreply.github.com>
---
 scrapers/oecd.org.js | 56 ++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 56 insertions(+)
 create mode 100644 scrapers/oecd.org.js

diff --git a/scrapers/oecd.org.js b/scrapers/oecd.org.js
new file mode 100644
index 000000000..63ba2aecd
--- /dev/null
+++ b/scrapers/oecd.org.js
@@ -0,0 +1,56 @@
+module.exports = {
+    // JSON: SelectorElement "div.card---theme" (note triple dash in class name)
+    listSelector: 'div.card---theme',
+
+    parse: ($, el) => {
+        const titleEl = $(el).find('a').first();
+        const title = titleEl.text().trim();
+        const rawLink = titleEl.attr('href');
+
+        if (!title || !rawLink) return null;
+
+        const link = new URL(rawLink, 'https://www.oecd.org').href;
+
+        // Lazy-load image fallback pattern
+        const imgEl = $(el).find('img').first();
+        let img = imgEl.attr('src')
+                 || imgEl.attr('data-src')
+                 || imgEl.attr('data-lazy-src')
+                 || imgEl.attr('data-original')
+                 || null;
+
+        // Discard base64 placeholder images
+        if (img && img.startsWith('data:')) img = null;
+
+        const rawDate = $(el).find('.card__date').first().text().trim();
+        const pubDate = parseOecdDate(rawDate);
+
+        return {
+            title,
+            link,
+            enforcedImage: img,
+            content: '',
+            pubDate,
+            creator: 'OECD'
+        };
+    }
+};
+
+function parseOecdDate(str) {
+    if (!str) return new Date().toISOString();
+
+    // Try DD/MM/YYYY (European slash format)
+    const slashMatch = str.match(/^(\d{1,2})\/(\d{1,2})\/(\d{4})$/);
+    if (slashMatch) {
+        const day   = parseInt(slashMatch[1], 10);
+        const month = parseInt(slashMatch[2], 10) - 1;
+        const year  = parseInt(slashMatch[3], 10);
+        return new Date(Date.UTC(year, month, day, 12, 0, 0)).toISOString();
+    }
+
+    // Fallback: JS Date parse ("9 March 2026", "2026-03-09", etc.)
+    const d = new Date(str);
+    if (!isNaN(d.getTime())) return d.toISOString();
+
+    return new Date().toISOString();
+}