From 11e1b41039eac97d48400a138880dddb12ca8722 Mon Sep 17 00:00:00 2001
From: Hande Celikkanat <7702228+handecelikkanat@users.noreply.github.com>
Date: Mon, 17 Nov 2025 13:56:12 +0200
Subject: [PATCH] fix: re-add --to and --from args to cdxt

---
 aws-ccf-dataset.ipynb | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/aws-ccf-dataset.ipynb b/aws-ccf-dataset.ipynb
index a0ee0d8..337df26 100644
--- a/aws-ccf-dataset.ipynb
+++ b/aws-ccf-dataset.ipynb
@@ -380,8 +380,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# Lookup captures for the given url in the commoncrawl cdx index for CC-MAIN-2024-22, returning only the first match\n",
-    "!cdxt --limit 1 --crawl CC-MAIN-2024-22 iter an.wikipedia.org/wiki/Escopete\n",
+    "# Look up this capture in the comoncrawl cdx index\n",
+    "!cdxt --limit 1 --crawl CC-MAIN-2024-22 --from 20240518015810 --to 20240518015810 iter an.wikipedia.org/wiki/Escopete\n",
     "\n",
     "# Cleanup previous work\n",
     "!rm -f TEST-000000.extracted.warc.gz\n",