From: Nicolas Boisselier <nicolas.boisselier@gmail.com>
Date: Wed, 31 May 2023 22:15:43 +0000 (+0200)
Subject: Fix regexp when html <td...> as attributes
X-Git-Url: https://git.nbdom.net/?a=commitdiff_plain;h=3a0085d58ad152f45ebfbd2fd2966e71d3bb7d4f;p=nb.git

Fix regexp when html <td...> as attributes
---

diff --git a/lib/postgres/css_reference.sh b/lib/postgres/css_reference.sh
index 0cd7a91a..bbcd89b1 100755
--- a/lib/postgres/css_reference.sh
+++ b/lib/postgres/css_reference.sh
@@ -1,7 +1,7 @@
 #!/bin/bash -l
 http_get https://www.w3schools.com/cssref/index.php | \
 xmllint --html --xpath '/html/body//div[@id="cssproperties"]//table' - 2>/dev/null | \
-perl -pe 's|<td><a href="([^"]+)">([^<]+)</a></td>|<td>https://www.w3schools.com/cssref/$1</td><td>$2</td>|' | \
+perl -pe 's|<td[^>]*><a href="([^"]+)">([^<]+)</a></td>|<td>https://www.w3schools.com/cssref/$1</td><td>$2</td>|' | \
 html2csv | \
 sed -E "s,(\\\\),\1\1," | \
 awk 'BEGIN{FS="\t"}{print $2"\t"$3"\t"$1}' \