]> git.nbdom.net Git - nb.git/commitdiff
Fix regexp when html <td...> as attributes
authorNicolas Boisselier <nicolas.boisselier@gmail.com>
Wed, 31 May 2023 22:15:43 +0000 (00:15 +0200)
committerNicolas Boisselier <nicolas.boisselier@gmail.com>
Wed, 31 May 2023 22:15:43 +0000 (00:15 +0200)
lib/postgres/css_reference.sh

index 0cd7a91aac1598f0235a349fb84722b00c9b856c..bbcd89b16d583a8d52db70ef02760c07454bbd9d 100755 (executable)
@@ -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}' \