From: Nicolas Boisselier <nicolas.boisselier@gmail.com>
Date: Wed, 31 May 2023 22:50:14 +0000 (+0200)
Subject: use www.w3schools.com
X-Git-Url: https://git.nbdom.net/?a=commitdiff_plain;h=2d56601b7b2a0fd452c98f1679504e3d71a4cc79;p=nb.git

use www.w3schools.com
---

diff --git a/lib/postgres/html_attribute.sh b/lib/postgres/html_attribute.sh
index fadb700e..6bcaa627 100755
--- a/lib/postgres/html_attribute.sh
+++ b/lib/postgres/html_attribute.sh
@@ -1,7 +1,19 @@
 #!/bin/bash -l
-http_get https://html.com/attributes/ \
+
+# NB 01.06.23: TODEL  
+false && http_get https://html.com/attributes/ \
 | sed -E "s,<(thrive_headline|header)[^.>]+>([^<]+)</\1>,<div>\2</div>," \
 | xmllint --html --xpath //table - 2>/dev/null \
 | sed -E "s,<a[^>]+href=\"((https://html.com)?/attributes/([^\"\/]+)\/?)[^<]+</a>,\3</td><td>https://html.com/\1,g" \
 | xml2csv - \
 | awk 'BEGIN{FS="\t"}{print $1"\t"$3"\t"$2}' \
+
+
+true && http_get https://www.w3schools.com/tags/ref_attributes.asp | \
+xmllint --html --xpath '/html/body//div[@id="main"]//table' - 2>/dev/null | \
+grep -v 'href="tag_' | \
+perl -pe 's|<td[^>]*><a href="([^"]+)">([^<]+)</a></td>|<td>https://www.w3schools.com/tags/$1</td><td>$2</td>|' | \
+html2csv | \
+sed -E "s,(\\\\),\1\1," | \
+awk 'BEGIN{FS="\t"} /www\.w3schools\.com/ {print $2"\t"$3"\t"$1}' \
+