~rkta/blog: Add anti-cf article

4 files changed, 77 insertions(+), 0 deletions(-)

M .htaccess
M Makefile
A anti-cf.mc
A assets/anti-cf.cgi

M .htaccess => .htaccess +5 -0

@@ 1,4 1,9 @@
 ErrorDocument 404 "Not found"
+
+<FilesMatch "\.cgi$">
+        SetHandler send-as-is
+</FilesMatch>
+
 Redirect 301 /2017/10/03/irssi-awl-setup/index.html /irssi-awl.html"
 Redirect 301 /2018/12/27/irssi-with-openurl-and-ssh/index.html /irssi-openurl-ssh.html
 Redirect 301 /2018/12/27/wrong-permissions-on-jekyll-_site-files/index.html /jekyll-perms.html

M Makefile => Makefile +1 -0

@@ 16,6 16,7 @@ ARTS += m4fnmacro.mc
 ARTS += w3m-gemini.mc
 ARTS += zsh-globs.mc
 ARTS += ts-bench.mc
+ARTS += anti-cf.mc
 # EOH
 
 SITES  = about.mc

A anti-cf.mc => anti-cf.mc +55 -0

@@ 0,0 1,55 @@
+<!-- vi: set ft=m4html : -->
+define(`TITLE', `Circumventing Clownflare with w3m')dnl
+define(`DATE', `2024-05-03')dnl
+define(`MODIFIED', `2024-05-03T04:52:52Z')dnl
+define(`LANG', en)dnl
+
+<!DOCTYPE html>
+<html lang="LANG">
+include(head.mc)
+
+<body>
+include(header.mc)
+
+<h1>TITLE</h1>
+<time>DATE</time>
+
+<p>
+<b>Note:</b>
+At the time of publishing this article I did not get blocked anymore.
+</p>
+
+<p>
+Recently Cloudflare started blocking w3m when visiting any site from the StackExchange network.
+This was confirmed by multiple users and happened with w3m on Debian, but not with w3m on OpenBSD.
+</p>
+
+<p>
+Some debugging showed that curl still worked, so I utilized w3m's siteconf and a CGI script to circumvent the blocking.
+</p>
+
+<p>
+The <a href="./assets/anti-cf.cgi">script</a> looks like this:
+<pre><code>`
+#!/bin/sh
+
+# Circumvent Clownfare with curl
+
+# Put this file in one of the configured cgi-bin directories of w3m and make
+# it executable.
+# Add the two next lines your ~/.w3m/siteconf omitting the # at the beginning
+#url m!^https?://stackoverflow.com/!
+#substitute_url "file:///cgi-bin/anti-cf.cgi?"
+#url m!^https?://.*stackexchange.com/!
+#substitute_url "file:///cgi-bin/anti-cf.cgi?"
+
+printf "%s\n\n" "Content-Type: text/html"
+
+url=$(echo $W3M_CURRENT_LINK | sed &apos;s@\(http.\{0,1\}://[^/]*\)/.*@\1@&apos;)
+curl -L ${url}/${QUERY_STRING}
+'</code></pre>
+</p>
+
+include(artfoot.mc)
+</body>
+</html>

A assets/anti-cf.cgi => assets/anti-cf.cgi +16 -0

@@ 0,0 1,16 @@
+#!/bin/sh
+
+# Circumvent Clownfare with curl
+
+# Put this file in one of the configured cgi-bin directories of w3m and make
+# it executable.
+# Add the two next lines your ~/.w3m/siteconf omitting the # at the beginning
+#url m!^https?://stackoverflow.com/!
+#substitute_url "file:///cgi-bin/anti-cf.cgi?"
+#url m!^https?://.*stackexchange.com/!
+#substitute_url "file:///cgi-bin/anti-cf.cgi?"
+
+printf "%s\n\n" "Content-Type: text/html"
+
+url=$(echo $W3M_CURRENT_LINK | sed 's@\(http.\{0,1\}://[^/]*\)/.*@\1@')
+curl -L ${url}/${QUERY_STRING}