Decode HTML in the title using recode (adds recode as a dependency)

1 files changed, 3 insertions, 2 deletions

diff --git a/title.bash b/title.bash
index df06d52..f0065fd 100755
--- a/title.bash
+++ b/title.bash
@@ -18,6 +18,7 @@
 # v0.9.3: advertise text/html acceptance as some servers require it
 # v0.9.4: switch to a cleaner awk script to detect titles
 # v1.0  : if Content-Type is text/plain, just use the first line as the title
+# v1.1  : decode HTML in the title using recode (adds recode as a dependency)
 
 OPTS='--location --insecure --silent --max-filesize 1048576 --max-time 10 -A "Mozilla/5.0 (X11; Linux x86_64; rv:36.0) Gecko/20100101 Firefox/36.0" -H "Accept-Encoding: gzip" -H "Accept: text/html"'
 
@@ -36,7 +37,7 @@ then
   echo "Usage: '!title <url>' where <url> is an http:// or https:// URL"
 elif [ "$url" == "-v" ] || [ "$url" == "--version" ]
 then
-  echo "blatitle version 1.0"
+  echo "blatitle version 1.1"
 else
   eval curl $OPTS -D /tmp/$TIME.header '$url' -o /tmp/$TIME.body.gz
   grep -q "Content-Encoding: gzip" /tmp/$TIME.header && gunzip /tmp/$TIME.body.gz || mv /tmp/$TIME.body.gz /tmp/$TIME.body
@@ -45,7 +46,7 @@ else
   then
     head -n1 /tmp/$TIME.body
   else
-    awk -vRS="</title>" '/<title>/{gsub(/.*<title>|\n+/,"");print;exit}' IGNORECASE=1 /tmp/$TIME.body | sed ':a;N;$!ba;s/\n//g' | sed -e 's/^[ \t]*//'
+    awk -vRS="</title>" '/<title>/{gsub(/.*<title>|\n+/,"");print;exit}' IGNORECASE=1 /tmp/$TIME.body | sed ':a;N;$!ba;s/\n//g' | sed -e 's/^[ \t]*//' | recode html..ascii
   fi
   rm /tmp/$TIME.header /tmp/$TIME.body
 fi