Replace title header extraction method with one that doesn't care about attributes inside the opening tag

1 files changed, 1 insertions, 2 deletions

diff --git a/title.bash b/title.bash
index 8ad7705..988f544 100755
--- a/title.bash
+++ b/title.bash
@@ -74,8 +74,7 @@ else
   then
     grep -m1 . /tmp/$TIME.body
   else
-    awk -vRS="</title>" '/<title>/{gsub(/.*<title>|\n+/,"");print;exit}' IGNORECASE=1 /tmp/$TIME.body | sed ':a;N;$!ba;s/\n//g' \
-      | sed -e 's/^[ \t]*//' | php -r 'while(($line=fgets(STDIN)) !== FALSE) echo html_entity_decode($line, ENT_QUOTES|ENT_HTML401);'
+    cat /tmp/$TIME.body | tr '\n' ' ' | tr '\r' ' ' | grep -oiE '<title.*>.*</title>' | sed -r 's/<title[^>]*//I; s/^>//I; s/<\/title>$//I' | php -r 'while(($line=fgets(STDIN)) !== FALSE) echo html_entity_decode($line, ENT_QUOTES|ENT_HTML401);'
   fi
   rm /tmp/$TIME.header /tmp/$TIME.body
 fi