qbit/werc
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Much better (I hope) get_html_title implementation, first try to find <title>, if that fails, get the first non-tag string in the file.

Browse Source
This commit is contained in:
uriel 2009-07-30 02:12:06 +02:00
parent a188daebdc
commit e4424e0844
1 changed files with 7 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
bin/werclib.rc
View File

@ -98,12 +98,13 @@ fn get_md_title {
}
fn get_html_title {
# H1 is not reliable because htmlroff doesn't use it :(
#desc=`{cat $1 | sed 32q | grep '<[Hh]1>' | sed 's/<[Hh]1>(.*)(<\/[Hh]1>|$)/\1/;s/<[^>]*>//g;1q'}
# Pick the first line of body instead
desc=`{sed -n '/<[Bb][Oo][Dd][Yy]/,/./s/(<[^>]*>|$)//gp' < $1}
if(~ $#desc 0)
desc=`{sed 's/<[^>]*>//g; 1q' < $1}
t=`{sed -n '32q; s/^.*<[Tt][Ii][Tt][Ll][Ee]> *([^<]+) *(<\/[Tt][Ii][Tt][Ll][Ee]>.*)?$/\1/p' < $1}
# As a backup we might want to pick the first 'non-tag' text in the file with:
if(~ $"t '')
t=`{sed -n -e 's/^(<[^>]+>)*([^<]+).*/\2/p; 32q' < $1 | sed 1q}
echo $t
}
fn get_file_title {