#! /bin/ksh

# Get web links for the genealogy web site

# written by John Guest June 20, 1997

files=`ls *.html`

# extract http links
#for file in "index.html" 
for file in $files
do
    print "processing $file ..."
    print "processing $file ..." >>href.log
    awk '
        BEGIN{ 
                FS="\""
        } 
        /telnet:/ {
                for (i=1;i<=NF;i++) {
                        n = index($i,"</a>")
                        n += index($i,"</A>")
                        n += index($i,"<BR>")
                        if ( (substr($i,1,6) == "telnet") && n == 0) { 
                                split($i,x," ")
                                print x[1]
                        }
                }
        }
        /gopher:/ {
                for (i=1;i<=NF;i++) {
                        n = index($i,"</a>")
                        n += index($i,"</A>")
                        n += index($i,"<BR>")
                        if ( substr($i,1,6) == "gopher" && n == 0 ) {
                                split($i,o," ")
                                print o[1]
                        }
                }
        }
        /ftp:/ {
                for (i=1;i<=NF;i++) {
                        n = index($i,"</a>")
                        n += index($i,"</A>")
                        n += index($i,"<BR>")
                        if ( substr($i,1,3) == "ftp" && n == 0 ) {
                                split($i,o," ")
                                print o[1]
                        }
                }
        }
        /http:/ {
                for (i=1;i<=NF;i++) {
                        n = index($i,"</a>")
                        n += index($i,"</A>")
                        n += index($i,"<BR>")
                        if ( substr($i,1,4) == "http" && n == 0 ) {
                                split($i,o," ")
                                print o[1]
                        }
                }
        }' <$file >>html.list

done