s they ## contain. This is so I can get recursive list and know what ## stuff is by what title and name it is. ## ###################################################################### # # # I'm not sure if I just want to work # from the text directory or not. This would # be the code to do just that. Hrm... # do I really want them to have to download all the # gifs or not? Hey...I'll do this, I'll let them # /choose/ whether or not they wanna download # the pictures or not, so there! # Even though this does make my job harder... # ###################################################################### ## ## sub fileadd ## ## This subroutine extracts a filename a title from the file ## and puts it in nn_file ###################################################################### sub fileadd { #print LOGFILE "contains: @_\n"; $htmlfile = $_[0]; #print "I'm working on $htmlfile\n"; open (HTMLFILE, "<$htmlfile"); while( <HTMLFILE> ) { chop; # # determine whether we are in multiline status # if ($multiLine == 1) { $titlestring = $titlestring ." ". $_; if (/>/) { $multiLine = 0; $foundit = 0; } next; } # # find <title> statements! # if (/<title/i) { $foundit =1; if ( !/<title>*<\/title>/i) { # Time to cat a multi line string! $multiLine =+ 1; $titlestring = $_; } } elsif ($multiLine == 0) # not dealing with an img statement { #print LOGFILE "$_\n"; if ( $foundit == 1 ) { print NN_FILE "$_\n"; } } else { #$multiLine--; } # # don't print out the line if it's not a title # if ( $foundit == 1 ) { # # remove unwanted frills from our title # $titlestring =~ s/<head>//ig; $titlestring =~ s/<\/head>//ig; $titlestring =~ s/<html>//ig; $titlestring =~ s/<\/html>//ig; $titlestring =~ s/<body>//ig; $titlestring =~ s/<\/body>//ig; $titlestring =~ s/<title>//ig; $titlestring =~ s/<\/title>//ig; $titlestring =~ s/^\W*//; # remove starting whitespace $titlestring =~ s/\W*$//; # remove ending whitespace # figure out "a nice format" $centering = 42 - length( $titlestring ); $padding = " " x $centering; $outline = $titlestring . ":" . $padding . $workingdir . "/" . $htmlfile . "\n"; print NN_FILE "$outline"; } # end of if foundit } # end of fucknob close HTMLFILE; } # end of do_file ###################################################################### ## ## main script ## ###################################################################### # open a logfile, tempfile, and final file open(LOGFILE, ">listmake.log") || die "Can't open logfile.\n"; open (NN_FILE, ">listmake.out") || die "Can't open nn.file.\n"; $basedirectory =`pwd`; chop $basedirectory; print LOGFILE "STARTING OFF IN: $basedirectory\n"; foreach ( `du` ) { chdir ($basedirectory); chop; s/.*\s+//i; s/$basedirectory//i; # # skip any non-text directories # if (!/.*text.*/) { print LOGFILE "Skipping non-TEXT dir.\n"; next; } print LOGFILE " ENTERING $_ \n"; $workingdir = $_; chdir( $_ ); # # for each *.html file # while ( $htmlfile = <*.html> ) { $tallyfiles++; print LOGFILE "$htmlfile, "; do fileadd($htmlfile); } # end of while each *.html print LOGFILE "\n"; } # end foreach du print "Processed $tallyfiles files.\n"; close (NN

#!/usr/bin/perl ###################################################################### ## ## listmake ::: Jed Reynolds ::: Nov 23, 1995 ## ## This is a silly li'l program which makes a list of a source ## tree and compiles a list of filenames and html s they ## contain. This is so I can get recursive list and know what ## stuff is by what title and name it is. ## ###################################################################### # # # I'm not sure if I just want to work # from the text directory or not. This would # be the code to do just that. Hrm... # do I really want them to have to download all the # gifs or not? Hey...I'll do this, I'll let them # /choose/ whether or not they wanna download # the pictures or not, so there! # Even though this does make my job harder... # ###################################################################### ## ## sub fileadd ## ## This subroutine extracts a filename a title from the file ## and puts it in nn_file ###################################################################### sub fileadd { #print LOGFILE "contains: @_\n"; $htmlfile = $_[0]; #print "I'm working on $htmlfile\n"; open (HTMLFILE, "<$htmlfile"); while( <HTMLFILE> ) { chop; # # determine whether we are in multiline status # if ($multiLine == 1) { $titlestring = $titlestring ." ". $_; if (/>/) { $multiLine = 0; $foundit = 0; } next; } # # find <title> statements! # if (/<title/i) { $foundit =1; if ( !/<title>*<\/title>/i) { # Time to cat a multi line string! $multiLine =+ 1; $titlestring = $_; } } elsif ($multiLine == 0) # not dealing with an img statement { #print LOGFILE "$_\n"; if ( $foundit == 1 ) { print NN_FILE "$_\n"; } } else { #$multiLine--; } # # don't print out the line if it's not a title # if ( $foundit == 1 ) { # # remove unwanted frills from our title # $titlestring =~ s/<head>//ig; $titlestring =~ s/<\/head>//ig; $titlestring =~ s/<html>//ig; $titlestring =~ s/<\/html>//ig; $titlestring =~ s/<body>//ig; $titlestring =~ s/<\/body>//ig; $titlestring =~ s/<title>//ig; $titlestring =~ s/<\/title>//ig; $titlestring =~ s/^\W*//; # remove starting whitespace $titlestring =~ s/\W*$//; # remove ending whitespace # figure out "a nice format" $centering = 42 - length( $titlestring ); $padding = " " x $centering; $outline = $titlestring . ":" . $padding . $workingdir . "/" . $htmlfile . "\n"; print NN_FILE "$outline"; } # end of if foundit } # end of fucknob close HTMLFILE; } # end of do_file ###################################################################### ## ## main script ## ###################################################################### # open a logfile, tempfile, and final file open(LOGFILE, ">listmake.log") || die "Can't open logfile.\n"; open (NN_FILE, ">listmake.out") || die "Can't open nn.file.\n"; $basedirectory =`pwd`; chop $basedirectory; print LOGFILE "STARTING OFF IN: $basedirectory\n"; foreach ( `du` ) { chdir ($basedirectory); chop; s/.*\s+//i; s/$basedirectory//i; # # skip any non-text directories # if (!/.*text.*/) { print LOGFILE "Skipping non-TEXT dir.\n"; next; } print LOGFILE " ENTERING $_ \n"; $workingdir = $_; chdir( $_ ); # # for each *.html file # while ( $htmlfile = <*.html> ) { $tallyfiles++; print LOGFILE "$htmlfile, "; do fileadd($htmlfile); } # end of while each *.html print LOGFILE "\n"; } # end foreach du print "Processed $tallyfiles files.\n"; close (NN_FILE); close (LOGFILE); # eof #