igor@5: #!/usr/bin/perl igor@5: igor@5: igor@6: $regexp=$ARGV[0]; igor@6: $page=$ARGV[1]; igor@5: #if (open(PAGE, "lynx -dump '$page'|")) { igor@5: if (open(PAGE, "$page")) { igor@5: local $/; igor@5: $text=; igor@5: $text =~ s@http://[a-zA-Z&_.:/0-9%?=,\#+()\[\]~-]*@@g; igor@5: $text =~ s@\n@@g; igor@15: $text =~ s@(Mr|Mrs)\.@\1POINT@g; igor@19: @sentences=split /[.!?]/, $text; igor@5: for (@sentences) { igor@15: s@(Mr|Mrs)POINT@\1.@g; igor@5: s/^\s*//; igor@5: s/\s*$//; igor@5: s/\[[0-9]+\]//g; igor@5: s/\s+/ /g; igor@5: print "$_.\n\n" if /\b$regexp\b/; igor@5: } igor@5: }