%PDF- <> %âãÏÓ endobj 2 0 obj <> endobj 3 0 obj <>/ExtGState<>/ProcSet[/PDF/Text/ImageB/ImageC/ImageI] >>/Annots[ 28 0 R 29 0 R] /MediaBox[ 0 0 595.5 842.25] /Contents 4 0 R/Group<>/Tabs/S>> endobj ºaâÚÎΞ-ÌE1ÍØÄ÷{òò2ÿ ÛÖ^ÔÀá TÎ{¦?§®¥kuµùÕ5sLOšuY>endobj 2 0 obj<>endobj 2 0 obj<>endobj 2 0 obj<>endobj 2 0 obj<> endobj 2 0 obj<>endobj 2 0 obj<>es 3 0 R>> endobj 2 0 obj<> ox[ 0.000000 0.000000 609.600000 935.600000]/Fi endobj 3 0 obj<> endobj 7 1 obj<>/ProcSet[/PDF/Text/ImageB/ImageC/ImageI]>>/Subtype/Form>> stream
#!/usr/bin/perl -w # Shows how to mangle all plain text in an HTML document, using an arbitrary # Perl expression. Plain text is all text not within a tag declaration, i.e. # not in <p ...>, but possibly between <p> and </p> # Example (Reverse 'Debian' in all text) : # lynx -dump -source -raw http://www/debian.org > /tmp/a.txt # ./htextsub '$_ =~ s/Debian/Naibed/gi' /tmp/a.txt use strict; my $code = shift || usage(); $code = 'sub edit_print { local $_ = shift; ' . $code . '; print }'; #print $code; eval $code; die $@ if $@; use HTML::Parser 3.05; my $p = HTML::Parser->new(unbroken_text => 1, default_h => [ sub { print @_; }, "text" ], text_h => [ \&edit_print, "text" ], ); my $file = shift || usage(); $p->parse_file($file) || die "Can't open file $file: $!\n"; sub usage { my $progname = $0; $progname =~ s,^.*/,,; die "Usage: $progname <perlexpr> <filename>\n"; }