%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 # Extract all plain text from an HTML file use strict; use HTML::Parser 3.00 (); use Encode; my %inside; sub tag { my($tag, $num) = @_; $inside{$tag} += $num; print " "; # not for all tags } sub text { return if $inside{script} || $inside{style}; print encode('utf8',$_[0]); } HTML::Parser->new(api_version => 3, handlers => [start => [\&tag, "tagname, '+1'"], end => [\&tag, "tagname, '-1'"], text => [\&text, "dtext"], ], marked_sections => 1, )->parse_file(shift) || die "Can't open file: $!\n";;