![]() System : Linux absol.cf 5.4.0-198-generic #218-Ubuntu SMP Fri Sep 27 20:18:53 UTC 2024 x86_64 User : www-data ( 33) PHP Version : 7.4.33 Disable Function : pcntl_alarm,pcntl_fork,pcntl_waitpid,pcntl_wait,pcntl_wifexited,pcntl_wifstopped,pcntl_wifsignaled,pcntl_wifcontinued,pcntl_wexitstatus,pcntl_wtermsig,pcntl_wstopsig,pcntl_signal,pcntl_signal_get_handler,pcntl_signal_dispatch,pcntl_get_last_error,pcntl_strerror,pcntl_sigprocmask,pcntl_sigwaitinfo,pcntl_sigtimedwait,pcntl_exec,pcntl_getpriority,pcntl_setpriority,pcntl_async_signals,pcntl_unshare, Directory : /usr/share/doc/libhtml-parser-perl/examples/ |
Upload File : |
#!/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";;