use Mojo::Base -strict; use 5.014; use Mojo::UserAgent; use Mojo::DOM; use Mojo::Util qw/dumper/; package Mojo::DOM::Role::TreeWalker { use Mojo::Base -strict; use Role::Tiny; use Mojo::Collection; sub walk { $_[0]->_walk($_[1], 0) || Mojo::Collection->new } sub _walk { my ($self, $cb, $depth) = @_; my $c = Mojo::Collection->new; { local $_ = $self; push @$c, $cb->($self, $depth++); } my $rv = $self->child_nodes->map('_walk', $cb, $depth); push @$c, $rv if @$rv; @$c ? $c : (); } sub walk_text { my ($self, $cb) = @_; $self->walk(sub { $_->type eq 'cdata' || $_->type eq 'raw' || $_->type eq 'text' ? $cb->(@_) : () }); } } my $ua = Mojo::UserAgent->new( max_redirects => 3 ); my $res = $ua->get('http://www.spacex.com/webcast')->result; die $res->message unless $res->is_success; my $dom = $res->dom; $dom->find('script, style')->map('remove'); my $texts = $dom->with_roles('+TreeWalker')->walk_text(sub { $_->content=~/\S/ ? $_->content=~s/^\s+|\s+$//gr : () })->flatten; print dumper $texts; __END__ bless( [ "STARLINK MISSION | SpaceX", "Jump to navigation", "Falcon 9", "Falcon Heavy", "Dragon", "Starship", "Updates", "About SpaceX", "Careers", "Shop", "You are here", "Home", "STARLINK MISSION", "On Wednesday, April 22 at 3:30 p.m. EDT, or 19:30 p.m. UTC, SpaceX launched its seventh Starlink mission. Falcon 9 lifted off from Launch Complex 39A (LC-39A) at NASA\x{2019}s Kennedy Space Center in Florida.", "Falcon 9\x{2019}s first stage previously supported Crew Dragon\x{2019}s first flight to the International Space Station, launch of the RADARSAT Constellation Mission, and the fourth Starlink mission. Following stage separation, SpaceX landed Falcon 9\x{2019}s first stage on the \x{201c}Of Course I Still Love You\x{201d} droneship, which was stationed in the Atlantic Ocean. Falcon 9\x{2019}s fairing previously supported the AMOS-17 mission.", "You can watch a replay of the launch below and learn more about the mission", "here.", "|", "Twitter", "YouTube", "Flickr", "Instagram", "Privacy", "\x{a9} 2020 Space Exploration Technologies Corp." ], 'Mojo::Collection' )