Created
May 4, 2022 15:09
-
-
Save ace411/6b515bbe0eb3d41841a9598c8063cb0d to your computer and use it in GitHub Desktop.
Web Scraping with Perl
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/perl -w | |
use 5.30.0; | |
use LWP::UserAgent; | |
use HTML::TreeBuilder; | |
use HTML::FormatText; | |
use HTML::Element; | |
use Encode; | |
use warnings; | |
use open qw(:std :utf8); | |
if ($#ARGV + 1 != 1) { | |
die "Please provide song input\n"; | |
} | |
my $ua = LWP::UserAgent->new; | |
$ua->agent("Genius Scraper"); | |
my $url = "https://genius.com/$ARGV[0]"; | |
my $formatter = HTML::FormatText->new(leftmargin => 0, rightmargin => 50); | |
my $root = HTML::TreeBuilder->new(); | |
my $request = $ua->get($url) or die "Cannot contact Genius $!\n"; | |
if ($request->is_success) { | |
$root->parse(decode_utf8 $request->content); | |
my $data = $root->look_down( | |
_tag => "div", | |
id => "lyrics-root" | |
); | |
say $formatter->format($data); | |
} else { | |
print "Cannot display the lyrics.\n"; | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment