kimmel

#!/usr/bin/perl

use v5.16;
use warnings;
use autodie qw( :all );
use utf8::all;
use List::MoreUtils qw( uniq any );
use Benchmark qw( cmpthese :hireswallclock );

my %file_names = ();

kimmel

#!/usr/bin/perl

use v5.14;
use warnings;
use utf8::all;
use File::Slurp qw( read_file );

my $pattern_list = do 'fw.pl';
my @patterns = keys $pattern_list;
my $content = read_file( 'dracula.txt' );

kimmel

#!/usr/bin/perl

use v5.14;
use warnings;
use utf8::all;
use File::Slurp qw( read_file );

my $pattern_list = do 'fw.pl';
my @patterns = keys $pattern_list;
my $content = read_file( 'dracula.txt' );

kimmel

#!/usr/bin/perl

use v5.14;
use warnings;
use utf8::all;
use File::Slurp qw( read_file );

...

my @patterns = map {qr/\b$_\b/ixms} keys $pattern_list;

kimmel

#!/usr/bin/perl

use v5.14;
use warnings;
use utf8::all;
use List::Util qw( reduce );
use List::MoreUtils qw( uniq any );
use Path::Class::Rule;
use File::Slurp qw( read_file );

kimmel

#!/usr/bin/perl

use v5.14;
use warnings;
use utf8::all;
use Encode;
use Data::Dumper;
use JSON::XS qw( decode_json );

my $wl = '{"creche":"crèche", "¥":"£", "₡":"волн"}';

kimmel

        $html =~ m{
>\s*$num\.</td>\s*<td>\s*<center>\s*<a\s+id=up_
(\d+) # $1 -> id
\s+href="vote\?for=\g1&dir=up&whence=[%a-e0-9]+">\s*<img\s+src="http://yc
ombinator\.com/images/grayarrow\.gif"\s+border=\d+\s+vspace=\d+\s+hspace=
\d+>\s*</a>\s*<span\s+id=down_\g1>\s*</span>\s*</center>\s*</td>\s*<td\s+
class="title">\s*<a\s+href="
([^"]+) # $2 -> uri
">
([^<]+) # $3 -> desc

kimmel

 locatestarttagend = re.compile(r"""
<[a-zA-Z][-.a-zA-Z0-9:_]* # tag name
(?:[\s/]* # optional whitespace before attribute name
(?:(?<=['"\s/])[^\s/>][^\s/=>]* # attribute name
(?:\s*=+\s* # value indicator
(?:'[^']*' # LITA-enclosed value
|"[^"]*" # LIT-enclosed value
|(?!['"])[^>\s]* # bare value
)
)?(?:\s|/(?!>))*

kimmel

 # Methods for supporting CSS selectors.

    tag_name_re = re.compile('^[a-z0-9]+$')

    # /^(\w+)\[(\w+)([=~\|\^\$\*]?)=?"?([^\]"]*)"?\]$/
    #   \---/  \---/\-------------/    \-------/
    #     |      |         |               |
    #     |      |         |           The value
    #     |      |    ~,|,^,$,* or =
    #     |   Attribute

kimmel

from datetime import datetime
import BeautifulSoup as soup
import requests

...

r = requests.get(host + page)
        doc = soup.BeautifulSoup(r.content)
        titles = doc.table.findAll(True, {'class': 'title'})