Last active
August 29, 2015 14:14
-
-
Save paveljurca/1ecb3439cfca31784432 to your computer and use it in GitHub Desktop.
Právě půjčeno | Městská knihovna v Praze /* SKRIPT PRO UCHOVÁNÍ SI PŘEHLEDU O KNIŽNÍCH VÝPŮJČKÁCH */
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/env perl | |
use strict; | |
use warnings; | |
use open qw(:std :utf8); | |
use utf8; | |
################################# | |
# EXAMPLE # | |
# http://jurcapavel.cz/books.pl # | |
################################# | |
# SOURCE => https://www.mlp.cz/cz/moje-knihovna/moje-knihy/prave-pujceno/ | |
@ARGV = q[ Právě půjčeno | Městská knihovna v Praze.html ]; | |
my %books; | |
while (<>) { | |
if (/col1">([^<]+)/) { | |
#table heading row | |
next if $1 eq "Název knihy"; | |
my $book = $1; | |
my($surname,$forename) = <> =~ />([^,]+,\s)(.)/; | |
# key => $books{'Čapek, K.'} | |
$books{"\u\L$surname\U$forename."} .= "$book\n"; | |
} | |
} | |
for my $author (sort keys %books) { | |
print "$author: $_\n" for (split /\n/, $books{$author}); | |
} |
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/env perl | |
use strict; | |
use warnings; | |
use 5.010; | |
use utf8; | |
# http://search.mlp.cz/?action=cdqc&espQCId=tov-ctenar-seznamy&callback=myCallbackFunction&phase=open&lbparam=open&name=NAZEV_SEZNAMU | |
# w3m search.mlp.cz.html -dump -cols 200 > input.txt | |
open (my $fh, '<:encoding(UTF-8)', 'input.txt') or die; | |
my %books; | |
while (<$fh>) { | |
chomp; | |
m/^(.{53})(.{59})/; | |
my $c = $2; | |
my $d = $1; | |
$c =~ s/^\s+|\s+$//g; | |
$d =~ s/^\s+|\s+$//g; | |
$books{"$c"} .= "$d\n" ; | |
} | |
my @c; | |
my @d; | |
my $record; | |
my $l; | |
close($fh); | |
open ($fh, '>:encoding(UTF-8)', 'books.txt') or die; | |
foreach my $author (sort keys %books) { | |
@c = split /\s/, $author; | |
@d = split /\n/, $books{$author}; | |
$record = pop @c; | |
foreach (@c) { | |
$l = length($_) - 1; | |
s/.{$l}$/\./; | |
} | |
$" = ""; | |
$record .= ", @c: "; | |
say $fh "${record}$_\n" foreach @d; | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment