~vanvugt/ubuntu/oneiric/mediatomb/fix-770964-784431

« back to all changes in this revision

Viewing changes to scripts/readme_xhtml_div_extract.pl

• browse files at revision 1.1.2
• compare with another revision
• download diff
• download tarball
• view history from revision 1.1.2

Show diffs side-by-side

added

removed

scripts/readme_xhtml_div_extract.pl

 

1

#!/usr/bin/perl

 

2

 

 

3

use XML::DOM;

 

4

use XML::XQL;

 

5

use XML::XQL::DOM;

 

6

 

 

7

 

 

8

#binmode STDOUT, ":utf8";

 

9

 

 

10

sub my_tag_compression

 

11

{

 

12

    my ($tag, $elem) = @_;

 

13

    

 

14

    # Print empty br, hr and img tags like this: <br />

 

15

    return 2 if $tag =~ /^(br|hr|img)$/;

 

16

    

 

17

    # Print other empty tags like this: <empty></empty>

 

18

    return 1;

 

19

}

 

20

 

 

21

XML::DOM::setTagCompression (\&my_tag_compression);

 

22

 

 

23

my $parser = new XML::DOM::Parser;

 

24

#my $doc = $parser->parsefile ("readme.html");

 

25

my $doc = $parser->parse(\*STDIN);

 

26

 

 

27

my @res = $doc->xql('//div[h2/@class="title"]');

 

28

if (! @res)

 

29

{

 

30

    @res = $doc->xql('//div[h1/@class="title"]');

 

31

}

 

32

 

 

33

$res[0]->getParentNode()->removeChild($res[0]);

 

34

 

 

35

@res = $doc->xql("/html/body/div/*");

 

36

 

 

37

foreach (@res)

 

38

{

 

39

    print $_->toString();

 

40

}

• Older »

Loggerhead is a web-based interface for Breezy
Version: 2.0.1