line |
stmt |
bran |
cond |
sub |
pod |
time |
code |
1
|
1
|
|
|
1
|
|
3264
|
use 5.12.0; |
|
1
|
|
|
|
|
4
|
|
|
1
|
|
|
|
|
70
|
|
2
|
|
|
|
|
|
|
|
3
|
|
|
|
|
|
|
package WebService::LOC::CongRec::Page; |
4
|
|
|
|
|
|
|
our $VERSION = '0.1_04'; |
5
|
1
|
|
|
1
|
|
217
|
use Moose 1.13; |
|
0
|
|
|
|
|
|
|
|
0
|
|
|
|
|
|
|
6
|
|
|
|
|
|
|
with 'MooseX::Log::Log4perl'; |
7
|
|
|
|
|
|
|
|
8
|
|
|
|
|
|
|
use HTML::Strip; |
9
|
|
|
|
|
|
|
use Data::Dumper; |
10
|
|
|
|
|
|
|
|
11
|
|
|
|
|
|
|
=head1 DESCRIPTION |
12
|
|
|
|
|
|
|
|
13
|
|
|
|
|
|
|
A single page from the Congressional Record on THOMAS. |
14
|
|
|
|
|
|
|
|
15
|
|
|
|
|
|
|
The URL is not persistent, but is along the lines of: |
16
|
|
|
|
|
|
|
http://thomas.loc.gov/cgi-bin/query/D?r111:15:./temp/~r111h782Bg:: |
17
|
|
|
|
|
|
|
|
18
|
|
|
|
|
|
|
=cut |
19
|
|
|
|
|
|
|
|
20
|
|
|
|
|
|
|
=head1 ATTRIBUTES |
21
|
|
|
|
|
|
|
|
22
|
|
|
|
|
|
|
=over 1 |
23
|
|
|
|
|
|
|
|
24
|
|
|
|
|
|
|
=item mech |
25
|
|
|
|
|
|
|
|
26
|
|
|
|
|
|
|
A WWW::Mechanize object that we can use to grab the page from Thomas. |
27
|
|
|
|
|
|
|
|
28
|
|
|
|
|
|
|
=cut |
29
|
|
|
|
|
|
|
|
30
|
|
|
|
|
|
|
has 'mech' => ( |
31
|
|
|
|
|
|
|
is => 'rw', |
32
|
|
|
|
|
|
|
isa => 'Object', |
33
|
|
|
|
|
|
|
required => 1, |
34
|
|
|
|
|
|
|
); |
35
|
|
|
|
|
|
|
|
36
|
|
|
|
|
|
|
=item url |
37
|
|
|
|
|
|
|
|
38
|
|
|
|
|
|
|
The page URL. |
39
|
|
|
|
|
|
|
|
40
|
|
|
|
|
|
|
=cut |
41
|
|
|
|
|
|
|
|
42
|
|
|
|
|
|
|
has 'url' => ( |
43
|
|
|
|
|
|
|
is => 'ro', |
44
|
|
|
|
|
|
|
isa => 'Str', |
45
|
|
|
|
|
|
|
required => 1, |
46
|
|
|
|
|
|
|
); |
47
|
|
|
|
|
|
|
|
48
|
|
|
|
|
|
|
=item pageID |
49
|
|
|
|
|
|
|
|
50
|
|
|
|
|
|
|
This page's ID. |
51
|
|
|
|
|
|
|
|
52
|
|
|
|
|
|
|
=cut |
53
|
|
|
|
|
|
|
|
54
|
|
|
|
|
|
|
has 'pageID' => ( |
55
|
|
|
|
|
|
|
is => 'rw', |
56
|
|
|
|
|
|
|
isa => 'Str', |
57
|
|
|
|
|
|
|
); |
58
|
|
|
|
|
|
|
|
59
|
|
|
|
|
|
|
=item summary |
60
|
|
|
|
|
|
|
|
61
|
|
|
|
|
|
|
This page's summary. |
62
|
|
|
|
|
|
|
|
63
|
|
|
|
|
|
|
=cut |
64
|
|
|
|
|
|
|
|
65
|
|
|
|
|
|
|
has 'summary' => ( |
66
|
|
|
|
|
|
|
is => 'rw', |
67
|
|
|
|
|
|
|
isa => 'Str', |
68
|
|
|
|
|
|
|
); |
69
|
|
|
|
|
|
|
|
70
|
|
|
|
|
|
|
=item content |
71
|
|
|
|
|
|
|
|
72
|
|
|
|
|
|
|
This page's content. |
73
|
|
|
|
|
|
|
|
74
|
|
|
|
|
|
|
=cut |
75
|
|
|
|
|
|
|
|
76
|
|
|
|
|
|
|
has 'content' => ( |
77
|
|
|
|
|
|
|
is => 'rw', |
78
|
|
|
|
|
|
|
isa => 'Str', |
79
|
|
|
|
|
|
|
default => '', |
80
|
|
|
|
|
|
|
); |
81
|
|
|
|
|
|
|
|
82
|
|
|
|
|
|
|
=back |
83
|
|
|
|
|
|
|
|
84
|
|
|
|
|
|
|
=cut |
85
|
|
|
|
|
|
|
|
86
|
|
|
|
|
|
|
sub BUILD { |
87
|
|
|
|
|
|
|
my ($self) = @_; |
88
|
|
|
|
|
|
|
|
89
|
|
|
|
|
|
|
my $tagStripper = HTML::Strip->new(); |
90
|
|
|
|
|
|
|
$self->mech->get($self->url); |
91
|
|
|
|
|
|
|
|
92
|
|
|
|
|
|
|
my @lines = split /\n/, $self->mech->content; |
93
|
|
|
|
|
|
|
foreach my $line (@lines) { |
94
|
|
|
|
|
|
|
# Summary line doesn't have a <p> leader |
95
|
|
|
|
|
|
|
if ($line =~ m!^<b>(.+)</b><br/>!) { |
96
|
|
|
|
|
|
|
$self->summary($1); |
97
|
|
|
|
|
|
|
next; |
98
|
|
|
|
|
|
|
} |
99
|
|
|
|
|
|
|
|
100
|
|
|
|
|
|
|
next if ($line !~ /^<p>/ || $line =~ /^<p>---/); |
101
|
|
|
|
|
|
|
|
102
|
|
|
|
|
|
|
# Page ID |
103
|
|
|
|
|
|
|
if ($line =~ m!^<p><center><pre>\[Page: ([HSE]\d{1,6})\] <b>!) { |
104
|
|
|
|
|
|
|
$self->pageID($1); |
105
|
|
|
|
|
|
|
next; |
106
|
|
|
|
|
|
|
} |
107
|
|
|
|
|
|
|
|
108
|
|
|
|
|
|
|
# Line of actual content |
109
|
|
|
|
|
|
|
if ($line =~ m/^<p>(.*)$/) { |
110
|
|
|
|
|
|
|
my $text = $tagStripper->parse($1) . "\n"; |
111
|
|
|
|
|
|
|
|
112
|
|
|
|
|
|
|
# Strip non-breaking spaces |
113
|
|
|
|
|
|
|
$text =~ s/\xA0//g; |
114
|
|
|
|
|
|
|
|
115
|
|
|
|
|
|
|
$self->content($self->content . $text); |
116
|
|
|
|
|
|
|
|
117
|
|
|
|
|
|
|
$tagStripper->eof(); |
118
|
|
|
|
|
|
|
} |
119
|
|
|
|
|
|
|
} |
120
|
|
|
|
|
|
|
} |
121
|
|
|
|
|
|
|
|
122
|
|
|
|
|
|
|
1; |