| line |
stmt |
bran |
cond |
sub |
pod |
time |
code |
|
1
|
|
|
|
|
|
|
package Podcast::ESLPodcast::Splitter; |
|
2
|
|
|
|
|
|
|
|
|
3
|
1
|
|
|
1
|
|
64464
|
use warnings; |
|
|
1
|
|
|
|
|
2
|
|
|
|
1
|
|
|
|
|
27
|
|
|
4
|
1
|
|
|
1
|
|
5
|
use strict; |
|
|
1
|
|
|
|
|
1
|
|
|
|
1
|
|
|
|
|
30
|
|
|
5
|
1
|
|
|
1
|
|
4
|
use Carp; |
|
|
1
|
|
|
|
|
5
|
|
|
|
1
|
|
|
|
|
79
|
|
|
6
|
|
|
|
|
|
|
|
|
7
|
1
|
|
|
1
|
|
951
|
use LWP::UserAgent; |
|
|
1
|
|
|
|
|
86928
|
|
|
|
1
|
|
|
|
|
43
|
|
|
8
|
1
|
|
|
1
|
|
12
|
use File::Basename; |
|
|
1
|
|
|
|
|
3
|
|
|
|
1
|
|
|
|
|
137
|
|
|
9
|
1
|
|
|
1
|
|
446
|
use XML::FeedPP; |
|
|
0
|
|
|
|
|
|
|
|
|
0
|
|
|
|
|
|
|
|
10
|
|
|
|
|
|
|
use MP3::Splitter; |
|
11
|
|
|
|
|
|
|
use Data::Dumper; |
|
12
|
|
|
|
|
|
|
use Time::Piece; |
|
13
|
|
|
|
|
|
|
use List::MoreUtils qw(any all); |
|
14
|
|
|
|
|
|
|
|
|
15
|
|
|
|
|
|
|
use version; our $VERSION = qv('0.0.1'); |
|
16
|
|
|
|
|
|
|
|
|
17
|
|
|
|
|
|
|
use constant FEEDURI => |
|
18
|
|
|
|
|
|
|
'http://feeds.feedburner.com/EnglishAsASecondLanguagePodcast?format=xml'; |
|
19
|
|
|
|
|
|
|
|
|
20
|
|
|
|
|
|
|
# constructor |
|
21
|
|
|
|
|
|
|
sub new { |
|
22
|
|
|
|
|
|
|
my ( $class, @args ) = @_; |
|
23
|
|
|
|
|
|
|
my %args = ref $args[0] eq 'HASH' ? %{ $args[0] } : @args; |
|
24
|
|
|
|
|
|
|
my $self = {%args}; |
|
25
|
|
|
|
|
|
|
$self->{n} ||= 5; |
|
26
|
|
|
|
|
|
|
bless $self, $class; |
|
27
|
|
|
|
|
|
|
} |
|
28
|
|
|
|
|
|
|
|
|
29
|
|
|
|
|
|
|
# fetch a feed information for the ESLPodcast |
|
30
|
|
|
|
|
|
|
sub fetch_feed { |
|
31
|
|
|
|
|
|
|
my $feed = XML::FeedPP->new(FEEDURI); |
|
32
|
|
|
|
|
|
|
printf STDERR "===============FEED INFO================\n"; |
|
33
|
|
|
|
|
|
|
printf STDERR "Title: %s\n", $feed->title; |
|
34
|
|
|
|
|
|
|
printf STDERR "Date: %s\n", $feed->pubDate; |
|
35
|
|
|
|
|
|
|
printf STDERR "Copyright: %s\n", $feed->copyright; |
|
36
|
|
|
|
|
|
|
printf STDERR "Link: %s\n", $feed->link; |
|
37
|
|
|
|
|
|
|
printf STDERR "Language: %s\n", $feed->language; |
|
38
|
|
|
|
|
|
|
printf STDERR "========================================\n"; |
|
39
|
|
|
|
|
|
|
return $feed; |
|
40
|
|
|
|
|
|
|
} |
|
41
|
|
|
|
|
|
|
|
|
42
|
|
|
|
|
|
|
sub run { |
|
43
|
|
|
|
|
|
|
my $self = shift; |
|
44
|
|
|
|
|
|
|
my $feed = fetch_feed(); |
|
45
|
|
|
|
|
|
|
my $num_mp3s = 1; |
|
46
|
|
|
|
|
|
|
for my $item ( $feed->get_item() ) { |
|
47
|
|
|
|
|
|
|
if ( $item->title =~ /English Cafe/ ) { |
|
48
|
|
|
|
|
|
|
printf STDERR "skip: %s\n", $item->title; |
|
49
|
|
|
|
|
|
|
next; |
|
50
|
|
|
|
|
|
|
} |
|
51
|
|
|
|
|
|
|
last if ( $num_mp3s > $self->{n} ); |
|
52
|
|
|
|
|
|
|
|
|
53
|
|
|
|
|
|
|
printf STDERR "\tURL: %s\n\tTitle: %s\n\tguid: %s\n\tDescription: %s\n", |
|
54
|
|
|
|
|
|
|
$item->link, $item->title, $item->guid, ""; # $item->description; |
|
55
|
|
|
|
|
|
|
|
|
56
|
|
|
|
|
|
|
my $durations = extract_durations( $item->description ); |
|
57
|
|
|
|
|
|
|
next if ( !$durations ); |
|
58
|
|
|
|
|
|
|
|
|
59
|
|
|
|
|
|
|
my $uri = $item->guid(); |
|
60
|
|
|
|
|
|
|
my $mp3_file = basename($uri); |
|
61
|
|
|
|
|
|
|
if ( !download_mp3( \$uri, \$mp3_file ) ) { |
|
62
|
|
|
|
|
|
|
printf STDERR "download failure: %s\n", $mp3_file; |
|
63
|
|
|
|
|
|
|
next; |
|
64
|
|
|
|
|
|
|
} |
|
65
|
|
|
|
|
|
|
if ( split_mp3( \$mp3_file, $durations ) ) { |
|
66
|
|
|
|
|
|
|
printf STDERR "split failure: %s\n", $mp3_file; |
|
67
|
|
|
|
|
|
|
} |
|
68
|
|
|
|
|
|
|
|
|
69
|
|
|
|
|
|
|
++$num_mp3s; |
|
70
|
|
|
|
|
|
|
} |
|
71
|
|
|
|
|
|
|
printf STDERR "DONE!"; |
|
72
|
|
|
|
|
|
|
} |
|
73
|
|
|
|
|
|
|
|
|
74
|
|
|
|
|
|
|
# extract durations for each dialog |
|
75
|
|
|
|
|
|
|
sub extract_durations { |
|
76
|
|
|
|
|
|
|
my ($desc) = @_; |
|
77
|
|
|
|
|
|
|
|
|
78
|
|
|
|
|
|
|
# find started at |
|
79
|
|
|
|
|
|
|
my $started_at = { slow => undef, explanation => undef, fast => undef }; |
|
80
|
|
|
|
|
|
|
for ( split( /[\n|\r\n]/, $desc ) ) { |
|
81
|
|
|
|
|
|
|
chomp; |
|
82
|
|
|
|
|
|
|
if (/Slow (dialog|dialogue):\s*(\d+:\d+)/) { |
|
83
|
|
|
|
|
|
|
$started_at->{slow} = $2; |
|
84
|
|
|
|
|
|
|
} |
|
85
|
|
|
|
|
|
|
if (/Explanations:\s*(\d+:\d+)/) { |
|
86
|
|
|
|
|
|
|
$started_at->{explanation} = $1; |
|
87
|
|
|
|
|
|
|
} |
|
88
|
|
|
|
|
|
|
if (/Fast (dialog|dialogue):\s*(\d+:\d+)/) { |
|
89
|
|
|
|
|
|
|
$started_at->{fast} = $2; |
|
90
|
|
|
|
|
|
|
} |
|
91
|
|
|
|
|
|
|
} |
|
92
|
|
|
|
|
|
|
|
|
93
|
|
|
|
|
|
|
# print Dumper($started_at); |
|
94
|
|
|
|
|
|
|
if ( !( all { defined($_) } values %$started_at ) ) { |
|
95
|
|
|
|
|
|
|
printf STDERR "something wrong in this feed\n"; |
|
96
|
|
|
|
|
|
|
return 0; |
|
97
|
|
|
|
|
|
|
} |
|
98
|
|
|
|
|
|
|
|
|
99
|
|
|
|
|
|
|
# find durations |
|
100
|
|
|
|
|
|
|
my $durations = { slow => undef, explanation => undef, fast => undef }; |
|
101
|
|
|
|
|
|
|
$durations->{slow} = [ |
|
102
|
|
|
|
|
|
|
$started_at->{slow}, |
|
103
|
|
|
|
|
|
|
find_duration( $started_at->{explanation}, $started_at->{slow} ) |
|
104
|
|
|
|
|
|
|
]; |
|
105
|
|
|
|
|
|
|
$durations->{explanation} = [ |
|
106
|
|
|
|
|
|
|
$started_at->{explanation}, |
|
107
|
|
|
|
|
|
|
find_duration( $started_at->{fast}, $started_at->{explanation} ) |
|
108
|
|
|
|
|
|
|
]; |
|
109
|
|
|
|
|
|
|
$durations->{fast} = [ $started_at->{fast}, "=INF" ]; |
|
110
|
|
|
|
|
|
|
return $durations; |
|
111
|
|
|
|
|
|
|
} |
|
112
|
|
|
|
|
|
|
|
|
113
|
|
|
|
|
|
|
# find a duration |
|
114
|
|
|
|
|
|
|
sub find_duration { |
|
115
|
|
|
|
|
|
|
my ( $from, $to ) = @_; |
|
116
|
|
|
|
|
|
|
my $t1 = Time::Piece->strptime( $from, "%M:%S" ); |
|
117
|
|
|
|
|
|
|
my $t2 = Time::Piece->strptime( $to, "%M:%S" ); |
|
118
|
|
|
|
|
|
|
my $diff = $t2 - $t1; |
|
119
|
|
|
|
|
|
|
return $diff->seconds; |
|
120
|
|
|
|
|
|
|
} |
|
121
|
|
|
|
|
|
|
|
|
122
|
|
|
|
|
|
|
# split a mp3 file into three files |
|
123
|
|
|
|
|
|
|
sub split_mp3 { |
|
124
|
|
|
|
|
|
|
my ( $mp3_file, $durations ) = @_; |
|
125
|
|
|
|
|
|
|
mp3split( |
|
126
|
|
|
|
|
|
|
$$mp3_file, { verbose => 1 }, |
|
127
|
|
|
|
|
|
|
$durations->{start}, $durations->{explanation}, |
|
128
|
|
|
|
|
|
|
$durations->{fast} |
|
129
|
|
|
|
|
|
|
); |
|
130
|
|
|
|
|
|
|
return 1; |
|
131
|
|
|
|
|
|
|
} |
|
132
|
|
|
|
|
|
|
|
|
133
|
|
|
|
|
|
|
# download a mp3 file |
|
134
|
|
|
|
|
|
|
sub download_mp3 { |
|
135
|
|
|
|
|
|
|
my ( $uri, $mp3_file ) = @_; |
|
136
|
|
|
|
|
|
|
open( my $fh, '>', $$mp3_file ) or die "$$mp3_file: $!"; |
|
137
|
|
|
|
|
|
|
my $res = LWP::UserAgent->new->get( |
|
138
|
|
|
|
|
|
|
$$uri, |
|
139
|
|
|
|
|
|
|
':content_cb' => sub { |
|
140
|
|
|
|
|
|
|
my ( $chunk, $res, $proto ) = @_; |
|
141
|
|
|
|
|
|
|
print $fh $chunk; |
|
142
|
|
|
|
|
|
|
my $size = tell $fh; |
|
143
|
|
|
|
|
|
|
if ( my $total = $res->header('Content-Length') ) { |
|
144
|
|
|
|
|
|
|
printf "%d/%d (%f%%)\r", $size, $total, $size / $total * 100; |
|
145
|
|
|
|
|
|
|
} |
|
146
|
|
|
|
|
|
|
else { |
|
147
|
|
|
|
|
|
|
printf "%d/Unknown bytes\r", $size; |
|
148
|
|
|
|
|
|
|
} |
|
149
|
|
|
|
|
|
|
} |
|
150
|
|
|
|
|
|
|
); |
|
151
|
|
|
|
|
|
|
close $fh; |
|
152
|
|
|
|
|
|
|
print "\n", $res->status_line, "\n"; |
|
153
|
|
|
|
|
|
|
unlink $$mp3_file if ( !$res->is_success ); |
|
154
|
|
|
|
|
|
|
return $res->is_success; |
|
155
|
|
|
|
|
|
|
} |
|
156
|
|
|
|
|
|
|
|
|
157
|
|
|
|
|
|
|
1; # Magic true value required at end of module |
|
158
|
|
|
|
|
|
|
__END__ |