| line |
stmt |
bran |
cond |
sub |
pod |
time |
code |
|
1
|
|
|
|
|
|
|
package Mojolicious::Plugin::IsBot; |
|
2
|
|
|
|
|
|
|
|
|
3
|
1
|
|
|
1
|
|
611265
|
use Mojo::Base 'Mojolicious::Plugin'; |
|
|
1
|
|
|
|
|
3
|
|
|
|
1
|
|
|
|
|
9
|
|
|
4
|
|
|
|
|
|
|
|
|
5
|
|
|
|
|
|
|
our $VERSION = '0.001'; |
|
6
|
|
|
|
|
|
|
|
|
7
|
|
|
|
|
|
|
our @EXPORT_OK = qw(is_bot); |
|
8
|
|
|
|
|
|
|
|
|
9
|
|
|
|
|
|
|
# Credits to: https://github.com/omrilotan/isbot |
|
10
|
|
|
|
|
|
|
my $BOT_HEADERS = [ |
|
11
|
|
|
|
|
|
|
qr/\sdaum[ \/]/, |
|
12
|
|
|
|
|
|
|
qr/\sdeusu\//, |
|
13
|
|
|
|
|
|
|
qr/\syadirectfetcher/, |
|
14
|
|
|
|
|
|
|
qr/(?:^|\s)site/, |
|
15
|
|
|
|
|
|
|
qr/(?:^|[^g])news/, |
|
16
|
|
|
|
|
|
|
qr/@[a-z]/, |
|
17
|
|
|
|
|
|
|
qr/\\(at\\)[a-z]/, |
|
18
|
|
|
|
|
|
|
qr/\(github\.com/, |
|
19
|
|
|
|
|
|
|
qr/\\[at\\][a-z]/, |
|
20
|
|
|
|
|
|
|
qr/^12345/, |
|
21
|
|
|
|
|
|
|
qr/^, |
|
22
|
|
|
|
|
|
|
qr/[\s]{50,}/, |
|
23
|
|
|
|
|
|
|
qr/^active/, |
|
24
|
|
|
|
|
|
|
qr/^ad muncher/, |
|
25
|
|
|
|
|
|
|
qr/^amaya/, |
|
26
|
|
|
|
|
|
|
qr/^anglesharp/, |
|
27
|
|
|
|
|
|
|
qr/^anonymous/, |
|
28
|
|
|
|
|
|
|
qr/^avsdevicesdk/, |
|
29
|
|
|
|
|
|
|
qr/^axios/, |
|
30
|
|
|
|
|
|
|
qr/^bidtellect/, |
|
31
|
|
|
|
|
|
|
qr/^biglotron/, |
|
32
|
|
|
|
|
|
|
qr/^btwebclient/, |
|
33
|
|
|
|
|
|
|
qr/^castro/, |
|
34
|
|
|
|
|
|
|
qr/^clamav[\s\/]/, |
|
35
|
|
|
|
|
|
|
qr/^client/, |
|
36
|
|
|
|
|
|
|
qr/^cobweb/, |
|
37
|
|
|
|
|
|
|
qr/^coccoc/, |
|
38
|
|
|
|
|
|
|
qr/^custom/, |
|
39
|
|
|
|
|
|
|
qr/^ddg[_-]android/, |
|
40
|
|
|
|
|
|
|
qr/^discourse/, |
|
41
|
|
|
|
|
|
|
qr/^dispatch\/\d/, |
|
42
|
|
|
|
|
|
|
qr/^downcast/, |
|
43
|
|
|
|
|
|
|
qr/^duckduckgo/, |
|
44
|
|
|
|
|
|
|
qr/^facebook/, |
|
45
|
|
|
|
|
|
|
qr/^fdm[\s\/]\d/, |
|
46
|
|
|
|
|
|
|
qr/^getright/, |
|
47
|
|
|
|
|
|
|
qr/^gozilla/, |
|
48
|
|
|
|
|
|
|
qr/^hatena/, |
|
49
|
|
|
|
|
|
|
qr/^hobbit/, |
|
50
|
|
|
|
|
|
|
qr/^hotzonu/, |
|
51
|
|
|
|
|
|
|
qr/^hwcdn/, |
|
52
|
|
|
|
|
|
|
qr/^jeode/, |
|
53
|
|
|
|
|
|
|
qr/^jetty/, |
|
54
|
|
|
|
|
|
|
qr/^jigsaw/, |
|
55
|
|
|
|
|
|
|
qr/^linkdex/, |
|
56
|
|
|
|
|
|
|
qr/^lwp[-:\s]/, |
|
57
|
|
|
|
|
|
|
qr/^metauri/, |
|
58
|
|
|
|
|
|
|
qr/^microsoft\sbits/, |
|
59
|
|
|
|
|
|
|
qr/^movabletype/, |
|
60
|
|
|
|
|
|
|
qr/^mozilla\/\d\.\d\s(compatible;?\\)$/, |
|
61
|
|
|
|
|
|
|
qr/^mozilla\/\d\.\d\s\w*$/, |
|
62
|
|
|
|
|
|
|
qr/^navermailapp/, |
|
63
|
|
|
|
|
|
|
qr/^netsurf/, |
|
64
|
|
|
|
|
|
|
qr/^offline\sexplorer/, |
|
65
|
|
|
|
|
|
|
qr/^php/, |
|
66
|
|
|
|
|
|
|
qr/^postman/, |
|
67
|
|
|
|
|
|
|
qr/^postrank/, |
|
68
|
|
|
|
|
|
|
qr/^python/, |
|
69
|
|
|
|
|
|
|
qr/^read/, |
|
70
|
|
|
|
|
|
|
qr/^reed/, |
|
71
|
|
|
|
|
|
|
qr/^restsharp/, |
|
72
|
|
|
|
|
|
|
qr/^snapchat/, |
|
73
|
|
|
|
|
|
|
qr/^space\sbison/, |
|
74
|
|
|
|
|
|
|
qr/^svn/, |
|
75
|
|
|
|
|
|
|
qr/^swcd\s/, |
|
76
|
|
|
|
|
|
|
qr/^taringa/, |
|
77
|
|
|
|
|
|
|
qr/^test\scertificate\sinfo/, |
|
78
|
|
|
|
|
|
|
qr/^thumbor/, |
|
79
|
|
|
|
|
|
|
qr/^tumblr/, |
|
80
|
|
|
|
|
|
|
qr/^user-agent:mozilla/, |
|
81
|
|
|
|
|
|
|
qr/^valid/, |
|
82
|
|
|
|
|
|
|
qr/^venus\/fedoraplanet/, |
|
83
|
|
|
|
|
|
|
qr/^w3c/, |
|
84
|
|
|
|
|
|
|
qr/^webbandit/, |
|
85
|
|
|
|
|
|
|
qr/^webcopier/, |
|
86
|
|
|
|
|
|
|
qr/^wget/, |
|
87
|
|
|
|
|
|
|
qr/^whatsapp/, |
|
88
|
|
|
|
|
|
|
qr/^xenu\slink\ssleuth/, |
|
89
|
|
|
|
|
|
|
qr/^yahoo/, |
|
90
|
|
|
|
|
|
|
qr/^yandex/, |
|
91
|
|
|
|
|
|
|
qr/^zdm\/\d/, |
|
92
|
|
|
|
|
|
|
qr/^zoom\smarketplace/, |
|
93
|
|
|
|
|
|
|
qr/^\{\{.*\}\}$/, |
|
94
|
|
|
|
|
|
|
qr/adbeat\.com/, |
|
95
|
|
|
|
|
|
|
qr/appinsights/, |
|
96
|
|
|
|
|
|
|
qr/archive/, |
|
97
|
|
|
|
|
|
|
qr/ask\sjeeves\/teoma/, |
|
98
|
|
|
|
|
|
|
qr/bit\.ly/, |
|
99
|
|
|
|
|
|
|
qr/bluecoat\sdrtr/, |
|
100
|
|
|
|
|
|
|
qr/bot/, |
|
101
|
|
|
|
|
|
|
qr/browsex/, |
|
102
|
|
|
|
|
|
|
qr/burpcollaborator/, |
|
103
|
|
|
|
|
|
|
qr/capture/, |
|
104
|
|
|
|
|
|
|
qr/catch/, |
|
105
|
|
|
|
|
|
|
qr/check/, |
|
106
|
|
|
|
|
|
|
qr/chrome-lighthouse/, |
|
107
|
|
|
|
|
|
|
qr/chromeframe/, |
|
108
|
|
|
|
|
|
|
qr/cloud/, |
|
109
|
|
|
|
|
|
|
qr/crawl/, |
|
110
|
|
|
|
|
|
|
qr/cryptoapi/, |
|
111
|
|
|
|
|
|
|
qr/dareboost/, |
|
112
|
|
|
|
|
|
|
qr/datanyze/, |
|
113
|
|
|
|
|
|
|
qr/dataprovider/, |
|
114
|
|
|
|
|
|
|
qr/dejaclick/, |
|
115
|
|
|
|
|
|
|
qr/dmbrowser/, |
|
116
|
|
|
|
|
|
|
qr/download/, |
|
117
|
|
|
|
|
|
|
qr/evc-batch.*/, |
|
118
|
|
|
|
|
|
|
qr/feed/, |
|
119
|
|
|
|
|
|
|
qr/firephp/, |
|
120
|
|
|
|
|
|
|
qr/freesafeip/, |
|
121
|
|
|
|
|
|
|
qr/ghost/, |
|
122
|
|
|
|
|
|
|
qr/gomezagent/, |
|
123
|
|
|
|
|
|
|
qr/google/, |
|
124
|
|
|
|
|
|
|
qr/headlesschrome/, |
|
125
|
|
|
|
|
|
|
qr/http/, |
|
126
|
|
|
|
|
|
|
qr/httrack/, |
|
127
|
|
|
|
|
|
|
qr/hubspot\smarketing\sgrader/, |
|
128
|
|
|
|
|
|
|
qr/hydra/, |
|
129
|
|
|
|
|
|
|
qr/ibisbrowser/, |
|
130
|
|
|
|
|
|
|
qr/images/, |
|
131
|
|
|
|
|
|
|
qr/iplabel/, |
|
132
|
|
|
|
|
|
|
qr/ips-agent/, |
|
133
|
|
|
|
|
|
|
qr/java/, |
|
134
|
|
|
|
|
|
|
qr/library/, |
|
135
|
|
|
|
|
|
|
qr/mail\.ru/, |
|
136
|
|
|
|
|
|
|
qr/manager/, |
|
137
|
|
|
|
|
|
|
qr/monitor/, |
|
138
|
|
|
|
|
|
|
qr/morningscore/, |
|
139
|
|
|
|
|
|
|
qr/neustar\swpm/, |
|
140
|
|
|
|
|
|
|
qr/nutch/, |
|
141
|
|
|
|
|
|
|
qr/offbyone/, |
|
142
|
|
|
|
|
|
|
qr/optimize/, |
|
143
|
|
|
|
|
|
|
qr/pageburst/, |
|
144
|
|
|
|
|
|
|
qr/pagespeed/, |
|
145
|
|
|
|
|
|
|
qr/perl/, # :( |
|
146
|
|
|
|
|
|
|
qr/phantom/, |
|
147
|
|
|
|
|
|
|
qr/pingdom/, |
|
148
|
|
|
|
|
|
|
qr/powermarks/, |
|
149
|
|
|
|
|
|
|
qr/preview/, |
|
150
|
|
|
|
|
|
|
qr/proxy/, |
|
151
|
|
|
|
|
|
|
qr/ptst[\s\/]\d/, |
|
152
|
|
|
|
|
|
|
qr/reader/, |
|
153
|
|
|
|
|
|
|
qr/rexx;/, |
|
154
|
|
|
|
|
|
|
qr/rigor/, |
|
155
|
|
|
|
|
|
|
qr/rss/, |
|
156
|
|
|
|
|
|
|
qr/scan/, |
|
157
|
|
|
|
|
|
|
qr/scrape/, |
|
158
|
|
|
|
|
|
|
qr/search/, |
|
159
|
|
|
|
|
|
|
qr/serp\s\?reputation\s\?management/, |
|
160
|
|
|
|
|
|
|
qr/server/, |
|
161
|
|
|
|
|
|
|
qr/sogou/, |
|
162
|
|
|
|
|
|
|
qr/sparkler/, |
|
163
|
|
|
|
|
|
|
qr/speedcurve/, |
|
164
|
|
|
|
|
|
|
qr/spider/, |
|
165
|
|
|
|
|
|
|
qr/splash/, |
|
166
|
|
|
|
|
|
|
qr/statuscake/, |
|
167
|
|
|
|
|
|
|
qr/stumbleupon\.com/, |
|
168
|
|
|
|
|
|
|
qr/supercleaner/, |
|
169
|
|
|
|
|
|
|
qr/synapse/, |
|
170
|
|
|
|
|
|
|
qr/synthetic/, |
|
171
|
|
|
|
|
|
|
qr/taginspector/, |
|
172
|
|
|
|
|
|
|
qr/torrent/, |
|
173
|
|
|
|
|
|
|
qr/tracemyfile/, |
|
174
|
|
|
|
|
|
|
qr/transcoder/, |
|
175
|
|
|
|
|
|
|
qr/trendsmapresolver/, |
|
176
|
|
|
|
|
|
|
qr/twingly\srecon/, |
|
177
|
|
|
|
|
|
|
qr/url/, |
|
178
|
|
|
|
|
|
|
qr/virtuoso/, |
|
179
|
|
|
|
|
|
|
qr/wappalyzer/, |
|
180
|
|
|
|
|
|
|
qr/webglance/, |
|
181
|
|
|
|
|
|
|
qr/webkit2png/, |
|
182
|
|
|
|
|
|
|
qr/websitemetadataretriever/, |
|
183
|
|
|
|
|
|
|
qr/whatcms/, |
|
184
|
|
|
|
|
|
|
qr/wordpress/, |
|
185
|
|
|
|
|
|
|
qr/zgrab/ |
|
186
|
|
|
|
|
|
|
]; |
|
187
|
|
|
|
|
|
|
|
|
188
|
|
|
|
|
|
|
sub register { |
|
189
|
1
|
|
|
1
|
1
|
340428
|
my $app = $_[1]; |
|
190
|
|
|
|
|
|
|
|
|
191
|
|
|
|
|
|
|
{ |
|
192
|
1
|
|
|
1
|
|
3151
|
no warnings 'all'; |
|
|
1
|
|
|
|
|
3
|
|
|
|
1
|
|
|
|
|
44
|
|
|
|
1
|
|
|
|
|
2
|
|
|
193
|
1
|
|
|
1
|
|
4
|
no strict 'refs'; |
|
|
1
|
|
|
|
|
17
|
|
|
|
1
|
|
|
|
|
227
|
|
|
194
|
1
|
|
|
|
|
9
|
*{"Mojo::Message::Request::is_bot"} = sub { |
|
195
|
43
|
|
|
43
|
|
72365
|
my $self = shift; |
|
196
|
43
|
|
66
|
|
|
175
|
my $str = $self->headers->user_agent // shift; |
|
197
|
|
|
|
|
|
|
|
|
198
|
43
|
|
|
|
|
1127
|
foreach my $p (@$BOT_HEADERS) { |
|
199
|
5805
|
100
|
|
|
|
19564
|
if ( $str =~ $p ) { |
|
200
|
23
|
|
|
|
|
181
|
return 1; |
|
201
|
|
|
|
|
|
|
} |
|
202
|
|
|
|
|
|
|
} |
|
203
|
|
|
|
|
|
|
|
|
204
|
20
|
|
|
|
|
188
|
return 0; |
|
205
|
1
|
|
|
|
|
5
|
}; |
|
206
|
|
|
|
|
|
|
} |
|
207
|
|
|
|
|
|
|
|
|
208
|
1
|
|
|
|
|
4
|
return $_[0]; |
|
209
|
|
|
|
|
|
|
} |
|
210
|
|
|
|
|
|
|
|
|
211
|
|
|
|
|
|
|
=encoding utf8 |
|
212
|
|
|
|
|
|
|
|
|
213
|
|
|
|
|
|
|
=head1 Name |
|
214
|
|
|
|
|
|
|
|
|
215
|
|
|
|
|
|
|
Mojolicious::Plugin::IsBot |
|
216
|
|
|
|
|
|
|
|
|
217
|
|
|
|
|
|
|
=head1 Synopsis |
|
218
|
|
|
|
|
|
|
|
|
219
|
|
|
|
|
|
|
A super simple Mojolicious plugin to test if a User-Agent header is possbily a bot. |
|
220
|
|
|
|
|
|
|
|
|
221
|
|
|
|
|
|
|
Works by adding a C method to L. |
|
222
|
|
|
|
|
|
|
|
|
223
|
|
|
|
|
|
|
=head2 Example |
|
224
|
|
|
|
|
|
|
|
|
225
|
|
|
|
|
|
|
use Mojolicious::Lite -signatures; |
|
226
|
|
|
|
|
|
|
|
|
227
|
|
|
|
|
|
|
plugin('IsBot'); |
|
228
|
|
|
|
|
|
|
|
|
229
|
|
|
|
|
|
|
get '/' => sub { |
|
230
|
|
|
|
|
|
|
my $s = shift; |
|
231
|
|
|
|
|
|
|
|
|
232
|
|
|
|
|
|
|
return $s->render(text => 'You are bot!') if $s->req->is_bot; |
|
233
|
|
|
|
|
|
|
|
|
234
|
|
|
|
|
|
|
$s->render(text => 'You are not bot!'); |
|
235
|
|
|
|
|
|
|
}; |
|
236
|
|
|
|
|
|
|
|
|
237
|
|
|
|
|
|
|
app->start; |
|
238
|
|
|
|
|
|
|
|
|
239
|
|
|
|
|
|
|
=head2 License |
|
240
|
|
|
|
|
|
|
|
|
241
|
|
|
|
|
|
|
Is::Bot is provided under the Artistic 2.0 license. |