This file is indexed.

/usr/share/perl5/Scrappy.pm is in libscrappy-perl 0.94112090-2.

This file is owned by root:root, with mode 0o644.

The actual contents of the file can be viewed below.

  1
  2
  3
  4
  5
  6
  7
  8
  9
 10
 11
 12
 13
 14
 15
 16
 17
 18
 19
 20
 21
 22
 23
 24
 25
 26
 27
 28
 29
 30
 31
 32
 33
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
# ABSTRACT: The All Powerful Web Spidering, Scraping, Creeping Crawling Framework
# Dist::Zilla: +PodWeaver

package Scrappy;

BEGIN {
    $Scrappy::VERSION = '0.94112090';
}

# load OO System
use Moose;

# load other libraries
use Carp;
extends 'Scrappy::Scraper';

sub crawl {
    my ($self, $starting_url, %pages) = @_;

    croak(
        'Please provide a starting URL and a valid configuration before crawling'
    ) unless ($self && $starting_url && keys %pages);

    # register the starting url
    $self->queue->add($starting_url);

    # start the crawl loop
    while (my $url = $self->queue->next) {

        # check if the url matches against any registered pages
        foreach my $page (keys %pages) {
            my $data = $self->page_match($page, $url);

            if ($data) {

                # found a page match, fetch and scrape the page for data
                if ($self->get($url)->page_loaded) {

                    foreach my $selector (keys(%{$pages{$page}})) {

                        # loop through resultset
                        foreach my $item (@{$self->select($selector)->data}) {

                            # execute selector code
                            $pages{$page}->{$selector}->($self, $item, $data);
                        }
                    }
                }
            }
        }
    }

    return $self;
}


1;

__END__

=pod

=head1 NAME

Scrappy - The All Powerful Web Spidering, Scraping, Creeping Crawling Framework

=head1 VERSION

version 0.94112090

=head1 SYNOPSIS

    #!/usr/bin/perl
    use Scrappy;

    my  $scraper = Scrappy->new;
    
        $scraper->crawl('http://search.cpan.org/recent',
            '/recent' => {
                '#cpansearch li a' => sub {
                    print $_[1]->{href}, "\n";
                }
            }
        );

And now manually, ... without crawl, the above is similar to the following ...

    #!/usr/bin/perl
    use Scrappy;

    my  $scraper = Scrappy->new;
        
        if ($scraper->get($url)->page_loaded) {
            $scraper->select('#cpansearch li a')->each(sub{
                print shift->{href}, "\n";
            });
        }

=head1 DESCRIPTION

Scrappy is an easy (and hopefully fun) way of scraping, spidering, and/or
harvesting information from web pages, web services, and more. Scrappy is a
feature rich, flexible, intelligent web automation tool.

Scrappy (pronounced Scrap+Pee) == 'Scraper Happy' or 'Happy Scraper'; If you
like you may call it Scrapy (pronounced Scrape+Pee) although Python has a web
scraping framework by that name and this module is not a port of that one.

=head2 FEATURES

Scrappy provides a framework containing all the tools necessary to create a
simple yet powerful web scraper. At its core, Scrappy loads an array of
features for access control, event logging, session handling, url matching,
web request and response handling, proxy management, web scraping, and downloading.

Furthermore, Scrappy provides a simple Moose-based plugin system that allows Scrappy
to be easily extended.

    my  $scraper = Scrappy->new;
    
        $scraper->control;      # Scrappy::Scraper::Control (access control)
        $scraper->parser;       # Scrappy::Scraper::Parser (web scraper)
        $scraper->user_agent;   # Scrappy::Scraper::UserAgent (user-agent tools)
        $scraper->logger;       # Scrappy::Logger (event logger)
        $scraper->queue;        # Scrappy::Queue (flow control for loops)
        $scraper->session;      # Scrappy::Session (session management)

Please see the METHODS section for a more in-depth look at all Scrappy
functionality.

=head2 ATTRIBUTES

The following is a list of object attributes available with every Scrappy instance,
attributes always return an instance of the class they represent.

=head3 content

The content attribute holds the L<HTTP::Response> object of the current request.
Returns undef if no page has been successfully fetched.

    my  $scraper = Scrappy->new;
        $scraper->content;

=head3 control

The control attribute holds the L<Scrappy::Scraper::Control> object which is used
the provide access conrtol to the scraper.

    my  $scraper = Scrappy->new;
        $scraper->control;
        
        ... $scraper->control->restrict('google.com');
        ... $scraper->control->allow('cpan.org');
        ... if $scraper->control->is_allowed($url);

=head3 debug

The debug attribute holds a boolean which controls whether event logs are captured.

    my  $scraper = Scrappy->new;
        $scraper->debug(1);

=head3 logger

The logger attribute holds the L<Scrappy::Logger> object which is used to provide
event logging capabilities to the scraper.

    my  $scraper = Scrappy->new;
        $scraper->logger;

=head3 parser

The parser attribute holds the L<Scrappy::Scraper::Parser> object which is used
to scrape html data from the specified source material.

    my  $scraper = Scrappy->new;
        $scraper->parser;

=head3 plugins

The plugins attribute holds the L<Scrappy::Plugin> object which is an interface
used to load plugins.

    my  $scraper = Scrappy->new;
        $scraper->plugins;

=head3 queue

The queue attribute holds the L<Scrappy::Queue> object which is used to provide
flow-control for the standard loop approach to crawling.

    my  $scraper = Scrappy->new;
        $scraper->queue;

=head3 session

The session attribute holds the L<Scrappy::Session> object which is used to provide
session support and persistent data across executions.

    my  $scraper = Scrappy->new;
        $scraper->session;

=head3 user_agent

The user_agent attribute holds the L<Scrappy::Scraper::UserAgent> object which is
used to set and manipulate the user-agent header of the scraper.

    my  $scraper = Scrappy->new;
        $scraper->user_agent;

=head3 worker

The worker attribute holds the L<WWW::Mechanize> object which is used navigate web
pages and provide request and response header information.

    my  $scraper = Scrappy->new;
        $scraper->worker;

=head1 METHODS

=head2 back

The back method is the equivalent of hitting the "back" button in a browser, it
returns the previous page (response) and returns that URL, it will not backtrack
beyond the first request.

    my  $scraper = Scrappy->new;
        
        $scraper->get(...);
        ...
        $scraper->get(...);
        ...
        my $last_url = $scraper->back;

=head2 cookies

The cookies method returns an HTTP::Cookie object. Note! Cookies can be made
persistent by enabling session-support. Session-support is enable by simply
specifying a file to be used.

    my  $scraper = Scrappy->new;
    
        $scraper->session->write('session.yml'); # enable session support
        $scraper->get(...);
    my  $cookies = $scraper->cookies;

=head2 crawl

The crawl method is very useful when it is desired to crawl an entire website or
at-least partially, it automates the tasks of creating a queue, fetching and
parsing html pages, and establishing simple flow-control. See the SYNOPSIS for
a simplified example, ... the following is a more complex example.

    my  $scrappy = Scrappy->new;
    
        $scrappy->crawl('http://search.cpan.org/recent',
            '/recent' => {
                '#cpansearch li a' => sub {
                    my ($self, $item) = @_;
                    # follow all recent modules from search.cpan.org
                    $self->queue->add($item->{href});
                }
            },
            '/~:author/:name-:version/' => {
                'body' => sub {
                    my ($self, $item, $args) = @_;
                    
                    my $reviews = $self
                    ->select('.box table tr')->focus(3)->select('td.cell small a')
                    ->data->[0]->{text};
                    
                    $reviews = $reviews =~ /\d+ Reviews/ ?
                        $reviews : '0 reviews';
                    
                    print "found $args->{name} version $args->{version} ".
                        "[$reviews] by $args->{author}\n";
                }
            }
        );

=head2 domain

The domain method returns the domain host of the current page. Local pages, e.g.
file:///this/that/the_other will return undef.

    my  $scraper = Scrappy->new;
    
        $scraper->get('http://www.google.com');
        print $scraper->domain; # print www.google.com

=head2 download

The download method is passed a URL, a Download Directory Path and a optionally
a File Path, then it will follow the link and store the response contents into
the specified file without leaving the current page. Basically it downloads the
contents of the request (especially when the request pushes a file download). If
a File Path is not specified, Scrappy will attempt to name the file automatically
resorting to a random 6-charater string only if all else fails, then returns to
the originating page.

    my  $scaper = Scrappy->new;
    my  $requested_url = '...';
    
        $scraper->download($requested_url, '/tmp');
    
        # supply your own file name
        $scraper->download($requested_url, '/tmp', 'somefile.txt');

=head2 dumper

The dumper method is a convenience feature that passes the passed-in objects to
L<Data::Dumper> which in turn returns a stringified representation of that
object/data-structure.

    my  $scaper = Scrappy->new;
    my  $requested_url = '...';
    
        $scraper->get($requested_url);
    
    my  $data = $scraper->select('//a[@href]')->data;
    
    # print out the scraped data
    print $scraper->dumper($data);

=head2 form

The form method is used to submit a form on the current page.

    my  $scraper = Scrappy->new;
    
        $scraper->form(fields => {
            username => 'mrmagoo',
            password => 'foobarbaz'
        });
        
        # or more specifically, for pages with multiple forms
        
        $scraper->form(form_name => 'login_form', fields => {
            username => 'mrmagoo',
            password => 'foobarbaz'
        });
        
        $scraper->form(form_number => 1, fields => {
            username => 'mrmagoo',
            password => 'foobarbaz'
        });

=head2 get

The get method takes a URL or URI object, fetches a web page and returns the
Scrappy object.

    my  $scraper = Scrappy->new;
    
    if ($scraper->get($new_url)->page_loaded) {
        ...
    }
    
    # $self->content has the HTTP::Response object

=head2 log

The log method logs an event with the event logger.

    my  $scraper = Scrappy->new;
        
        $scraper->debug(1); # unnecessary, on by default
        $scraper->logger->verbose(1); # more detailed log
        
        $scraper->log('error', 'Somthing bad happened');
        
        ...
        
        $scraper->log('info', 'Somthing happened');
        $scraper->log('warn', 'Somthing strange happened');
        $scraper->log('coolness', 'Somthing cool happened');

Note! Event logs are always recorded but never automatically written to a file
unless explicitly told to do so using the following:

        $scraper->logger->write('log.yml');

=head2 page_content_type

The page_content_type method returns the content_type of the current page.

    my  $scraper = Scrappy->new;
        $scraper->get('http://www.google.com/');
        print $scraper->page_content_type; # prints text/html

=head2 page_data

The page_data method returns the HTML content of the current page, additionally
this method when passed a string with HTML markup, updates the content of the
current page with that data and returns the modified content.

    my  $scraper = Scrappy->new;
        $scraper->get(...);
    my  $html = $scraper->page_data;

=head2 page_ishtml

The page_ishtml method returns true/false based on whether our content is HTML,
according to the HTTP headers.

    my $scraper = Scrappy->new;
    
        $scraper->get($requested_url);
        if ($scraper->is_html) {
            ...
        }

=head2 page_loaded

The page_loaded method returns true/false based on whether the last request was
successful.

    my $scraper = Scrappy->new;
    
        $scraper->get($requested_url);
        if ($scraper->page_loaded) {
            ...
        }

=head2 page_match

The page_match method checks the passed-in URL (or URL of the current page if
left empty) against the URL pattern (route) defined. If URL is a match, it will
return the parameters of that match much in the same way a modern web application
framework processes URL routes. 

    my $url = 'http://somesite.com/tags/awesomeness';
    
    ...
    
    my $scraper = Scrappy->new;
    
    # match against the current page
    my $this = $scraper->page_match('/tags/:tag');
    if ($this) {
        print $this->{'tag'};
        # ... prints awesomeness
    }
    
    .. or ..
    
    # match against a passed url
    my $this = $scraper->page_match('/tags/:tag', $url, {
        host => 'somesite.com'
    });
    
    if ($this) {
        print "This is the ", $this->{tag}, " page";
        # ... prints this is the awesomeness page
    }

=head2 page_reload

The page_reload method acts like the refresh button in a browser, it simply
repeats the current request.

    my  $scraper = Scrappy->new;
        
        $scraper->get(...);
        ...
        $scraper->reload;

=head2 page_status

The page_status method returns the 3-digit HTTP status code of the response.

    my  $scraper = Scrappy->new;
        $scraper->get(...);
        
        if ($scraper->page_status == 200) {
            ...
        }

=head2 page_text

The page_text method returns a text representation of the last page having
all HTML markup stripped.

    my  $scraper = Scrappy->new;
        $scraper->get(...);
        
    my  $text = $scraper->page_text;

=head2 page_title

The page_title method returns the content of the title tag if the current page
is HTML, otherwise returns undef.

    my  $scraper = Scrappy->new;
        $scraper->get('http://www.google.com/');
        
    my  $title = $scraper->page_title;
        print $title; # print Google

=head2 pause

This method sets breaks between your requests in an attempt to simulate human
interaction. 

    my  $scraper = Scrappy->new;
        $scraper->pause(20);
    
        $scraper->get($request_1);
        $scraper->get($request_2);
        $scraper->get($request_3);

Given the above example, there will be a 20 sencond break between each request made,
get, post, request, etc., You can also specify a range to have the pause method
select from at random...

        $scraper->pause(5,20);
    
        $scraper->get($request_1);
        $scraper->get($request_2);
    
        # reset/turn it off
        $scraper->pause(0);
    
        print "I slept for ", ($scraper->pause), " seconds";

Note! The download method is exempt from any automatic pausing.

=head2 plugin

The plugin method allow you to load a plugin. Using the appropriate case is
recommended but not necessary. See L<Scrappy::Plugin> for more information.

    my $scraper = Scrappy->new;
    
    $scraper->plugin('foo_bar');    # will load Scrappy::Plugin::FooBar
    $scraper->plugin('foo-bar');    # will load Scrappy::Plugin::Foo::Bar
    $scraper->plugin('Foo::Bar');   # will load Scrappy::Plugin::Foo::Bar
    
    # more pratically
    $scraper->plugin('whois', 'spammer_check');
    
    ... somewhere in code
    
    my $var = $scraper->plugin_method();

    # example using core plugin Scrappy::Plugin::RandomProxy
    
    my  $s = Scrappy->new;
        
        $s->plugin('random_proxy');
        $s->use_random_proxy;
        
        $s->get(...);

=head2 post

The post method takes a URL, a hashref of key/value pairs, and optionally an
array of key/value pairs, and posts that data to the specified URL, then returns
an HTTP::Response object.

    my $scraper = Scrappy->new;

    $scraper->post($requested_url, {
        input_a => 'value_a',
        input_b => 'value_b'
    });
    
    # w/additional headers
    my %headers = ('Content-Type' => 'multipart/form-data');
    $scraper->post($requested_url, {
        input_a => 'value_a',
        input_b => 'value_b'
    },  %headers);

Note! The most common post headers for content-type are
application/x-www-form-urlencoded and multipart/form-data.

=head2 proxy

The proxy method will set the proxy for the next request to be tunneled through.

    my $scraper = Scrappy->new;
    
    $scraper->proxy('http', 'http://proxy1.example.com:8000/');
    $scraper->get($requested_url);
    
    $scraper->proxy('http', 'ftp', 'http://proxy2.example.com:8000/');
    $scraper->get($requested_url);
    
    # best practice when using proxies
    
    use Tiny::Try;
    
    my $proxie = Scrappy->new;
    
    $proxie->proxy('http', 'http://proxy.example.com:8000/');
    
    try {
        $proxie->get($requested_url);
    } catch {
        die "Proxy failed\n";
    };

Note! When using a proxy to perform requests, be aware that if they fail your
program will die unless you wrap your code in an eval statement or use a try/catch
mechanism. In the example above we use Tiny::Try to trap any errors that might occur
when using proxy.

=head2 request_denied

The request_denied method is a simple shortcut to determine if the page you
requested got loaded or redirected. This method is very useful on systems
that require authentication and redirect if not authorized. This function
return boolean, 1 if the current page doesn't match the requested page.

    my $scraper = Scrappy->new;
    $scraper->get($url_to_dashboard);
    
    if ($scraper->request_denied) {
        # do login, again
    }
    else {
        # resume ...
    }

=head2 response

The response method returns the HTTP::Repsonse object of the current page.

    my  $scraper = Scrappy->new;
        $scraper->get(...);
    my  $res = $scraper->response;

=head2 select

The select method takes XPATH or CSS selectors and returns a
L<Scrappy::Scraper::Parser> object which contains the matching elements.

    my $scraper = Scrappy->new;
    
    # return a list of links
    my $list = $scraper->select('#profile li a')->data; # see Scrappy::Scraper::Parser
    
    foreach my $link (@{$list}) {
        print $link->{href}, "\n";
    }
    
    # Zoom in on specific chunks of html code using the following ...
    my $list = $scraper
    ->select('#container table tr') # select all rows
    ->focus(4) # focus on the 5th row
    ->select('div div')->data;
    
    # The code above selects the div > div inside of the 5th tr in #container table
    # Access attributes html, text and other attributes as follows...
    
    $element = $scraper->select('table')->data->[0];
    $element->{html}; # HTML representation of the table
    $element->{text}; # Table stripped of all HTML
    $element->{cellpadding}; # cellpadding
    $element->{height}; # ...

=head2 stash

The stash method sets a stash (shared) variable or returns a reference to the entire
stash object.

    my  $scraper = Scrappy->new;
        $scraper->stash(age => 31);
        
        print 'stash access works'
            if $scraper->stash('age') == $scraper->stash->{age};
    
    my  @array = (1..20);
        $scraper->stash(integers => [@array]);

=head2 store

The store method stores the contents of the current page into the specified file.
If the content-type does not begin with 'text', the content is saved as binary data.

    my  $scraper = Scrappy->new;
    
        $scraper->get($requested_url);
        $scraper->store('/tmp/foo.html');

=head2 url

The url method returns the complete URL for the current page.

    my  $scraper = Scrappy->new;
        $scraper->get('http://www.google.com/');
        print $scraper->url; # prints http://www.google.com/

=head1 AUTHOR

Al Newkirk <awncorp@cpan.org>

=head1 COPYRIGHT AND LICENSE

This software is copyright (c) 2010 by awncorp.

This is free software; you can redistribute it and/or modify it under
the same terms as the Perl 5 programming language system itself.

=cut