| 1 |
NAME |
| 2 |
Scrappy - The All Powerful Web Spidering, Scraping, Creeping Crawling |
| 3 |
Framework |
| 4 |
|
| 5 |
VERSION |
| 6 |
version 0.94112090 |
| 7 |
|
| 8 |
SYNOPSIS |
| 9 |
#!/usr/bin/perl |
| 10 |
use Scrappy; |
| 11 |
|
| 12 |
my $scraper = Scrappy->new; |
| 13 |
|
| 14 |
$scraper->crawl('http://search.cpan.org/recent', |
| 15 |
'/recent' => { |
| 16 |
'#cpansearch li a' => sub { |
| 17 |
print $_[1]->{href}, "\n"; |
| 18 |
} |
| 19 |
} |
| 20 |
); |
| 21 |
|
| 22 |
And now manually, ... without crawl, the above is similar to the |
| 23 |
following ... |
| 24 |
|
| 25 |
#!/usr/bin/perl |
| 26 |
use Scrappy; |
| 27 |
|
| 28 |
my $scraper = Scrappy->new; |
| 29 |
|
| 30 |
if ($scraper->get($url)->page_loaded) { |
| 31 |
$scraper->select('#cpansearch li a')->each(sub{ |
| 32 |
print shift->{href}, "\n"; |
| 33 |
}); |
| 34 |
} |
| 35 |
|
| 36 |
DESCRIPTION |
| 37 |
Scrappy is an easy (and hopefully fun) way of scraping, spidering, |
| 38 |
and/or harvesting information from web pages, web services, and more. |
| 39 |
Scrappy is a feature rich, flexible, intelligent web automation tool. |
| 40 |
|
| 41 |
Scrappy (pronounced Scrap+Pee) == 'Scraper Happy' or 'Happy Scraper'; If |
| 42 |
you like you may call it Scrapy (pronounced Scrape+Pee) although Python |
| 43 |
has a web scraping framework by that name and this module is not a port |
| 44 |
of that one. |
| 45 |
|
| 46 |
FEATURES |
| 47 |
Scrappy provides a framework containing all the tools neccessary to |
| 48 |
create a simple yet powerful web scraper. At its core, Scrappy loads an |
| 49 |
array of features for access control, event logging, session handling, |
| 50 |
url matching, web request and response handling, proxy management, web |
| 51 |
scraping, and downloading. |
| 52 |
|
| 53 |
Futhermore, Scrappy provides a simple Moose-based plugin system that |
| 54 |
allows Scrappy to be easily extended. |
| 55 |
|
| 56 |
my $scraper = Scrappy->new; |
| 57 |
|
| 58 |
$scraper->control; # Scrappy::Scraper::Control (access control) |
| 59 |
$scraper->parser; # Scrappy::Scraper::Parser (web scraper) |
| 60 |
$scraper->user_agent; # Scrappy::Scraper::UserAgent (user-agent tools) |
| 61 |
$scraper->logger; # Scrappy::Logger (event logger) |
| 62 |
$scraper->queue; # Scrappy::Queue (flow control for loops) |
| 63 |
$scraper->session; # Scrappy::Session (session management) |
| 64 |
|
| 65 |
Please see the METHODS section for a more in-depth look at all Scrappy |
| 66 |
functionality. |
| 67 |
|
| 68 |
ATTRIBUTES |
| 69 |
The following is a list of object attributes available with every |
| 70 |
Scrappy instance, attributes always return an instance of the class they |
| 71 |
represent. |
| 72 |
|
| 73 |
content |
| 74 |
The content attribute holds the HTTP::Response object of the current |
| 75 |
request. Returns undef if no page has been successfully fetched. |
| 76 |
|
| 77 |
my $scraper = Scrappy->new; |
| 78 |
$scraper->content; |
| 79 |
|
| 80 |
control |
| 81 |
The control attribute holds the Scrappy::Scraper::Control object which |
| 82 |
is used the provide access conrtol to the scraper. |
| 83 |
|
| 84 |
my $scraper = Scrappy->new; |
| 85 |
$scraper->control; |
| 86 |
|
| 87 |
... $scraper->control->restrict('google.com'); |
| 88 |
... $scraper->control->allow('cpan.org'); |
| 89 |
... if $scraper->control->is_allowed($url); |
| 90 |
|
| 91 |
debug |
| 92 |
The debug attribute holds a boolean which controls whether event logs |
| 93 |
are captured. |
| 94 |
|
| 95 |
my $scraper = Scrappy->new; |
| 96 |
$scraper->debug(1); |
| 97 |
|
| 98 |
logger |
| 99 |
The logger attribute holds the Scrappy::Logger object which is used to |
| 100 |
provide event logging capabilities to the scraper. |
| 101 |
|
| 102 |
my $scraper = Scrappy->new; |
| 103 |
$scraper->logger; |
| 104 |
|
| 105 |
parser |
| 106 |
The parser attribute holds the Scrappy::Scraper::Parser object which is |
| 107 |
used to scrape html data from the specified source material. |
| 108 |
|
| 109 |
my $scraper = Scrappy->new; |
| 110 |
$scraper->parser; |
| 111 |
|
| 112 |
plugins |
| 113 |
The plugins attribute holds the Scrappy::Plugin object which is an |
| 114 |
interface used to load plugins. |
| 115 |
|
| 116 |
my $scraper = Scrappy->new; |
| 117 |
$scraper->plugins; |
| 118 |
|
| 119 |
queue |
| 120 |
The queue attribute holds the Scrappy::Queue object which is used to |
| 121 |
provide flow-control for the standard loop approach to crawling. |
| 122 |
|
| 123 |
my $scraper = Scrappy->new; |
| 124 |
$scraper->queue; |
| 125 |
|
| 126 |
session |
| 127 |
The session attribute holds the Scrappy::Session object which is used to |
| 128 |
provide session support and persistent data across executions. |
| 129 |
|
| 130 |
my $scraper = Scrappy->new; |
| 131 |
$scraper->session; |
| 132 |
|
| 133 |
user_agent |
| 134 |
The user_agent attribute holds the Scrappy::Scraper::UserAgent object |
| 135 |
which is used to set and manipulate the user-agent header of the |
| 136 |
scraper. |
| 137 |
|
| 138 |
my $scraper = Scrappy->new; |
| 139 |
$scraper->user_agent; |
| 140 |
|
| 141 |
worker |
| 142 |
The worker attribute holds the WWW::Mechanize object which is used |
| 143 |
navigate web pages and provide request and response header information. |
| 144 |
|
| 145 |
my $scraper = Scrappy->new; |
| 146 |
$scraper->worker; |
| 147 |
|
| 148 |
METHODS |
| 149 |
back |
| 150 |
The back method is the equivalent of hitting the "back" button in a |
| 151 |
browser, it returns the previous page (response) and returns that URL, |
| 152 |
it will not backtrack beyond the first request. |
| 153 |
|
| 154 |
my $scraper = Scrappy->new; |
| 155 |
|
| 156 |
$scraper->get(...); |
| 157 |
... |
| 158 |
$scraper->get(...); |
| 159 |
... |
| 160 |
my $last_url = $scraper->back; |
| 161 |
|
| 162 |
cookies |
| 163 |
The cookies method returns an HTTP::Cookie object. Note! Cookies can be |
| 164 |
made persistent by enabling session-support. Session-support is enable |
| 165 |
by simply specifying a file to be used. |
| 166 |
|
| 167 |
my $scraper = Scrappy->new; |
| 168 |
|
| 169 |
$scraper->session->write('session.yml'); # enable session support |
| 170 |
$scraper->get(...); |
| 171 |
my $cookies = $scraper->cookies; |
| 172 |
|
| 173 |
crawl |
| 174 |
The crawl method is very useful when it is desired to crawl an entire |
| 175 |
website or at-least partially, it automates the tasks of creating a |
| 176 |
queue, fetching and parsing html pages, and establishing simple |
| 177 |
flow-control. See the SYNOPSIS for a simplified example, ... the |
| 178 |
following is a more complex example. |
| 179 |
|
| 180 |
my $scrappy = Scrappy->new; |
| 181 |
|
| 182 |
$scrappy->crawl('http://search.cpan.org/recent', |
| 183 |
'/recent' => { |
| 184 |
'#cpansearch li a' => sub { |
| 185 |
my ($self, $item) = @_; |
| 186 |
# follow all recent modules from search.cpan.org |
| 187 |
$self->queue->add($item->{href}); |
| 188 |
} |
| 189 |
}, |
| 190 |
'/~:author/:name-:version/' => { |
| 191 |
'body' => sub { |
| 192 |
my ($self, $item, $args) = @_; |
| 193 |
|
| 194 |
my $reviews = $self |
| 195 |
->select('.box table tr')->focus(3)->select('td.cell small a') |
| 196 |
->data->[0]->{text}; |
| 197 |
|
| 198 |
$reviews = $reviews =~ /\d+ Reviews/ ? |
| 199 |
$reviews : '0 reviews'; |
| 200 |
|
| 201 |
print "found $args->{name} version $args->{version} ". |
| 202 |
"[$reviews] by $args->{author}\n"; |
| 203 |
} |
| 204 |
} |
| 205 |
); |
| 206 |
|
| 207 |
domain |
| 208 |
The domain method returns the domain host of the current page. Local |
| 209 |
pages, e.g. file:///this/that/the_other will return undef. |
| 210 |
|
| 211 |
my $scraper = Scrappy->new; |
| 212 |
|
| 213 |
$scraper->get('http://www.google.com'); |
| 214 |
print $scraper->domain; # print www.google.com |
| 215 |
|
| 216 |
download |
| 217 |
The download method is passed a URL, a Download Directory Path and a |
| 218 |
optionally a File Path, then it will follow the link and store the |
| 219 |
response contents into the specified file without leaving the current |
| 220 |
page. Basically it downloads the contents of the request (especially |
| 221 |
when the request pushes a file download). If a File Path is not |
| 222 |
specified, Scrappy will attempt to name the file automatically resorting |
| 223 |
to a random 6-charater string only if all else fails, then returns to |
| 224 |
the originating page. |
| 225 |
|
| 226 |
my $scaper = Scrappy->new; |
| 227 |
my $requested_url = '...'; |
| 228 |
|
| 229 |
$scraper->download($requested_url, '/tmp'); |
| 230 |
|
| 231 |
# supply your own file name |
| 232 |
$scraper->download($requested_url, '/tmp', 'somefile.txt'); |
| 233 |
|
| 234 |
dumper |
| 235 |
The dumper method is a convenience feature that passes the passed-in |
| 236 |
objects to Data::Dumper which in turn returns a stringified |
| 237 |
representation of that object/data-structure. |
| 238 |
|
| 239 |
my $scaper = Scrappy->new; |
| 240 |
my $requested_url = '...'; |
| 241 |
|
| 242 |
$scraper->get($requested_url); |
| 243 |
|
| 244 |
my $data = $scraper->select('//a[@href]')->data; |
| 245 |
|
| 246 |
# print out the scraped data |
| 247 |
print $scraper->dumper($data); |
| 248 |
|
| 249 |
form |
| 250 |
The form method is used to submit a form on the current page. |
| 251 |
|
| 252 |
my $scraper = Scrappy->new; |
| 253 |
|
| 254 |
$scraper->form(fields => { |
| 255 |
username => 'mrmagoo', |
| 256 |
password => 'foobarbaz' |
| 257 |
}); |
| 258 |
|
| 259 |
# or more specifically, for pages with multiple forms |
| 260 |
|
| 261 |
$scraper->form(form_name => 'login_form', fields => { |
| 262 |
username => 'mrmagoo', |
| 263 |
password => 'foobarbaz' |
| 264 |
}); |
| 265 |
|
| 266 |
$scraper->form(form_number => 1, fields => { |
| 267 |
username => 'mrmagoo', |
| 268 |
password => 'foobarbaz' |
| 269 |
}); |
| 270 |
|
| 271 |
get |
| 272 |
The get method takes a URL or URI object, fetches a web page and returns |
| 273 |
the Scrappy object. |
| 274 |
|
| 275 |
my $scraper = Scrappy->new; |
| 276 |
|
| 277 |
if ($scraper->get($new_url)->page_loaded) { |
| 278 |
... |
| 279 |
} |
| 280 |
|
| 281 |
# $self->content has the HTTP::Response object |
| 282 |
|
| 283 |
log |
| 284 |
The log method logs an event with the event logger. |
| 285 |
|
| 286 |
my $scraper = Scrappy->new; |
| 287 |
|
| 288 |
$scraper->debug(1); # unneccessary, on by default |
| 289 |
$scraper->logger->verbose(1); # more detailed log |
| 290 |
|
| 291 |
$scraper->log('error', 'Somthing bad happened'); |
| 292 |
|
| 293 |
... |
| 294 |
|
| 295 |
$scraper->log('info', 'Somthing happened'); |
| 296 |
$scraper->log('warn', 'Somthing strange happened'); |
| 297 |
$scraper->log('coolness', 'Somthing cool happened'); |
| 298 |
|
| 299 |
Note! Event logs are always recorded but never automatically written to |
| 300 |
a file unless explicitly told to do so using the following: |
| 301 |
|
| 302 |
$scraper->logger->write('log.yml'); |
| 303 |
|
| 304 |
page_content_type |
| 305 |
The page_content_type method returns the content_type of the current |
| 306 |
page. |
| 307 |
|
| 308 |
my $scraper = Scrappy->new; |
| 309 |
$scraper->get('http://www.google.com/'); |
| 310 |
print $scraper->page_content_type; # prints text/html |
| 311 |
|
| 312 |
page_data |
| 313 |
The page_data method returns the HTML content of the current page, |
| 314 |
additionally this method when passed a string with HTML markup, updates |
| 315 |
the content of the current page with that data and returns the modified |
| 316 |
content. |
| 317 |
|
| 318 |
my $scraper = Scrappy->new; |
| 319 |
$scraper->get(...); |
| 320 |
my $html = $scraper->page_data; |
| 321 |
|
| 322 |
page_ishtml |
| 323 |
The page_ishtml method returns true/false based on whether our content |
| 324 |
is HTML, according to the HTTP headers. |
| 325 |
|
| 326 |
my $scraper = Scrappy->new; |
| 327 |
|
| 328 |
$scraper->get($requested_url); |
| 329 |
if ($scraper->is_html) { |
| 330 |
... |
| 331 |
} |
| 332 |
|
| 333 |
page_loaded |
| 334 |
The page_loaded method returns true/false based on whether the last |
| 335 |
request was successful. |
| 336 |
|
| 337 |
my $scraper = Scrappy->new; |
| 338 |
|
| 339 |
$scraper->get($requested_url); |
| 340 |
if ($scraper->page_loaded) { |
| 341 |
... |
| 342 |
} |
| 343 |
|
| 344 |
page_match |
| 345 |
The page_match method checks the passed-in URL (or URL of the current |
| 346 |
page if left empty) against the URL pattern (route) defined. If URL is a |
| 347 |
match, it will return the parameters of that match much in the same way |
| 348 |
a modern web application framework processes URL routes. |
| 349 |
|
| 350 |
my $url = 'http://somesite.com/tags/awesomeness'; |
| 351 |
|
| 352 |
... |
| 353 |
|
| 354 |
my $scraper = Scrappy->new; |
| 355 |
|
| 356 |
# match against the current page |
| 357 |
my $this = $scraper->page_match('/tags/:tag'); |
| 358 |
if ($this) { |
| 359 |
print $this->{'tag'}; |
| 360 |
# ... prints awesomeness |
| 361 |
} |
| 362 |
|
| 363 |
.. or .. |
| 364 |
|
| 365 |
# match against a passed url |
| 366 |
my $this = $scraper->page_match('/tags/:tag', $url, { |
| 367 |
host => 'somesite.com' |
| 368 |
}); |
| 369 |
|
| 370 |
if ($this) { |
| 371 |
print "This is the ", $this->{tag}, " page"; |
| 372 |
# ... prints this is the awesomeness page |
| 373 |
} |
| 374 |
|
| 375 |
page_reload |
| 376 |
The page_reload method acts like the refresh button in a browser, it |
| 377 |
simply repeats the current request. |
| 378 |
|
| 379 |
my $scraper = Scrappy->new; |
| 380 |
|
| 381 |
$scraper->get(...); |
| 382 |
... |
| 383 |
$scraper->reload; |
| 384 |
|
| 385 |
page_status |
| 386 |
The page_status method returns the 3-digit HTTP status code of the |
| 387 |
response. |
| 388 |
|
| 389 |
my $scraper = Scrappy->new; |
| 390 |
$scraper->get(...); |
| 391 |
|
| 392 |
if ($scraper->page_status == 200) { |
| 393 |
... |
| 394 |
} |
| 395 |
|
| 396 |
page_text |
| 397 |
The page_text method returns a text representation of the last page |
| 398 |
having all HTML markup stripped. |
| 399 |
|
| 400 |
my $scraper = Scrappy->new; |
| 401 |
$scraper->get(...); |
| 402 |
|
| 403 |
my $text = $scraper->page_text; |
| 404 |
|
| 405 |
page_title |
| 406 |
The page_title method returns the content of the title tag if the |
| 407 |
current page is HTML, otherwise returns undef. |
| 408 |
|
| 409 |
my $scraper = Scrappy->new; |
| 410 |
$scraper->get('http://www.google.com/'); |
| 411 |
|
| 412 |
my $title = $scraper->page_title; |
| 413 |
print $title; # print Google |
| 414 |
|
| 415 |
pause |
| 416 |
This method sets breaks between your requests in an attempt to simulate |
| 417 |
human interaction. |
| 418 |
|
| 419 |
my $scraper = Scrappy->new; |
| 420 |
$scraper->pause(20); |
| 421 |
|
| 422 |
$scraper->get($request_1); |
| 423 |
$scraper->get($request_2); |
| 424 |
$scraper->get($request_3); |
| 425 |
|
| 426 |
Given the above example, there will be a 20 sencond break between each |
| 427 |
request made, get, post, request, etc., You can also specify a range to |
| 428 |
have the pause method select from at random... |
| 429 |
|
| 430 |
$scraper->pause(5,20); |
| 431 |
|
| 432 |
$scraper->get($request_1); |
| 433 |
$scraper->get($request_2); |
| 434 |
|
| 435 |
# reset/turn it off |
| 436 |
$scraper->pause(0); |
| 437 |
|
| 438 |
print "I slept for ", ($scraper->pause), " seconds"; |
| 439 |
|
| 440 |
Note! The download method is exempt from any automatic pausing. |
| 441 |
|
| 442 |
plugin |
| 443 |
The plugin method allow you to load a plugin. Using the appropriate case |
| 444 |
is recommended but not neccessary. See Scrappy::Plugin for more |
| 445 |
information. |
| 446 |
|
| 447 |
my $scraper = Scrappy->new; |
| 448 |
|
| 449 |
$scraper->plugin('foo_bar'); # will load Scrappy::Plugin::FooBar |
| 450 |
$scraper->plugin('foo-bar'); # will load Scrappy::Plugin::Foo::Bar |
| 451 |
$scraper->plugin('Foo::Bar'); # will load Scrappy::Plugin::Foo::Bar |
| 452 |
|
| 453 |
# more pratically |
| 454 |
$scraper->plugin('whois', 'spammer_check'); |
| 455 |
|
| 456 |
... somewhere in code |
| 457 |
|
| 458 |
my $var = $scraper->plugin_method(); |
| 459 |
|
| 460 |
# example using core plugin Scrappy::Plugin::RandomProxy |
| 461 |
|
| 462 |
my $s = Scrappy->new; |
| 463 |
|
| 464 |
$s->plugin('random_proxy'); |
| 465 |
$s->use_random_proxy; |
| 466 |
|
| 467 |
$s->get(...); |
| 468 |
|
| 469 |
post |
| 470 |
The post method takes a URL, a hashref of key/value pairs, and |
| 471 |
optionally an array of key/value pairs, and posts that data to the |
| 472 |
specified URL, then returns an HTTP::Response object. |
| 473 |
|
| 474 |
my $scraper = Scrappy->new; |
| 475 |
|
| 476 |
$scraper->post($requested_url, { |
| 477 |
input_a => 'value_a', |
| 478 |
input_b => 'value_b' |
| 479 |
}); |
| 480 |
|
| 481 |
# w/additional headers |
| 482 |
my %headers = ('Content-Type' => 'multipart/form-data'); |
| 483 |
$scraper->post($requested_url, { |
| 484 |
input_a => 'value_a', |
| 485 |
input_b => 'value_b' |
| 486 |
}, %headers); |
| 487 |
|
| 488 |
Note! The most common post headers for content-type are |
| 489 |
application/x-www-form-urlencoded and multipart/form-data. |
| 490 |
|
| 491 |
proxy |
| 492 |
The proxy method will set the proxy for the next request to be tunneled |
| 493 |
through. |
| 494 |
|
| 495 |
my $scraper = Scrappy->new; |
| 496 |
|
| 497 |
$scraper->proxy('http', 'http://proxy1.example.com:8000/'); |
| 498 |
$scraper->get($requested_url); |
| 499 |
|
| 500 |
$scraper->proxy('http', 'ftp', 'http://proxy2.example.com:8000/'); |
| 501 |
$scraper->get($requested_url); |
| 502 |
|
| 503 |
# best practice when using proxies |
| 504 |
|
| 505 |
use Tiny::Try; |
| 506 |
|
| 507 |
my $proxie = Scrappy->new; |
| 508 |
|
| 509 |
$proxie->proxy('http', 'http://proxy.example.com:8000/'); |
| 510 |
|
| 511 |
try { |
| 512 |
$proxie->get($requested_url); |
| 513 |
} catch { |
| 514 |
die "Proxy failed\n"; |
| 515 |
}; |
| 516 |
|
| 517 |
Note! When using a proxy to perform requests, be aware that if they fail |
| 518 |
your program will die unless you wrap your code in an eval statement or |
| 519 |
use a try/catch mechanism. In the example above we use Tiny::Try to trap |
| 520 |
any errors that might occur when using proxy. |
| 521 |
|
| 522 |
request_denied |
| 523 |
The request_denied method is a simple shortcut to determine if the page |
| 524 |
you requested got loaded or redirected. This method is very useful on |
| 525 |
systems that require authentication and redirect if not authorized. This |
| 526 |
function return boolean, 1 if the current page doesn't match the |
| 527 |
requested page. |
| 528 |
|
| 529 |
my $scraper = Scrappy->new; |
| 530 |
$scraper->get($url_to_dashboard); |
| 531 |
|
| 532 |
if ($scraper->request_denied) { |
| 533 |
# do login, again |
| 534 |
} |
| 535 |
else { |
| 536 |
# resume ... |
| 537 |
} |
| 538 |
|
| 539 |
response |
| 540 |
The response method returns the HTTP::Repsonse object of the current |
| 541 |
page. |
| 542 |
|
| 543 |
my $scraper = Scrappy->new; |
| 544 |
$scraper->get(...); |
| 545 |
my $res = $scraper->response; |
| 546 |
|
| 547 |
select |
| 548 |
The select method takes XPATH or CSS selectors and returns a |
| 549 |
Scrappy::Scraper::Parser object which contains the matching elements. |
| 550 |
|
| 551 |
my $scraper = Scrappy->new; |
| 552 |
|
| 553 |
# return a list of links |
| 554 |
my $list = $scraper->select('#profile li a')->data; # see Scrappy::Scraper::Parser |
| 555 |
|
| 556 |
foreach my $link (@{$list}) { |
| 557 |
print $link->{href}, "\n"; |
| 558 |
} |
| 559 |
|
| 560 |
# Zoom in on specific chunks of html code using the following ... |
| 561 |
my $list = $scraper |
| 562 |
->select('#container table tr') # select all rows |
| 563 |
->focus(4) # focus on the 5th row |
| 564 |
->select('div div')->data; |
| 565 |
|
| 566 |
# The code above selects the div > div inside of the 5th tr in #container table |
| 567 |
# Access attributes html, text and other attributes as follows... |
| 568 |
|
| 569 |
$element = $scraper->select('table')->data->[0]; |
| 570 |
$element->{html}; # HTML representation of the table |
| 571 |
$element->{text}; # Table stripped of all HTML |
| 572 |
$element->{cellpadding}; # cellpadding |
| 573 |
$element->{height}; # ... |
| 574 |
|
| 575 |
stash |
| 576 |
The stash method sets a stash (shared) variable or returns a reference |
| 577 |
to the entire stash object. |
| 578 |
|
| 579 |
my $scraper = Scrappy->new; |
| 580 |
$scraper->stash(age => 31); |
| 581 |
|
| 582 |
print 'stash access works' |
| 583 |
if $scraper->stash('age') == $scraper->stash->{age}; |
| 584 |
|
| 585 |
my @array = (1..20); |
| 586 |
$scraper->stash(integers => [@array]); |
| 587 |
|
| 588 |
store |
| 589 |
The store method stores the contents of the current page into the |
| 590 |
specified file. If the content-type does not begin with 'text', the |
| 591 |
content is saved as binary data. |
| 592 |
|
| 593 |
my $scraper = Scrappy->new; |
| 594 |
|
| 595 |
$scraper->get($requested_url); |
| 596 |
$scraper->store('/tmp/foo.html'); |
| 597 |
|
| 598 |
url |
| 599 |
The url method returns the complete URL for the current page. |
| 600 |
|
| 601 |
my $scraper = Scrappy->new; |
| 602 |
$scraper->get('http://www.google.com/'); |
| 603 |
print $scraper->url; # prints http://www.google.com/ |
| 604 |
|
| 605 |
AUTHOR |
| 606 |
Al Newkirk <[email protected]> |
| 607 |
|
| 608 |
COPYRIGHT AND LICENSE |
| 609 |
This software is copyright (c) 2010 by awncorp. |
| 610 |
|
| 611 |
This is free software; you can redistribute it and/or modify it under |
| 612 |
the same terms as the Perl 5 programming language system itself. |
| 613 |
|