Created
May 12, 2012 00:19
-
-
Save sasezaki/2663276 to your computer and use it in GitHub Desktop.
just sandbox prototype for async spider
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| <?php | |
| namespace Miffie; | |
| use Zend\Stdlib\Parameters as StdlibParameters; | |
| class Parameters extends StdlibParameters | |
| { | |
| public function __invoke($response) | |
| { | |
| } | |
| } | |
| class Runner | |
| { | |
| public function run() | |
| { | |
| $options = // 設定ファイルから | |
| $parameterSet// = ; | |
| $this->handleParameterSet(); | |
| } | |
| protected function handleParameterSet() | |
| { | |
| //$spider = new Spider(); | |
| foreach ($parameterSet as $parameter) { | |
| //$request = $parameter->getRequest(); | |
| //$response = $client->run($request); | |
| //$parameter->handle($response); | |
| $request = $this->getSpiderFirstRequest($parameter); | |
| $response = $this->client->send($request); | |
| $spider->invoke($response); | |
| } | |
| do { | |
| $nextprocess(); | |
| } | |
| // or | |
| do { | |
| $this->getLocator()->getQueue(); | |
| } | |
| } | |
| } | |
| class MultiRunner | |
| { | |
| protected function handleParameterSet() | |
| { | |
| $spider = new Spider; | |
| foreach ($parameterSet as $parameter) { | |
| //$spider = new Spider($parameter); | |
| $spider->setParameter($parameter); | |
| //$request = $spider->tofirstRequest($parameter); | |
| $request = $this->getSpiderFirstRequest($parameter); | |
| $request->on('comlete', function ($response, $pool) use ($spider) { | |
| $spider->invoke($response); | |
| }); | |
| //$request->getDispatch()->addListener('success', function($event) | |
| $this->pool->attach($request); | |
| // $requests[] = $request; | |
| } | |
| } | |
| } | |
| class Spider | |
| { | |
| public function invoke($response) | |
| { | |
| $result = $this->scrape($response); | |
| if ($request = $this->getNextRequest($result)) { | |
| $spider = clone $this; | |
| //$request->on | |
| $this->nextprocess = function () use ($spider, $request) { | |
| //$this->queue = function () | |
| $response = $spider->getLocator()->get('client')->send($send); | |
| $spider->invoke($response); | |
| }; | |
| } | |
| //$this->getLocator()->get('pool'); | |
| } | |
| } | |
| class Spider0 | |
| { | |
| public function run($parameter) | |
| { | |
| $page = 1; | |
| $request = $parameters->getRequest(); | |
| do { | |
| $page++; | |
| retry: | |
| try { | |
| $response = $this->client->send($request); | |
| $result = $parameters($response); | |
| } catch (\Exception $e) { | |
| goto retry; | |
| } | |
| if ($page == $parameter->get('depth')) { | |
| goto loop_exit; | |
| } | |
| if ($result['nextLink']) { | |
| //$request->setUrl($result['nextLink']); | |
| } | |
| } while (true); | |
| loop_exit: | |
| } | |
| } |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment