proposal

scraper_proposal.php

<?php
class Scraper{} // just a util or alias


$scraper = new Scraper();
$scraper->getDocumentResolver()->setHtmlFormatter();

class Scraper
{
    use EventManagerAware;
    public function find($expr)
    {
        $document = $this->getDocumentResolver()->getDocument();
        //$this->getEventManager()->dispatch();

        $documenet->getDom(Document::FORMAT_XHTML);
    }
}

class DocumentResolverFactory
{
    public static function fromUri($uri)
    {
        $documentResolver = new DocumentResolver;
        $documentResolver->setUri($uri);
        return $documentResolver;
    }

    public static function fromContent($content, $http_respones_header = array(), $uri = null)
    {
    
    }

    public static function fromResponseOfZF2($response, $uri = null)
    {
    
    
    }

}

class DocumentResolver implements DocumentResolverInterface, HtmlFormatterAwareInterface
{
    use HttpClientAwareTrait;
    use EventManagerAware;

    public function setUri($uri){}
    public function setDocument(){}

    public function getDocument()
    {
        if ($this->document) {
            return $this->document;
        } elseif ($this->response) {
            $document = new Document($this->uri);

        } else {
            $generateDocument = $this->getGenerateDocumentCallback();
            $document = $generateDocument();
        }

        $document->setHtmlFormatter($this->htmlFormatter);

        $this->document = $document;
        return $this->document;
    }

    public function getGenerateDocumentCallback()
    {
        return function () {
            return new Document($this->getHttpClient()->send(), $this->uri);
        };
    }

}

class Document
{
    const FORMAT_NONE = 0;
    const FORMAT_XHTML = 1;
    const FORMAT_HTML5 = 2;

    public function getContent($format = false)
    {
        if ($this->content) {
            $content = $this->content;
        }

        if (!$this->reponse && $this->dom) {
            $content = $this->dom->saveHTML();
        }
        if ($format) {
            $content = $this->getHtmlFormmater()->getXhtml($content);
        }

        return $content;
    }

    public function getDom($format = false)
    {
        $doc = new DOMDocument();
        $doc->loadHTML($this->getContent($format));
    }

}

class HtmlFormatter implements HtmlFormatterInterface
{
    use EventManagerAware;
    public function getXhtml()
    {
        //$this->getEventManager()->dispatch();

        // some tidy

        //$this->getEventManager()->dispatch();
    }

}


class Processer
{
    public function find($target)
    {
        if (is_string($target)) {
        
        } else {
            $process = self::process($target, $this->keyMapChanger);
        }

        $ret = $this->progressScrape($process);
    }

    protected function progressScrape($process)
    {
        $response = $resourceLocator->getHttpResponse($this->uri);

        $context = $this->strategy->som();

        foreach () {
        
        
        }
    }
}

$id = Scraper::uri($uri)->scrape('#id')->html()->filter(function($element) {});

// array
$ret = Scraper::uri($uri)->scrape([
    '//title' => 'html',
    '//a' => ['@href', 'callback', function($href) {return $href;}],
    '//tr' => [['html'], function ($trs) { return new LimitIterator($trs, 0, 2);}],
    '//id2' => function ($element) {
        return $element;   
    }
]);


//// multidimentional
$processor = Scraper::processor([
]);
$scraper->scrape(['#id' => [$process]]);

////
$process->keyMap([
    '//tr[@class="item"]' => 'entry'              
]);
$process->setHydrator($hydrator);


//
$scraper->scrape(function(){
    yield '//td' => 
});

usage.php

<?php

use Diggin\Scraper\DocumentResolverFactory;
use Diggin\Scraper\DocumentResolver;
use Diggin\Scraper\Finder;

/** 
 * constructor
 */
$resultSet = (new Finder($uri))->each('.postlist', function($postlist){
    return 
});

$resultSet = (new Finder(['header' => $headers, $body, 'base-uri' => $uri]))->each('.postlist', function($postlist){
    return 
});

$resultSet = (new Finder(DocumentResolverFactory::uri($uri)))->each('.postlist', function($postlist){
    return 
});

$resultSet = (new Finder(DocumentResolverFactory::response($response, $baseUri)))->each('.postlist', function($postlist){
    return 
});


/**
 * shortcuts
 */
$finder->findOne('h3 a')->href();
$finder->find('h3')->current();

/**
 * complex
 */
$resultSet = $finder
->bindfirst('content .key1')
->bindfirst('li .key3', function($key3) {return (int) $key3;});
->bindfirst('li .key4', 'html', 'specified-key-name')
->bindEach('div .list', function($list) {
    $list->bindfirst();
    return $list;
})
->bindHelper('feed') 
->execute();

foreach ($resultSet as $v) {
    $v->html();
}

/**
 * attachment
 */
$documentResolver->getEventManager()->attach('afterGet', $callback);

/**
 * crawling
 */
$finder->bindEach(/**/);
foreach ($uris as $uri) {
    $finder->getDocumentResolver()->setUri($uri);
    $finder->execute();
}

/**
 * pagerize
 */
$finder->getHelper('autopagerize')->some();
$finder->bindHeper('autopagerize');
while (true) {
    $finder->execute();
}

/**
 * setup http client
 */
new Finder((new DocumentResolver)->getHttpClient()->setConfig());