PHP code example of swader / diffbot-php-client

    
        
<?php
require_once('vendor/autoload.php');

/* Start to develop here. Best regards https://php-download.com/ */

    

swader / diffbot-php-client example snippets

$diffbot = new Diffbot('my_token');
$url = 'http://www.sitepoint.com/diffbot-crawling-visual-machine-learning/';
$articleApi = $diffbot->createArticleAPI($url);

echo $articleApi->call()->author; // prints out "Bruno Skvorc"

$diffbot = new Diffbot('my_token');

$api = $diffbot->createArticleAPI($url);

$api->setMeta(true);

$api->setDiscussion(false);

$api->setMeta(true)->setDiscussion(false);

$url = 'http://smittenkitchen.com/blog/2012/01/buckwheat-baby-with-salted-caramel-syrup/';
$imageApi = $diffbot->createImageAPI($url);
/** @var Image $imageEntity */
foreach ($imageApi->call() as $imageEntity) {
    echo 'Image dimensions: ' . $imageEntity->getHeight() . ' x ' . $imageEntity->getWidth() . '<br>';
}

/* Output:
Image dimensions: 333 x 500
Image dimensions: 333 x 500
Image dimensions: 334 x 500
Image dimensions: 333 x 500
Image dimensions: 333 x 500
Image dimensions: 333 x 500
Image dimensions: 333 x 500
Image dimensions: 333 x 500
Image dimensions: 333 x 500
*/

$articleApi = $diffbot->createArticleAPI('http://www.sitepoint.com/diffbot-crawling-visual-machine-learning/');
echo $articleApi->call()->author;
// or $articleApi->call()->getAuthor();

$url = $articleApi->buildUrl();

$articleApi = $diffbot->createArticleAPI('http://www.sitepoint.com/diffbot-crawling-visual-machine-learning/');
$guzzleResponse = $articleApi->call()->getResponse();

$url = 'http://community.sitepoint.com/t/php7-resource-recap/174325/';
$discussion = $diffbot->createDiscussionAPI($url)->call();
/** @var Post $post */
foreach($discussion->getPosts() as $post) {
    echo 'Author: '.$post->getAuthor().'<br>';
}

/*
Output:

Author: swader
Author: TaylorRen
Author: s_molinari
Author: s_molinari
Author: swader
Author: s_molinari
Author: swader
Author: s_molinari
Author: swader
Author: s_molinari
Author: TomB
Author: s_molinari
Author: TomB
Author: Wolf_22
Author: swader
Author: swader
Author: s_molinari
*/

$diffbot = new Diffbot('my_token');
$customApi = $diffbot->createCustomAPI('http://sitepoint.com/author/bskvorc', 'authorFolioNew');

$return = $customApi->call();

foreach ($return as $wildcard) {
    dump($wildcard->getAuthor()); // Bruno Skvorc
    dump($wildcard->author); // Bruno Skvorc
}

$diffbot = new Diffbot('my_token');
$jobs = $diffbot->crawl()->call();

$url = $job->downloadUrl("json");

// Create new diffbot as usual
$diffbot = new Diffbot('my_token');

// The crawlbot needs to be told which API to use to process crawled pages. This is optional - if omitted, it will be told to use the Analyze API with mode set to auto.
// The "crawl" url is a flag to tell APIs to prepare for consumption with Crawlbot, letting them know they won't be used directly.
$url = 'crawl';
$articleApi = $diffbot->createArticleAPI($url)->setDiscussion(false);

// Make a new crawl job. Optionally, pass in API instance
$crawl = $diffbot->crawl('sitepoint_01', $articleApi);

// Set seeds - seeds are URLs to crawl. By default, passing a subdomain into the crawl will also crawl other subdomains on main domain, including www.
$crawl->setSeeds(['http://sitepoint.com']);

// Call as usual - an EntityIterator collection of results is returned. In the case of a job's creation, only one job entity will always be returned.
$job = $crawl->call();

// See JobCrawl class to find out which getters are available 
dump($job->getDownloadUrl("json")); // outputs download URL to JSON dataset of the job's result

$diffbot = new Diffbot('my_token');

$crawl = $diffbot->crawl('sitepoint_01');

$job = $crawl->call();

dump($job->getDownloadUrl("json")); // outputs download URL to JSON dataset of the job's result

// Force start of a new crawl round manually
$crawl->roundStart();

// Pause or unpause (0) a job
$crawl->pause();
$crawl->pause(0)

// Restart removes all crawled data but keeps the job (and settings)
$crawl->restart();

// Delete a job and all related data
$crawl->delete();

$crawl->delete(false);

$url = $crawl->buildUrl();
$url->call();

$diffbot = new Diffbot('my_token');
$search = $diffbot->search('author:"Miles Johnson" AND type:article')->call();


foreach ($search as $article) {
    echo $article->getTitle();
}

    $diffbot = new Diffbot('my_token');
    $url = $diffbot
        ->createProductAPI('http://someurl.com')
        ->setMeta(true)
        ->...(insert other config methods here as desired)...
        ->buildUrl();
    echo $url;
    

bash
composer