Amazon Price Tracker Bridge (#741)
* [amazonprice] Adds AmazonPriceTracker bridge
This commit is contained in:
parent
fbf874cb29
commit
c7b0c9fd31
2 changed files with 150 additions and 1 deletions
149
bridges/AmazonPriceTrackerBridge.php
Normal file
149
bridges/AmazonPriceTrackerBridge.php
Normal file
|
@ -0,0 +1,149 @@
|
||||||
|
<?php
|
||||||
|
|
||||||
|
class AmazonPriceTrackerBridge extends BridgeAbstract {
|
||||||
|
const MAINTAINER = 'captn3m0';
|
||||||
|
const NAME = 'Amazon Price Tracker';
|
||||||
|
const URI = 'https://www.amazon.com/';
|
||||||
|
const CACHE_TIMEOUT = 3600; // 1h
|
||||||
|
const DESCRIPTION = 'Tracks price for a single product on Amazon';
|
||||||
|
|
||||||
|
const PARAMETERS = array(
|
||||||
|
array(
|
||||||
|
'asin' => array(
|
||||||
|
'name' => 'ASIN',
|
||||||
|
'required' => true,
|
||||||
|
'exampleValue' => 'B071GB1VMQ',
|
||||||
|
// https://stackoverflow.com/a/12827734
|
||||||
|
'pattern' => 'B[\dA-Z]{9}|\d{9}(X|\d)',
|
||||||
|
),
|
||||||
|
'tld' => array(
|
||||||
|
'name' => 'Country',
|
||||||
|
'type' => 'list',
|
||||||
|
'required' => true,
|
||||||
|
'values' => array(
|
||||||
|
'Australia' => 'com.au',
|
||||||
|
'Brazil' => 'com.br',
|
||||||
|
'Canada' => 'ca',
|
||||||
|
'China' => 'cn',
|
||||||
|
'France' => 'fr',
|
||||||
|
'Germany' => 'de',
|
||||||
|
'India' => 'in',
|
||||||
|
'Italy' => 'it',
|
||||||
|
'Japan' => 'co.jp',
|
||||||
|
'Mexico' => 'com.mx',
|
||||||
|
'Netherlands' => 'nl',
|
||||||
|
'Spain' => 'es',
|
||||||
|
'United Kingdom' => 'co.uk',
|
||||||
|
'United States' => 'com',
|
||||||
|
),
|
||||||
|
'defaultValue' => 'com',
|
||||||
|
),
|
||||||
|
));
|
||||||
|
|
||||||
|
protected $title;
|
||||||
|
|
||||||
|
/**
|
||||||
|
* Generates domain name given a amazon TLD
|
||||||
|
*/
|
||||||
|
private function getDomainName() {
|
||||||
|
return 'https://www.amazon.' . $this->getInput('tld');
|
||||||
|
}
|
||||||
|
|
||||||
|
/**
|
||||||
|
* Generates URI for a Amazon product page
|
||||||
|
*/
|
||||||
|
public function getURI() {
|
||||||
|
if (!is_null($this->getInput('asin'))) {
|
||||||
|
return $this->getDomainName() . '/dp/' . $this->getInput('asin') . '/';
|
||||||
|
}
|
||||||
|
return parent::getURI();
|
||||||
|
}
|
||||||
|
|
||||||
|
/**
|
||||||
|
* Scrapes the product title from the html page
|
||||||
|
* returns the default title if scraping fails
|
||||||
|
*/
|
||||||
|
private function getTitle($html) {
|
||||||
|
$titleTag = $html->find('#productTitle', 0);
|
||||||
|
|
||||||
|
if (!$titleTag) {
|
||||||
|
return $this->getDefaultTitle();
|
||||||
|
} else {
|
||||||
|
return trim(html_entity_decode($titleTag->innertext, ENT_QUOTES));
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
/**
|
||||||
|
* Title used by the feed if none could be found
|
||||||
|
*/
|
||||||
|
private function getDefaultTitle() {
|
||||||
|
return 'Amazon.' . $this->getInput('tld') . ': ' . $this->getInput('asin');
|
||||||
|
}
|
||||||
|
|
||||||
|
/**
|
||||||
|
* Returns name for the feed
|
||||||
|
* Uses title (already scraped) if it has one
|
||||||
|
*/
|
||||||
|
public function getName() {
|
||||||
|
if (isset($this->title)) {
|
||||||
|
return $this->title;
|
||||||
|
} else {
|
||||||
|
return parent::getName();
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
/**
|
||||||
|
* Returns a generated image tag for the product
|
||||||
|
*/
|
||||||
|
private function getImage($html) {
|
||||||
|
$imageSrc = $html->find('#main-image-container img', 0);
|
||||||
|
|
||||||
|
if ($imageSrc) {
|
||||||
|
$imageSrc = $imageSrc ? $imageSrc->getAttribute('data-old-hires') : '';
|
||||||
|
return <<<EOT
|
||||||
|
<img width="300" style="max-width:300;max-height:300" src="$imageSrc" alt="{$this->title}" />
|
||||||
|
EOT;
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
/**
|
||||||
|
* Return \simple_html_dom object
|
||||||
|
* for the entire html of the product page
|
||||||
|
*/
|
||||||
|
private function getHtml() {
|
||||||
|
$uri = $this->getURI();
|
||||||
|
|
||||||
|
return getSimpleHTMLDOM($uri) ?: returnServerError('Could not request Amazon.');
|
||||||
|
}
|
||||||
|
|
||||||
|
/**
|
||||||
|
* Scrape method for Amazon product page
|
||||||
|
* @return [type] [description]
|
||||||
|
*/
|
||||||
|
public function collectData() {
|
||||||
|
$html = $this->getHtml();
|
||||||
|
$this->title = $this->getTitle($html);
|
||||||
|
$imageTag = $this->getImage($html);
|
||||||
|
|
||||||
|
$asinData = $html->find('#cerberus-data-metrics', 0);
|
||||||
|
|
||||||
|
// <div id="cerberus-data-metrics" style="display: none;"
|
||||||
|
// data-asin="B00WTHJ5SU" data-asin-price="14.99" data-asin-shipping="0"
|
||||||
|
// data-asin-currency-code="USD" data-substitute-count="-1" ... />
|
||||||
|
$currency = $asinData->getAttribute('data-asin-currency-code');
|
||||||
|
$shipping = $asinData->getAttribute('data-asin-shipping');
|
||||||
|
$price = $asinData->getAttribute('data-asin-price');
|
||||||
|
|
||||||
|
$item = array(
|
||||||
|
'title' => $this->title,
|
||||||
|
'uri' => $this->getURI(),
|
||||||
|
'content' => "$imageTag<br/>Price: $price $currency",
|
||||||
|
);
|
||||||
|
|
||||||
|
if ($shipping !== '0') {
|
||||||
|
$item['content'] .= "<br>Shipping: $shipping $currency</br>";
|
||||||
|
}
|
||||||
|
|
||||||
|
$this->items[] = $item;
|
||||||
|
}
|
||||||
|
}
|
|
@ -1,7 +1,7 @@
|
||||||
<?php
|
<?php
|
||||||
class ContainerLinuxReleasesBridge extends BridgeAbstract {
|
class ContainerLinuxReleasesBridge extends BridgeAbstract {
|
||||||
|
|
||||||
const MAINTAINER = 'capt3m0';
|
const MAINTAINER = 'captn3m0';
|
||||||
const NAME = 'Core OS Container Linux Releases Bridge';
|
const NAME = 'Core OS Container Linux Releases Bridge';
|
||||||
const URI = 'https://coreos.com/releases/';
|
const URI = 'https://coreos.com/releases/';
|
||||||
const DESCRIPTION = 'Returns the releases notes for Container Linux';
|
const DESCRIPTION = 'Returns the releases notes for Container Linux';
|
||||||
|
|
Loading…
Reference in a new issue