How can I get all amazon category products?
How can I get all amazon products from an existing category?
With the API, I can browse 10 pages and get for each page 10 products.
The category has 502348 products, and I would like to get them all.
Here is my code:
Amazon Product Advertising API <?php ?>
$params = array(
'Operation' => 'Item开发者_StackOverflow社区Search',
'SearchIndex'=>'Electronics',
//'BrowseNode'=>'281052',
'ResponseGroup'=>'small',
//'MerchantId' => 'All',
//'Condition'=>'New',
'ItemPage'=>'1471',
Maybe you should try to add two additional search parameters in your query - MinimumPrice and MaximumPrice - in combination with the keywords, of course. Then, whenever you get more than 10 pages for your search criteria, you should correct your min/mix price values.
That's how I was able to "avoid" that unreasonable limit that amazon set.
Use the Sitemaps from the Amazon Robots.txt:
http://www.amazon.com/sitemaps.US_detail_page_sitemap_desktop_index.xml.gz
You're seeing a new limitation imposed by Amazon. From the Product Advertising API home page:
ItemPage parameter will be limited to a maximum of 10 pages for ItemSearch results
Use a loop, pulling all products from each page until there are no more pages.
<?php
namespace MarcL;
use MarcL\CurlHttpRequest;
use MarcL\AmazonUrlBuilder;
use MarcL\Transformers\DataTransformerFactory;
class AmazonAPI
{
private $urlBuilder = NULL;
private $dataTransformer = NULL;
public $item=0;
public $perRequest=0;
public function IND_money_format($money)
{
$len = strlen($money);
$m = '';
$money = strrev($money);
for($i=0;$i<$len;$i++){
if(( $i==3 || ($i>3 && ($i-1)%2==0) )&& $i!=$len){
$m .=',';
}
$m .=$money[$i];
}
return strrev($m);
}
// Valid names that can be used for search
private $mValidSearchNames = array(
'All',
'Apparel',
'Appliances',
'Automotive',
'Baby',
'Beauty',
'Blended',
'Books',
'Classical',
'DVD',
'Electronics',
'Grocery',
'HealthPersonalCare',
'HomeGarden',
'HomeImprovement',
'Jewelry',
'KindleStore',
'Kitchen',
'Lighting',
'Marketplace',
'MP3Downloads',
'Music',
'MusicTracks',
'MusicalInstruments',
'OfficeProducts',
'OutdoorLiving',
'Outlet',
'PetSupplies',
'PCHardware',
'Shoes',
'Software',
'SoftwareVideoGames',
'SportingGoods',
'Tools',
'Toys',
'VHS',
'Video',
'VideoGames',
'Watches'
);
private $mErrors = array();
public function __construct($urlBuilder, $outputType) {
$this->urlBuilder = $urlBuilder;
$this->dataTransformer = DataTransformerFactory::create($outputType);
}
public function GetValidSearchNames() {
return $this->mValidSearchNames;
}
/**
* Search for items
*
* @param keywords Keywords which we're requesting
* @param searchIndex Name of search index (category) requested. NULL if searching all.
* @param sortBy Category to sort by, only used if searchIndex is not 'All'
* @param condition Condition of item. Valid conditions : Used, Collectible, Refurbished, All
*
* @return mixed SimpleXML object, array of data or false if failure.
*/
public function ItemSearch($keywords,$itemPage, $searchIndex = NULL, $sortBy = NULL, $condition = 'All',$minPrice=50000,$maxPrice=55000) {
?>
<table cellpadding="5">
<thead>
<tr>
<td>Title</td>
<td>List Price</td>
<td>Offer Price</td>
<td>Offer Selling Price</td>
<td>Amount Saved</td>
<td>Brand Name</td>
<td>Size</td>
<td>Color</td>
<td>Manufacturer</td>
</tr>
</thead>
<tbody>
<?php
$totalPages=0;
while($maxPrice<=100000)
{
$finished=false;
$itemPage=0;
while(!$finished)
{
$itemPage=$itemPage+1;
sleep(1);
$mer="MerchantId";
$merVal="Amazon";
$params = array(
'Operation' => 'ItemSearch',
'ResponseGroup' => 'Small,ItemAttributes,Offers,OfferSummary,BrowseNodes',
'Keywords' => $keywords,
'Condition' => $condition,
'ItemPage' => $itemPage,
'ListPrice' => $itemPage,
'MinimumPrice' => $minPrice,
'MaximumPrice' => $maxPrice,
'SearchIndex' => empty($searchIndex) ? 'All' : $searchIndex,
'Sort' => $sortBy && ($searchIndex != 'All') ? $sortBy : NULL
);
$totalPages=$this->FetchItems($params,$itemPage,$maxPrice,false);
if(($itemPage)==1)
{
$finished=true;
$itemPage=0;
}
}
$minPrice=$maxPrice;
$maxPrice=$maxPrice+5000;
}
//echo "<br/>total Records : ".$this->item;
?>
</tbody>
</table>
<br/><br/>
<?php
$style="";
for($looper=1;$looper<=$totalPages;$looper++)
{
if($looper>($itemPage-3) && $looper<($itemPage+3))
{
if($looper==$itemPage)
{
$style="style='color:red;'";
echo "<a href='examples.php?itemPage=".$looper."' ".$style.">".$looper."</a> ";
}
else
{
echo "<a href='examples.php?itemPage=".$looper."'>".$looper."</a> ";
}
}else if($looper>($totalPages-3))
{
echo "<a href='examples.php?itemPage=".$looper."'>".$looper."</a> ";
}else if($looper>(($totalPages/2)-3) && $looper<(($totalPages/2)+3))
{
echo "<a href='examples.php?itemPage=".$looper."'>".$looper."</a> ";
}
}
die();
//return $this->MakeAndParseRequest($params,$itemPage);
}
/**
* Lookup items from ASINs
*
* @param asinList Either a single ASIN or an array of ASINs
* @param onlyFromAmazon True if only requesting items from Amazon and not 3rd party vendors
*
* @return mixed SimpleXML object, array of data or false if failure.
*/
public function ItemLookup($asinList,$itemPage, $onlyFromAmazon = false) {
$asinList="B01D0XDW1C";
if (is_array($asinList)) {
$asinList = implode(',', $asinList);
}
$params = array(
'Operation' => 'ItemLookup',
'ResponseGroup' => 'ItemAttributes,Offers,Images',
'ReviewSort' => '-OverallRating',
'ItemId' => $asinList,
'MerchantId' => ($onlyFromAmazon == true) ? 'Amazon' : 'All'
);
return $this->MakeAndParseRequest($params,$itemPage,true);
}
public function GetErrors() {
return $this->mErrors;
}
private function AddError($error) {
array_push($this->mErrors, $error);
}
public function FetchItems($params,$itemPage,$maxPrice,$lookup=false)
{
$signedUrl = $this->urlBuilder->generate($params);
if($lookup)
{
try
{
$request = new CurlHttpRequest();
$response = $request->execute($signedUrl);
$fileContents = str_replace(array("\n", "\r", "\t"), '', $response);
$fileContents = trim(str_replace('"', "'", $fileContents));
$simpleXml = simplexml_load_string($fileContents);
$json = json_encode($simpleXml);
$decodedJson=json_decode($json,true);
//print_r($decodedJson);
print_r($decodedJson);
die();
$parsedXml = simplexml_load_string($response);
if ($parsedXml === false) {
return false;
}
return $this->dataTransformer->execute($parsedXml);
} catch(\Exception $error) {
$this->AddError("Error downloading data : $signedUrl : " . $error->getMessage());
return false;
}
}
else
{
try
{
$request = new CurlHttpRequest();
$response = $request->execute($signedUrl);
$fileContents = str_replace(array("\n", "\r", "\t"), '', $response);
$fileContents = trim(str_replace('"', "'", $fileContents));
$simpleXml = simplexml_load_string($fileContents);
$json = json_encode($simpleXml);
$decodedJson=json_decode($json,true);
print_r($decodedJson);
die();
if(isset($decodedJson['Items']))
{
$this->perRequest=0;
foreach($decodedJson['Items']['Item'] as $itm)
{
if(isset($itm['ItemAttributes']['ListPrice']['FormattedPrice']))
{
$this->item=$this->item+1;
$this->perRequest=$this->perRequest+1;
?>
<tr>
<td>
<?php
if(isset($itm['ItemAttributes']['Title']))
echo $itm['ItemAttributes']['Title'];
else
echo "N/A";
?>
</td>
<td>
<?php
if(isset($itm['ItemAttributes']['ListPrice']['FormattedPrice']))
echo $itm['ItemAttributes']['ListPrice']['FormattedPrice'];
else
echo "N/A";
?>
</td>
<?php
$savedAmount=0;
if(isset($itm['Offers']['Offer']['OfferListing']['Price']['FormattedPrice']))
{
?>
<td><?php echo $itm['Offers']['Offer']['OfferListing']['Price']['FormattedPrice']; ?></td>
<?php
if(isset($itm['Offers']['Offer']['OfferListing']['SalePrice']['FormattedPrice']))
{
$total=(int)($itm['ItemAttributes']['ListPrice']['Amount']);
$offer=(int)($itm['Offers']['Offer']['OfferListing']['SalePrice']['Amount']);
$savedAmount=$total-$offer;
$savedAmount=$savedAmount/100;
$savedAmount=$this->IND_money_format($savedAmount);
$savedAmount="INR ".$savedAmount.".00";
?>
<td><?php echo $itm['Offers']['Offer']['OfferListing']['SalePrice']['FormattedPrice']; ?></td>
<td><?php echo $savedAmount; ?></td>
<?php
}
else
{
$total=(int)($itm['ItemAttributes']['ListPrice']['Amount']);
$offer=(int)($itm['Offers']['Offer']['OfferListing']['Price']['Amount']);
$savedAmount=$total-$offer;
$savedAmount=$savedAmount/100;
$savedAmount=$this->IND_money_format($savedAmount);
$savedAmount="INR ".$savedAmount.".00";
?>
<td><?php echo $itm['Offers']['Offer']['OfferListing']['Price']['FormattedPrice']; ?></td>
<td><?php echo $savedAmount; ?></td>
<?php
}
}
else if(isset($itm['OfferSummary']['LowestNewPrice']['FormattedPrice']))
{
$total=(int)($itm['ListPrice']['Amount']);
$offer=(int)($itm['Offers']['Offer']['OfferListing']['SalePrice']['Amount']);
$savedAmount=$total-$offer;
$savedAmount=$savedAmount/100;
$savedAmount=$this->IND_money_format($savedAmount);
$savedAmount="INR ".$savedAmount.".00";
?>
<td><?php echo $itm['OfferSummary']['LowestNewPrice']['FormattedPrice']; ?></td>
<td><?php echo $itm['OfferSummary']['LowestNewPrice']['FormattedPrice']; ?></td>
<td><?php echo $savedAmount; ?></td>
<?php
}
else
{
?>
<td>N/A</td>
<td>N/A</td>
<td>N/A</td>
<?php
}
?>
<td>
<?php
if(isset($itm['ItemAttributes']['Brand']))
echo $itm['ItemAttributes']['Brand'];
else
echo "N/A";
?>
</td>
<td>
<?php
if(isset($itm['ItemAttributes']['Size']))
echo $itm['ItemAttributes']['Size'];
else
echo "N/A";
?>
</td>
<td>
<?php
if(isset($itm['ItemAttributes']['Color']))
echo $itm['ItemAttributes']['Color'];
else
echo "N/A";
?>
</td>
<td>
<?php
if(isset($itm['ItemAttributes']['Manufacturer']))
echo $itm['ItemAttributes']['Manufacturer'];
else
echo "N/A";
?>
</td>
</tr>
<?php
}
}
//return
//echo $maxPrice." : ".$decodedJson['Items']['TotalPages']."<br/>";
}
//echo "PerRequest : ".$this->perRequest."<br/>";
//die();
//$parsedXml = simplexml_load_string($response);
//if ($parsedXml === false) {
// return false;
//}
//return $this->dataTransformer->execute($parsedXml);
} catch(\Exception $error) {
$this->AddError("Error downloading data : $signedUrl : " . $error->getMessage());
return false;
}
}
}
private function MakeAndParseRequest($params,$itemPage,$lookup=false)
{
$this->item=0;
/*$style="";
for($looper=1;$looper<=$totalPages;$looper++)
{
if($looper>($itemPage-3) && $looper<($itemPage+3))
{
if($looper==$itemPage)
{
$style="style='color:red;'";
echo "<a href='examples.php?itemPage=".$looper."' ".$style.">".$looper."</a> ";
}
else
{
echo "<a href='examples.php?itemPage=".$looper."'>".$looper."</a> ";
}
}else if($looper>($totalPages-3))
{
echo "<a href='examples.php?itemPage=".$looper."'>".$looper."</a> ";
}else if($looper>(($totalPages/2)-3) && $looper<(($totalPages/2)+3))
{
echo "<a href='examples.php?itemPage=".$looper."'>".$looper."</a> ";
}
}
*/
}
}
?>
加载中,请稍侯......
精彩评论