public function parsePageType(XPathHelper $xph)
{
if ($xph->xpQuery("//div[@class='srListing']") !== null) {
return "searchResult";
}
if (true) {
//FIXME detect product
return "product";
}
//FIXME: detect no result
}
public function parsePageType(XPathHelper $xph)
{
if (null !== $xph->xpQuery("//*[@id='noResultsTitle']")) {
return "searchResult";
}
if (null !== $xph->xpQuery("//*[@id='s-result-count']")) {
return "searchResult";
}
if (null !== $xph->xpQuery("//*[@id='atfResults']")) {
return "searchResult";
}
if (null !== $xph->xpQuery("//div[@id='product-title_feature_div']/div[@class='buying'] | //form[@id='handleBuy']/div[@class='buying']")) {
return "product";
}
// TODO: fix this
//if ('Robot Check' == $xph->queryValue("//html/body/title/text()", 1))
return "captcha";
// default, save for analysis
$ci =& get_instance();
$html_contents = "\n\n----------------------------------------------------------\n" . date('Y-m-d H:i:s') . "\n" . $xph->dump();
file_put_contents($ci->config->item('file_root') . "output.amazon.failed.parse.txt", $html_contents, FILE_APPEND);
throw new Exception(__FUNCTION__ . ": unexpected page type at " . $xph->__toString());
}