Question

我有两张桌子＆＃34; product_title＆＃34;拥有产品名称和＆＃34; product_list_url＆＃34;有产品清单页面的网址。我想从产品标题表中获取标题并获取并逐个转到每个URL并在页面上搜索相同的标题，如果找到，则提取一些数据并保存到数据库中。

我想检查每个网址上的每个产品。但无法获得所需的结果。

这是我的代码..

<?php
set_time_limit(0);
$dbhost = "localhost";
$dbuser = "root";
$dbpass = "";
$dbname = "crawl";
$conn = mysql_connect($dbhost, $dbuser, $dbpass) or die ("Error connecting to database");
mysql_select_db($dbname, $conn);
$q1 = mysql_query("SELECT * FROM `product-title`");
$q2 = mysql_query("SELECT * FROM `product-list-url`");
while($res1 = mysql_fetch_assoc($q1)){
    $product_title = $res1['title'];
    while($res2 = mysql_fetch_assoc($q2)){
        $url = $res2['url'];
        $html = file_get_contents($url);        
        $doc = new DOMDocument(); 
        @$doc->loadHTML($html);     
        $xpath = new DOMXPath($doc);
        $found = $xpath->evaluate("boolean(//span[contains(text(), '$product_title')])");
        if($found == false){
            echo "Not Found";       
        }

        else{ 
            $elements = $xpath->evaluate("//span[contains(text(), '$product_title' )]/following-sibling::div/span[@class='list_sale_price']");
            if (!is_null($elements)) {
                foreach ($elements as $element) {
                    $nodes = $element->childNodes;
                    foreach ($nodes as $node) {
                        $price = $node->nodeValue;
                        $price1 = preg_replace('/[^0-9-.]/','',$price);
                        $date = date('y-m-d');
                        mysql_query("INSERT INTO `prices` (`ptitle`, `price`, `date`) VALUES ('$product_title', '$price1', '$date')") or die(mysql_error());                    
                    }
                }
            }   
        }
    }
} 

?>

它只为第一个标题插入一条记录。

Answer 1

首先，mysql_的使用不好since it'll be deprecated。关于主题，我认为您正在寻找JOIN的答案。您的表product-title必须对每种产品都有某种唯一的ID吗？我假设您的product-list-url表也与第一个表中的产品具有匹配的ID。由于我没有任何表格结构，我会给你举例。

SELECT t1.title
     , t2.url
FROM `product-title` t1
JOIN `product-list-url` t2 ON t1.id = t2.id

Answer 2

重置指针可能允许您在第一个产品标题后处理记录。未经测试，也未检查过您的文档处理。

<?php
set_time_limit(0);
$dbhost = "localhost";
$dbuser = "root";
$dbpass = "";
$dbname = "crawl";
$conn = mysql_connect($dbhost, $dbuser, $dbpass) or die ("Error connecting to database");
mysql_select_db($dbname, $conn);
$q1 = mysql_query("SELECT * FROM `product-title`");
$q2 = mysql_query("SELECT * FROM `product-list-url`");
while($res1 = mysql_fetch_assoc($q1))
{
    $product_title = $res1['title'];
    while($res2 = mysql_fetch_assoc($q2))
    {
        $url = $res2['url'];
        $html = file_get_contents($url);        
        $doc = new DOMDocument(); 
        @$doc->loadHTML($html);     
        $xpath = new DOMXPath($doc);
        $found = $xpath->evaluate("boolean(//span[contains(text(), '$product_title')])");
        if($found == false)
        {
            echo "Not Found";       
        }

        else
        { 
            $elements = $xpath->evaluate("//span[contains(text(), '$product_title' )]/following-sibling::div/span[@class='list_sale_price']");
            if (!is_null($elements)) {
                foreach ($elements as $element) {
                    $nodes = $element->childNodes;
                    foreach ($nodes as $node) {
                        $price = $node->nodeValue;
                        $price1 = preg_replace('/[^0-9-.]/','',$price);
                        $date = date('y-m-d');
                        mysql_query("INSERT INTO `prices` (`ptitle`, `price`, `date`) VALUES ('$product_title', '$price1', '$date')") or die(mysql_error());                    
                    }
                }
            }   
        }
    }
    mysql_data_seek($q2, 0);
} 

?>

然而，将标题列表读入内存可能更有效，然后处理每个文件一次，多次检查内容。每个标题一次。

这样的事情： -

<?php
set_time_limit(0);
$dbhost = "localhost";
$dbuser = "root";
$dbpass = "";
$dbname = "crawl";
$conn = mysql_connect($dbhost, $dbuser, $dbpass) or die ("Error connecting to database");
mysql_select_db($dbname, $conn);
$product_titles = array();
$q1 = mysql_query("SELECT * FROM `product-title`");
while($res1 = mysql_fetch_assoc($q1))
{
    $product_titles[] = $res1['title'];
}
$q2 = mysql_query("SELECT * FROM `product-list-url`");

while($res2 = mysql_fetch_assoc($q2))
{
    $url = $res2['url'];
    $html = file_get_contents($url);        
    $doc = new DOMDocument(); 
    @$doc->loadHTML($html);     
    $xpath = new DOMXPath($doc);
    foreach($product_titles as $product_title)
    {
        $found = $xpath->evaluate("boolean(//span[contains(text(), '$product_title')])");
        if($found == false)
        {
            echo "Not Found";       
        }

        else
        { 
            $elements = $xpath->evaluate("//span[contains(text(), '$product_title' )]/following-sibling::div/span[@class='list_sale_price']");
            if (!is_null($elements)) 
            {
                foreach ($elements as $element) 
                {
                    $nodes = $element->childNodes;
                    foreach ($nodes as $node) 
                    {
                        $price = $node->nodeValue;
                        $price1 = preg_replace('/[^0-9-.]/','',$price);
                        $date = date('y-m-d');
                        mysql_query("INSERT INTO `prices` (`ptitle`, `price`, `date`) VALUES ('$product_title', '$price1', '$date')") or die(mysql_error());                    
                    }
                }
            }   
        }
    }
}

?>

从一个表（mysql）获取每个标题并从另一个表中获取url并使用title在每个url上提取数据

2 个答案: