Question

通过Curl我已经解析了网站。但是当我运行foreach循环时，当它进入mysql DB时，它会取出最后一个值。我理解，因为DB中的插入不在循环中，所以循环将处理db中的最后一个值。但是当我在循环中输入插入查询时，它会在每一行的左侧输入值。但我需要一行中的所有值。示例代码在这里，删除了许多字段。

希望，我能够解释问候 Rishabh :) 示例链接是：http://www.dvdempire.com/trending-blu-ray.html?page=1 要删除页面的详细信息为：http://www.dvdempire.com/1699319/300-rise-of-an-empire-blu-ray-dvd-ultraviolet-blu-ray.html

<?php
set_time_limit(0);
    for ($x=1; $x<=2; $x++) {
    $userAgent = 'Googlebot/2.1 (http://www.googlebot.com/bot.html)';
     sleep(1);
    $target_url = "http://www.dvdempire.com/trending-blu-ray.html?page=$x" ;

    $ch = curl_init();

    curl_setopt($ch, CURLOPT_USERAGENT, $userAgent);
    curl_setopt($ch, CURLOPT_URL,$target_url);
    curl_setopt($ch, CURLOPT_FAILONERROR, true);
    curl_setopt($ch, CURLOPT_FOLLOWLOCATION, true);
    curl_setopt($ch, CURLOPT_AUTOREFERER, true);
    curl_setopt($ch, CURLOPT_RETURNTRANSFER,true);
    curl_setopt($ch, CURLOPT_TIMEOUT, 13300000);
    $html= curl_exec($ch);
    if (!$html) {
        echo "<br />cURL error number:" .curl_errno($ch);
        echo "<br />cURL error:" . curl_error($ch);
        exit;
    }
    // parse the html into a DOMDocument
    $dom = new DOMDocument();
    @$dom->loadHTML($html);
    $xpath = new DOMXPath( $dom );
    $query21 = '//div[@class="container"]//p[@class="title"]//a';

    $nodes21 = $xpath->query( $query21 );

    foreach( $nodes21 as $node21 )
    {

    $target_url12=$node21->getAttribute('href');
     $target_url1 ="http://www.dvdempire.com$target_url12" ;
    curl($target_url1) ;
    }
}

        function curl($target_url1) {
        //Sigle Page Scraping 
        global $userAgent ;
        $userAgent = 'Googlebot/2.1 (http://www.googlebot.com/bot.html)';
        //$target_url1 = "http://www.dvdempire.com/1695169/3-days-to-kill-blu-ray-dvd-ultraviolet-blu-ray.html";
        $ch1 = curl_init();

        curl_setopt($ch1, CURLOPT_USERAGENT, $userAgent);
        curl_setopt($ch1, CURLOPT_URL,$target_url1);
        curl_setopt($ch1, CURLOPT_FAILONERROR, true);
        curl_setopt($ch1, CURLOPT_FOLLOWLOCATION, true);
        curl_setopt($ch1, CURLOPT_AUTOREFERER, true);
        curl_setopt($ch1, CURLOPT_RETURNTRANSFER,true);
        curl_setopt($ch1, CURLOPT_TIMEOUT, 13300000);
        $html1= curl_exec($ch1);
        if (!$html1) {
            echo "<br />cURL error number:" .curl_errno($ch1);
            echo "<br />cURL error:" . curl_error($ch1);
            exit;
        }
        // parse the html into a DOMDocument
        $dom = new DOMDocument();
        @$dom->loadHTML($html1);
        $xpath = new DOMXPath( $dom );

        $query1 = '//div[@id="GeneralInformation"]//div[@class="Section Synopsis"]//p';  // Synopsis
        $query2 = '//div[@class="subsection"]//time[@itemprop="duration"]';  // length
        $query7 = '//div[@class="Section Cast"]//li[@itemprop="actor"]//span[@itemprop="name"]';              //cast
        $query8 = '//div[@class="Section Cast"]//li[@itemprop="producer"]//span[@itemprop="name"]';  // Producer
        $query9 = '//div[@class="Section Cast"]//li[@itemprop="director"]//span[@itemprop="name"]';  // Director
        $query10 = '//div[@class="Section ProductInfo"]';  // For UPC Code

        $nodes1 = $xpath->query( $query1 );
        $nodes2 = $xpath->query( $query2 );
        $nodes7 = $xpath->query( $query7 );
        $nodes8 = $xpath->query( $query8 );
        $nodes9 = $xpath->query( $query9 );
        $nodes10 = $xpath->query( $query10 );

            //Synopsis
            echo "---------------  Synopsis --------------- "  ;
            foreach( $nodes1 as $node1 )
            {
           echo     $a1=$node1->nodeValue;
                }
            echo "<br>" ;

            // length
            echo "---------------  Length  --------------- "  ;
            foreach( $nodes2 as $node2 )
            {
            echo    $a2=$node2->nodeValue;
                }
            echo "<br>" ;
            echo "-------------- Cast --------------- "  ;
            foreach( $nodes7 as $node7 )
            {
            $a7=$node7->nodeValue;
            echo $a7 = $a7.",";
            }
            echo "<br>" ;

            echo "-------------- Producer --------------- "  ;
            foreach( $nodes8 as $node8 )
            {
                $a8=$node8->nodeValue;
            echo $a8 = $a8.",";
            }
            echo "<br>" ;
            echo "-------------- Director  --------------- "  ;
            foreach( $nodes9 as $node9 )
            {
             $a9=$node9->nodeValue;
            echo $a9 =  $a9.",";
            }
            echo "<hr>" ;

//数据库插入 / * $ con = mysql_connect（“localhost”，“root”，“”）; if（！$ con） { 死（'无法连接：'。mysql_error（））; } mysql_select_db（“dvd”，$ con）;

$sql="INSERT INTO data (synopsis,length,rating,cast,producer,director)
VALUES
('$a1','$a2','$a7','$a8','$a9')";
if (!mysql_query($sql,$con))
  {
  die('Error: ' . mysql_error());
  }
mysql_close($con) ; 
 */

} ？＆GT;

Answer 1

这有点粗糙，但我会这样做。虽然我肯定会使用使用PDO的预处理语句，而不是mysql_ *，因为这些函数已被弃用。但这又是另一个话题。

现在......这就是我在这种特殊情况下的表现......

$values=array();    

foreach( $nodes1 as $node1 )
        {
           echo     $a1=$node1->nodeValue;
           $values[]["Synopsis"] = $a1; 
        }
        echo "<br>" ;
        echo "---------------  Length  --------------- "  ;
        foreach( $nodes2 as $node2 )
        {
        echo    $a2=$node2->nodeValue;
        $values[]["Length"] = $a2; 
        }
        echo "<br>" ;
        echo "-------------- Cast --------------- "  ;
        foreach( $nodes7 as $node7 )
        {
        $a7=$node7->nodeValue;
        echo $a7 = $a7.",";
        $values[]["Cast"] = $a7; 
        }
        echo "<br>" ;
        echo "-------------- Producer --------------- "  ;
        foreach( $nodes8 as $node8 )
        {
            $a8=$node8->nodeValue;
        echo $a8 = $a8.",";
        $values[]["Producer"] = $a8; 
        }
        echo "<br>" ;
        echo "-------------- Director  --------------- "  ;
        foreach( $nodes9 as $node9 )
        {
         $a9=$node9->nodeValue;
        echo $a9 =  $a9.",";
        $values[]["Director"] = $a9; 
        }
        echo "<hr>" ;

然后这样做......

        $string="";
        //Loop through your values and build the query string
        foreach($values as $v){
         $string.="(".$v['Synopsis'].",".$v['Length'].",".$v['Cast'].",".$v['Producer'].",".$v['Director']."),";
        }
        //Trim the last comma off the string
        rtrim($string,',');

        //Append to your query and then execute 
        $sql="INSERT INTO data (synopsis,length,cast,producer,director) VALUES ".$string;

PHP中的Webscraper，

1 个答案: