Phpスクレーパーのデータをタグ間でのみ抽出

Question

<a>タグの間でデータをスクラップする必要があるスクレーパーを作成しようとしています。コードを少し変更して、間にデータを抽出しました。ここにコードがあります。

<?php 

    function scrape_between($data, $start, $end){ 
    $data = stristr($data, $start); 
    $data = substr($data, strlen($start)); 
    $stop = strpos($data, $end); 
    $data = substr($data, 0, $stop); 
    return $data; 
} 

function cURL($url) { 
    $options = array(
     CURLOPT_RETURNTRANSFER => TRUE, 
     CURLOPT_FOLLOWLOCATION => TRUE, 
     CURLOPT_AUTOREFERER => TRUE, 
     CURLOPT_CONNECTTIMEOUT => 120, 
     CURLOPT_MAXREDIRS => 10, 
     CURLOPT_USERAGENT => "Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.1) Gecko/20061204 Firefox/2.0.0.1", 
     CURLOPT_URL => $url, 
    ); 
    $ch = curl_init(); 
    curl_setopt_array($ch, $options); 
    $data = curl_exec($ch); 
    curl_close($ch); 
    return $data; 
} 
    $url = "http://www.imdb.com/search/title?genres=action"; 
    $results_page = curl($url); 
    $results_page = scrape_between($results_page, "<div id=\"main\">", "<div id=\"sidebar\">"); 
    $separate_results = explode("<td class=\"title\">", $results_page); 
    foreach ($separate_results as $separate_result) { 
     if ($separate_result != " ") { 
     $results_urls[] = "http://www.imdb.com " . scrape_between($separate_result, "<a href=", "a>"); 
     } 
    } 
    print_r($results_urls); 
?> 

私が探しているのは、データを映画のタイトルのリスト形式にすることです。私が正規表現についてここで使用されるかどうかは十分に分かっていないので、これを達成する適切な方法は何か。

Answer 1

これは役に立ちます。

これは（任意 タグの内部HTMLコンテンツとattibute値を抽出するための別 機能と[PHP DOMDocumentとcurlを使用してPHP配列 にIMDB映画メタ値（例：画像、タイトルや概要）をフェッチ。

<?php 

$dom = new DOMDocument; 

function disguise_curl($url) 
{ 
    $curl = curl_init(); 
    curl_setopt($curl, CURLOPT_URL, $url); 
    curl_setopt($curl, CURLOPT_AUTOREFERER, true); 
    curl_setopt($curl, CURLOPT_RETURNTRANSFER, true); 
    $html= curl_exec($curl); 
    if($html=== false) 
    { 
     if($errno = curl_errno($curl)){ 
     $error_message = curl_strerror($errno); 
     $html= "cURL error ({$errno}): {$error_message}\n"; 
     } 
    } 
    curl_close($curl); 

    return $html; 
} 

function scrape_between($data, $start, $end){ 
     $data = stristr($data, $start); 
     $data = substr($data, strlen($start)); 
     $stop = stripos($data, $end); 
     $data = substr($data, 0, $stop); 
     return $data; 
    } 

function getHTMLByID($id, $html) { 
    $dom = new DOMDocument; 
    libxml_use_internal_errors(true); 
    $dom->validateOnParse = true; 
    $dom->loadHTML($html); 
    $node = $dom->getElementById($id); 
    if($node) { 
     return $dom->saveHTML($node); 
    } 
    return FALSE; 
} 

function getHTMLByClass($class, $html, $bring_tag=false){ 
    $dom = new DOMDocument; 
    libxml_use_internal_errors(true); 
    $dom->validateOnParse = true; 
    $dom->loadHTML($html); 
    $class_arr= array(); 
    $xpath= new DOMXPath($dom); 
    $results = $xpath->query("//*[contains(@class, '$class')]"); 
    if($results->length > 0){ 
     foreach($results as $tag) 
     { 
      if($bring_tag===true) 
       array_push($class_arr, $tag); 
      else 
       array_push($class_arr, $dom->saveHTML($tag)); 
     } 
    }  
    return $class_arr; 
} 

function get_domattr($html, $tag, $attr) 
{ 
    $attr_vals= array(); 
    if(!empty($html)) 
    { 
    $dom = new DOMDocument; 
    libxml_use_internal_errors(true); 
    $dom->validateOnParse = true; 
    $dom->loadHTML($html); 
    foreach($dom->getElementsByTagName($tag) as $img) 
    array_push($attr_vals, $img->getAttribute($attr)); 
    } 
    return $attr_vals; 
} 

function getHTMLByTag($tag, $html) { 
    $attr_vals= array(); 
    if(!empty($html)) 
    { 
    global $dom; 
    libxml_use_internal_errors(true); 
    $dom->validateOnParse = true; 
    $dom->loadHTML($html); 

    foreach($dom->getElementsByTagName($tag) as $taghtml) 
     array_push($attr_vals, $dom->saveXML($taghtml)); 
    } 
    return $attr_vals; 
} 

$url= "http://www.imdb.com/search/title?genres=action"; 
$page_html= disguise_curl($url); 


$result_html= getHTMLByClass('image', $page_html); 

$movie_list= array(); 
$i=0; 
foreach($result_html as $cont_tag) 
{ 
    $img_link= get_domattr($cont_tag, 'img', 'src'); 
    if((!isset($img_link)) || (empty($img_link))) 
     $movie_list[$i]['photo']= 'na'; 
    else 
     $movie_list[$i]['photo']= $img_link[0]; 

    ++$i; 
} 

$result_html= getHTMLByClass('title', $page_html); 
$link_pre= 'http://imdb.com'; 

$i=0; 
foreach($result_html as $cont_tag) 
{ 
    $mtitle= getHTMLByTag('a', $cont_tag); 
    if((!isset($mtitle)) || (empty($mtitle))) 
     $movie_list[$i]['title']= 'na'; 
    else 
     $movie_list[$i]['title']= $mtitle[0]; 

    $mlink= get_domattr($cont_tag, 'a', 'href'); 
    if((!isset($mlink)) || (empty($mlink))) 
     $movie_list[$i]['link']= 'na'; 
    else 
     $movie_list[$i]['link']= $link_pre.''.$mlink[0]; 


    $moutline= getHTMLByClass('outline', $cont_tag); 
    if((!isset($moutline)) || (empty($moutline))) 
     $movie_list[$i]['outline']= 'na'; 
    else 
     $movie_list[$i]['outline']= $moutline[0]; 




    ++$i; 
} 

echo '<pre>'; 
print_r($movie_list); 
echo '</pre>'; 
?> 

サンプル出力：

Array 
(
    [0] => Array 
     (
      [photo] => http://ia.media-imdb.com/images/M/MV5BMjQ0MTgyNjAxMV5BMl5BanBnXkFtZTgwNjUzMDkyODE@._V1._SX54_CR0,0,54,74_.jpg 
      [title] => Captain America: Civil War 
      [link] => http://imdb.com/title/tt3498820/ 
      [outline] => Political interference in the Avengers' activities causes a rift between former allies Captain America and Iron Man. 
     ) 

    [1] => Array 
     (
      [photo] => http://ia.media-imdb.com/images/M/MV5BNTE5NzU3MTYzOF5BMl5BanBnXkFtZTgwNTM5NjQxODE@._V1._SX54_CR0,0,54,74_.jpg 
      [title] => Batman v Superman: Dawn of Justice 
      [link] => http://imdb.com/title/tt2975590/ 
      [outline] => Fearing the actions of Superman are left unchecked, Batman takes on the man of steel, while the world wrestles with what kind of a hero it really needs. With Batman and Superman fighting each other, a new threat, Doomsday, is created by Lex Luthor. It's up to Superman and Batman to set aside their differences along with Wonder Woman to stop Lex Luthor and Doomsday from destroying Metropolis. 
     ) 

    [2] => Array 
     (
      [photo] => http://ia.media-imdb.com/images/M/MV5BMTY0MDY0NjExN15BMl5BanBnXkFtZTgwOTU3OTYyODE@._V1._SX54_CR0,0,54,74_.jpg 
      [title] => na 
      [link] => na 
      [outline] => na 
     ) 
) 

マッチングID、タグ名およびクラス）]によって