0

我想从搜索词中使用来自 imdb 的 php 获取海报图片 url。例如，我有搜索词 21 Jump Street，我想取回图像 ur 或仅 imdb 电影 url。使用下面的代码，我只需要从搜索词中检索电影的 url

这是我的代码

<?php

    include("simple_html_dom.php");

//url to imdb page
$url = 'hereistheurliwanttogetfromsearch';

//get the page content
$imdb_content = file_get_contents($url);

$html = str_get_html($imdb_content);

$name = $html->find('title',0)->plaintext;

$director = $html->find('a[itemprop="director"]',0)->innertext;

$plot = $html->find('p[itemprop="description"]',0)->innertext;

$release_date = $html->find('time[itemprop="datePublished"]',0)->innertext;

$mpaa = $html->find('span[itemprop="contentRating"]',0)->innertext;

$run_time = $html->find('time[itemprop="duration"]',0)->innertext;

$img = $html->find('img[itemprop="image"]',0)->src;

$content = "";

//build content
$content.= '<h2>Film</h2><p>'.$name.'</p>';
$content.= '<h2>Director</h2><p>'.$director.'</p>';
$content.= '<h2>Plot</h2><p>'.$plot.'</p>';
$content.= '<h2>Release Date</h2><p>'.$release_date.'</p>';
$content.= '<h2>MPAA</h2><p>'.$mpaa.'</p>';
$content.= '<h2>Run Time</h2><p>'.$run_time.'</p>';
$content.= '<h2>Full Details</h2><p><a href="'.$url.'" rel="nofollow">'.$url.'</a></p>';
$content.= '<img src="'.$img.'" />';

echo $content;

?>
4

2 回答 2

2

使用 Kasper Mackenhauer Jacobsenless 建议的 API 可以得到更完整的答案：

$url = 'http://www.imdbapi.com/?i=&t=21+jump+street';

$json_response = file_get_contents($url);
$object_response = json_decode($json_response);

if(!is_null($object_response) && isset($object_response->Poster)) {
        $poster_url = $object_response->Poster;
        echo $poster_url."\n";
}
于 2012-05-10T22:23:00.070 回答
0

使用正则表达式进行解析很糟糕，但其中几乎没有什么可以破坏的。建议使用 curl 因为它更快，您可以屏蔽您的用户代理。

从搜索中获取图像的主要问题是您首先需要知道 IMDB ID，然后您才能加载页面并翻录图像 url。希望能帮助到你

<?php 
//Is form posted
if($_SERVER['REQUEST_METHOD']=='POST'){
    $find = $_POST['find'];

    //Get Imdb code from search
    $source = file_get_curl('http://www.imdb.com/find?q='.urlencode(strtolower($find)).'&s=tt');
    if(preg_match('#/title/(.*?)/mediaindex#',$source,$match)){
        //Get main page for imdb id
        $source = file_get_curl('http://www.imdb.com/title/'.$match[1]);
        //Grab the first .jpg image, which is always the main poster
        if(preg_match('#<img src=\"(.*).jpg\"#',$source,$match)){
            $imdb=$match[1];
            //do somthing with image
            echo '<img src="'.$imdb.'" />';
        }
    }
}

//The curl function
function file_get_curl($url){
(function_exists('curl_init')) ? '' : die('cURL Must be installed');
$curl = curl_init();
$header[0] = "Accept: text/xml,application/xml,application/xhtml+xml,";
$header[0] .= "text/html;q=0.9,text/plain;q=0.8,image/png,*/*;q=0.5";
$header[] = "Cache-Control: max-age=0";
$header[] = "Connection: keep-alive";
$header[] = "Keep-Alive: 300";
$header[] = "Accept-Charset: ISO-8859-1,utf-8;q=0.7,*;q=0.7";
$header[] = "Accept-Language: en-us,en;q=0.5";
$header[] = "Pragma: ";

curl_setopt($curl, CURLOPT_URL, $url);
curl_setopt($curl, CURLOPT_USERAGENT, 'Mozilla/5.0 (Windows NT 5.1; rv:5.0) Gecko/20100101 Firefox/5.0 Firefox/5.0');
curl_setopt($curl, CURLOPT_HTTPHEADER, $header);
curl_setopt($curl, CURLOPT_HEADER, true);
curl_setopt($curl, CURLOPT_REFERER, $url);
curl_setopt($curl, CURLOPT_ENCODING, 'gzip,deflate');
curl_setopt($curl, CURLOPT_AUTOREFERER, true);
curl_setopt($curl, CURLOPT_RETURNTRANSFER, true);
curl_setopt($curl, CURLOPT_TIMEOUT, 5);
curl_setopt($curl, CURLOPT_SSL_VERIFYPEER, false);

$html = curl_exec($curl);

$status = curl_getinfo($curl);
curl_close($curl);

if($status['http_code'] != 200){
    if($status['http_code'] == 301 || $status['http_code'] == 302) {
        list($header) = explode("\r\n\r\n", $html, 2);
        $matches = array();
        preg_match("/(Location:|URI:)[^(\n)]*/", $header, $matches);
        $url = trim(str_replace($matches[1],"",$matches[0]));
        $url_parsed = parse_url($url);
        return (isset($url_parsed))? file_get_curl($url):'';
    }
    return FALSE;
}else{
    return $html;
}
}
?>
<form method="POST" action="">
<p><input type="text" name="find" size="20"><input type="submit" value="Submit"></p>
</form>
于 2012-05-10T16:00:10.923 回答