当前位置 : 主页 > 网络编程 > PHP >

抓取豆瓣电影TOP250的PHP代码

来源:互联网 收集:自由互联 发布时间:2021-06-30
for ($start = 0; $start 250; $start += 25) { $url = "http://movie.douban.com/top250?start=$startfilter=type="; $titles = parsePage($url); if ($titles === false) { echo $url, "\n"; } else { array_walk($titles, 'printTitle'); }} function pars
for ($start = 0; $start < 250; $start += 25) {
    $url = "http://movie.douban.com/top250?start=$start&filter=&type=";
    $titles = parsePage($url);
    if ($titles === false) {
        echo $url, "\n";
    } else {
        array_walk($titles, 'printTitle');
    }
}
 
 
function parsePage($url) {
    $html = file_get_contents($url);
    if ($html === false) {
        return false;
    }
     
    if (preg_match_all('/<a.+?<span class="title">([^<]+)/s', $html, $matches) === false) {
        return false;
    }
     
    $titles = array();
    foreach($matches[1] as $item) {
        $titles[] = iconv('utf-8', 'gbk', $item);
    }
    return $titles;
}
 
 
$count = 0;
function printTitle($title) {
    global $count;
    ++$count;
    printf("%3d %s\n", $count, $title);
}
网友评论