我试图有点偷偷摸摸,作为学习过程的一部分,尝试并提高我的页面抓取技巧.
我遇到的一件事我还没有能够解决的问题是,某些网站会使用内部链接,然后重定向到外部链接.
我想要做的是修改一些卷曲代码以遵循重定向,直到它们停止然后获得最终的静止位置URL.
有人为我推荐一些代码吗?
我现在有这个,但目前还没有正确地遵循重定向.
$opts = array(CURLOPT_URL => $url,
CURLOPT_RETURNTRANSFER => true,
CURLOPT_HEADER => true,
CURLOPT_FOLLOWLOCATION => true);
$curl = curl_init();
curl_setopt_array($curl, $opts);
$str = curl_exec($curl);
curl_close($curl);
Run Code Online (Sandbox Code Playgroud)
Man*_*Raj 23
http.//php.net/manual/en/ref.curl.php
function get_final_url( $url, $timeout = 5 )
{
$url = str_replace( "&", "&", urldecode(trim($url)) );
$cookie = tempnam ("/tmp", "CURLCOOKIE");
$ch = curl_init();
curl_setopt( $ch, CURLOPT_USERAGENT, "Mozilla/5.0 (Windows; U; Windows NT 5.1; rv:1.7.3) Gecko/20041001 Firefox/0.10.1" );
curl_setopt( $ch, CURLOPT_URL, $url );
curl_setopt( $ch, CURLOPT_COOKIEJAR, $cookie );
curl_setopt( $ch, CURLOPT_FOLLOWLOCATION, true );
curl_setopt( $ch, CURLOPT_ENCODING, "" );
curl_setopt( $ch, CURLOPT_RETURNTRANSFER, true );
curl_setopt( $ch, CURLOPT_AUTOREFERER, true );
curl_setopt( $ch, CURLOPT_CONNECTTIMEOUT, $timeout );
curl_setopt( $ch, CURLOPT_TIMEOUT, $timeout );
curl_setopt( $ch, CURLOPT_MAXREDIRS, 10 );
$content = curl_exec( $ch );
$response = curl_getinfo( $ch );
curl_close ( $ch );
if ($response['http_code'] == 301 || $response['http_code'] == 302)
{
ini_set("user_agent", "Mozilla/5.0 (Windows; U; Windows NT 5.1; rv:1.7.3) Gecko/20041001 Firefox/0.10.1");
$headers = get_headers($response['url']);
$location = "";
foreach( $headers as $value )
{
if ( substr( strtolower($value), 0, 9 ) == "location:" )
return get_final_url( trim( substr( $value, 9, strlen($value) ) ) );
}
}
if ( preg_match("/window\.location\.replace\('(.*)'\)/i", $content, $value) ||
preg_match("/window\.location\=\"(.*)\"/i", $content, $value)
)
{
return get_final_url ( $value[1] );
}
else
{
return $response['url'];
}
}
Run Code Online (Sandbox Code Playgroud)
归档时间: |
|
查看次数: |
24202 次 |
最近记录: |