PHP _filterUrl示例

示例#1

文件： index.php 项目： qigge/Spider

/**
 * 爬虫
 * @param  string $url 
 * @return array  
 */
function spider($url)
{
    $html = _getHtmlFromUrl($url);
    if ($html) {
        $url_list = _reviseUrl($url, _filterUrl($html));
        if ($url_list) {
            return $url_list;
        } else {
            return;
        }
    } else {
        return;
    }
}

示例#2

文件： crawler.php 项目： happyer-lwl/DreamShipServer

/**
 * 爬虫
 * 
 * @param string $url 
 * @return array 
 */
function crawler($url)
{
    $content = _getUrlContent($url);
    if ($content) {
        $url_list = _reviseUrl($url, _filterUrl($content));
        if ($url_list) {
            return $url_list;
        } else {
            return;
        }
    } else {
        return;
    }
}

示例#3

文件： catch_img.php 项目： emocheng/catch_img

/**
* 测试
*/
function main()
{
    $url = 'http://www.nipic.com/';
    $handle = fopen($url, "r");
    if ($handle) {
        $content = stream_get_contents($handle, 1024 * 1024);
        $result = _filterUrl($content);
        //获取到图片的url
        //var_dump($result);
        foreach ($result as $key => $value) {
            $a = GrabImage($value);
            var_dump($a);
        }
    } else {
        return false;
    }
}

示例#4

文件： crawler.php 项目： AkihiJef/rookie_search_engine

function crawler($id, $url)
{
    $content = _curl_get_file_contents($url);
    _save($id, $url, $content);
    if ($content) {
        $url_list = _reviseUrl($url, _filterUrl($content));
        if ($url_list) {
            return $url_list;
        } else {
            return;
        }
    } else {
        return;
    }
}