91亚洲精华国内精华精华液_国产高清在线精品一区不卡_精品特级一级毛片免费观看_欧美日韩中文制服有码_亚洲精品无码你懂的网站369

/**
 * 爬蟲程序 -- 原型
 *
 * 從給定的url獲取html內(nèi)容
 *
 * @param string $url
 * @return string
 */
function _getUrlContent($url) {
    $handle = fopen($url, "r");
    if ($handle) {
        $content = stream_get_contents($handle, 1024 * 1024);
        return $content;
    } else {
        return false;
    }
}
/**
 * 從html內(nèi)容中篩選鏈接
 *
 * @param string $web_content
 * @return array
 */
function _filterUrl($web_content) {
    $reg_tag_a = '/<[a|A].*?href=[\'\"]{0,1}([^>\'\"\ ]*).*?>/';
    $result = preg_match_all($reg_tag_a, $web_content, $match_result);
    if ($result) {
        return $match_result[1];
    }
}
/**
 * 修正相對(duì)路徑
 *
 * @param string $base_url
 * @param array $url_list
 * @return array
 */
function _reviseUrl($base_url, $url_list) {
    $url_info = parse_url($base_url);
    $base_url = $url_info["scheme"] . '://';
    if ($url_info["user"] && $url_info["pass"]) {
        $base_url .= $url_info["user"] . ":" . $url_info["pass"] . "@";
    }
    $base_url .= $url_info["host"];
    if ($url_info["port"]) {
        $base_url .= ":" . $url_info["port"];
    }
    $base_url .= $url_info["path"];
    print_r($base_url);
    if (is_array($url_list)) {
        foreach ($url_list as $url_item) {
            if (preg_match('/^http/', $url_item)) {
                // 已經(jīng)是完整的url
                $result[] = $url_item;
            } else {
                // 不完整的url
                $real_url = $base_url . '/' . $url_item;
                $result[] = $real_url;
            }
        }
        return $result;
    } else {
        return;
    }
}
/**
 * 爬蟲
 *
 * @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 ;
    }
}
/**
 * 測(cè)試用主程序
 */
function main() {
    $current_url = "http://hao123.com/"; //初始url
    $fp_puts = fopen("url.txt", "ab"); //記錄url列表
    $fp_gets = fopen("url.txt", "r"); //保存url列表
    do {
        $result_url_arr = crawler($current_url);
        if ($result_url_arr) {
            foreach ($result_url_arr as $url) {
                fputs($fp_puts, $url . "\r\n");
            }
        }
    } while ($current_url = fgets($fp_gets, 1024)); //不斷獲得url
}
main();
 
?>

?

穩(wěn)定

產(chǎn)品高可用性高并發(fā)

貼心

項(xiàng)目群及時(shí)溝通

專業(yè)

產(chǎn)品經(jīng)理1v1支持

快速

MVP模式小步快跑

承諾

我們選擇聲譽(yù)

堅(jiān)持

10年專注高端品質(zhì)開發(fā)
  • 返回頂部