基于PHP的cURL快速入门教程 (小偷采集程序)

// CONFIG
$db_host = 'localhost';
$db_user = 'root';
$db_pass = '';
$db_name = 'wordpress';
$excluded_domains = array(
    'localhost', 'www.mydomain.com');
$max_connections = 10;
// 初始化一些变量
$url_list = array();
$working_urls = array();
$dead_urls = array();
$not_found_urls = array();
$active = null;
// 连到 MySQL
if (!mysql_connect($db_host, $db_user, $db_pass)) {
    die('Could not connect: ' . mysql_error());
}
if (!mysql_select_db($db_name)) {
    die('Could not select db: ' . mysql_error());
}
// 找出所有含有链接的文章
$q = "SELECT post_content FROM wp_posts
    WHERE post_content LIKE '%href=%'
    AND post_status = 'publish'
    AND post_type = 'post'";
$r = mysql_query($q) or die(mysql_error());
while ($d = mysql_fetch_assoc($r)) {
    // 用正则匹配链接
    if (preg_match_all("!href=\"(.*?)\"!", $d['post_content'], $matches)) {
        foreach ($matches[1] as $url) {
            // exclude some domains
            $tmp = parse_url($url);
            if (in_array($tmp['host'], $excluded_domains)) {
                continue;
            }
            // store the url
            $url_list []= $url;
        }
    }
}
// 移除重复链接
$url_list = array_values(array_unique($url_list));
if (!$url_list) {
    die('No URL to check');
}

// 1. 批处理器
$mh = curl_multi_init();
// 2. 加入需批量处理的URL
for ($i = 0; $i < $max_connections; $i++) {
    add_url_to_multi_handle($mh, $url_list);
}
// 3. 初始处理
do {
    $mrc = curl_multi_exec($mh, $active);
} while ($mrc == CURLM_CALL_MULTI_PERFORM);
// 4. 主循环
while ($active && $mrc == CURLM_OK) {
    // 5. 有活动连接
    if (curl_multi_select($mh) != -1) {
        // 6. 干活
        do {
            $mrc = curl_multi_exec($mh, $active);
        } while ($mrc == CURLM_CALL_MULTI_PERFORM);
        // 7. 有信息否？
        if ($mhinfo = curl_multi_info_read($mh)) {
            // 意味着该连接正常结束
            // 8. 从curl句柄获取信息
            $chinfo = curl_getinfo($mhinfo['handle']);
            // 9. 死链么？
            if (!$chinfo['http_code']) {
                $dead_urls []= $chinfo['url'];
            // 10. 404了?
            } else if ($chinfo['http_code'] == 404) {
                $not_found_urls []= $chinfo['url'];
            // 11. 还能用
            } else {
                $working_urls []= $chinfo['url'];
            }
            // 12. 移除句柄
            curl_multi_remove_handle($mh, $mhinfo['handle']);
            curl_close($mhinfo['handle']);
            // 13. 加入新URL，干活
            if (add_url_to_multi_handle($mh, $url_list)) {
                do {
                    $mrc = curl_multi_exec($mh, $active);
                } while ($mrc == CURLM_CALL_MULTI_PERFORM);
            }
        }
    }
}
// 14. 完了
curl_multi_close($mh);
echo "==Dead URLs==\n";
echo implode("\n",$dead_urls) . "\n\n";
echo "==404 URLs==\n";
echo implode("\n",$not_found_urls) . "\n\n";
echo "==Working URLs==\n";
echo implode("\n",$working_urls);
// 15. 向批处理器添加url
function add_url_to_multi_handle($mh, $url_list) {
    static $index = 0;
    // 如果还剩url没用
    if ($url_list[$index]) {
        // 新建curl句柄
        $ch = curl_init();
        // 配置url
        curl_setopt($ch, CURLOPT_URL, $url_list[$index]);
        // 不想输出返回的内容
        curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
        // 重定向到哪儿我们就去哪儿
        curl_setopt($ch, CURLOPT_FOLLOWLOCATION, 1);
        // 不需要内容体，能够节约带宽和时间
        curl_setopt($ch, CURLOPT_NOBODY, 1);
        // 加入到批处理器中
        curl_multi_add_handle($mh, $ch);
        // 拨一下计数器，下次调用该函数就能添加下一个url了
        $index++;
        return true;
    } else {
        // 没有新的URL需要处理了
        return false;
    }
}

<img border="0" src="/upload/201106/20110602225008534.png" />

$url = "http://www.somesite.com/members/";
$ch = curl_init();
curl_setopt($ch, CURLOPT_URL, $url);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
// 发送用户名和密码
curl_setopt($ch, CURLOPT_USERPWD, "myusername:mypassword");
// 你可以允许其重定向
curl_setopt($ch, CURLOPT_FOLLOWLOCATION, 1);
// 下面的选项让 cURL 在重定向后
// 也能发送用户名和密码
curl_setopt($ch, CURLOPT_UNRESTRICTED_AUTH, 1);
$output = curl_exec($ch);
curl_close($ch);

// 开一个文件指针
$file = fopen("/path/to/file", "r");
// url里包含了大部分所需信息
$url = "ftp://username:password@mydomain.com:21/path/to/new/file";
$ch = curl_init();
curl_setopt($ch, CURLOPT_URL, $url);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
// 上传相关的选项
curl_setopt($ch, CURLOPT_UPLOAD, 1);
curl_setopt($ch, CURLOPT_INFILE, $fp);
curl_setopt($ch, CURLOPT_INFILESIZE, filesize("/path/to/file"));
// 是否开启ASCII模式 (上传文本文件时有用)
curl_setopt($ch, CURLOPT_FTPASCII, 1);
$output = curl_exec($ch);
curl_close($ch);

$ch = curl_init();
curl_setopt($ch, CURLOPT_URL,'http://www.example.com');
curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
// 指定代理地址
curl_setopt($ch, CURLOPT_PROXY, '11.11.11.11:8080');
// 如果需要的话，提供用户名和密码
curl_setopt($ch, CURLOPT_PROXYUSERPWD,'user:pass');
$output = curl_exec($ch);
curl_close ($ch);

$ch = curl_init();
curl_setopt($ch, CURLOPT_URL,'http://net.tutsplus.com');
curl_setopt($ch, CURLOPT_WRITEFUNCTION,"progress_function");
curl_exec($ch);
curl_close ($ch);
function progress_function($ch,$str) {
    echo $str;
    return strlen($str);
}