<?php
/**
 * test get request
 * User: freephp
 * Date: 2015/10/8
 * Time: 15:08
 */

$ch = curl_init();

// 2. 设置选项，包括URL
curl_setopt($ch, CURLOPT_URL, "http://www.cnblogs.com/freephp");
curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
curl_setopt($ch, CURLOPT_HEADER, 0);
// 3. 执行并获取HTML文档内容
$output = curl_exec($ch);
// 4. 释放curl句柄
curl_close($ch);

print_r($output);

/**
 * 从html内容中筛选链接
 *
 * @param string $web_content
 * @return array
 */
function filterUrl($web_content){
    $reg_tag_a = '/<[a|A].*?class="postTitle2".*?href=[\'\"]{0,1}([^>\'\"\ ]*).*?>/';
    $result = preg_match_all($reg_tag_a,$web_content,$match_result);
    if($result){
        return $match_result[1];
    }
}

print_r(filterUrl($output));

<?php
/**
 * test get request
 * User: freephp
 * Date: 2015/10/8
 * Time: 15:08
 */

/**
 * 获取网页源码
 *
 * @param $url get方式请求的url
 * @return mixed
 */
function getRquest($url)
{
    $ch = curl_init();
    curl_setopt($ch, CURLOPT_URL, $url);
    curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
    curl_setopt($ch, CURLOPT_HEADER, 0);
    // 3. 执行并获取HTML文档内容
    $output = curl_exec($ch);
    // 4. 释放curl句柄
    curl_close($ch);
    return $output;
}


/**
 * 从html内容中筛选链接
 *
 * @param string $web_content
 * @return array
 */
function filterUrl($web_content)
{
    $reg_tag_a = '/<[a|A].*?class="postTitle2".*?href=[\'\"]{0,1}([^>\'\"\ ]*).*?>/';
    $result = preg_match_all($reg_tag_a, $web_content, $match_result);
    if ($result) {
        return $match_result[1];
    }
}

/**
 * 从html内容中筛选文章内容
 *
 * @param string $content
 * @return array
 */
function filterContent($content)
{

    $reg = '/<.*\"likecs_post_body\">(.*?)<\/div>/ism';
    $result = preg_match_all($reg, $content, $match_result);
    if ($result) {
        return $match_result[1];
    }
}

/**
 * 抓取文章内容写入文件。
 *
 * @param string $fileName 存储文件名
 * @param string $contents 文章内容
 */
function writeToFile($fileName, $contents)
{
    $fp = fopen($fileName, 'w');

    fwrite($fp, $contents);
    fclose($fp);
}

$output = getRquest("http://www.cnblogs.com/freephp");

$articleUrls = filterUrl($output);
if (empty($articleUrls)) {
    echo '获取文章url失败';
    die();
}
$articleNum = count($articleUrls); 
echo '总共文章为:', $articleNum, "\r\n";
foreach ($articleUrls as $url) {
    echo '开始爬取url:', $url, "\r\n";
    $out = getRquest($url);
    $cont = filterContent($out);
    $filename = str_replace('.html', '', str_replace('http://www.cnblogs.com/freephp/p/', '', $url));
    writeToFile($filename . '.txt', $cont[0]);
    echo '完成爬取url:', $url, "\r\n";
}