来源：http://www.niehonglei.info/archives/765.html
由于有过惨痛教训，老是错过重要的考试报名通知，所以这段代码抓取了上海教育考试院的报名页面，分析并发送短信通知相应的考试人员，然后将这个页面放到服务器上，每日定时检查，一有新的报名信息就能及时得知。中间涉及到部分php的知识点
fscoketopen，上一篇已经写过相应的介绍，即可以用其来模拟web service调用，也可以使用其来抓取页面
正则表达式，preg_match，用来提取抓取后页面返回的数据
编码转换iconv，抓取的页面是GBK类型，如果不转换，则在控制台显示乱码。第二个是发送短信的接口，由于我使用的接口是GBK数据，所以我需要再从UTF-8转换到GBK
php文件的相关操作函数：file_exists用来判断文件是否已经存在，fopen用来打开文件，fgets用来读取一行，fputs用来写入一行。
数组模拟push方法，使用arr[] = something;的形式
vim 格式化代码 ：gg=G
vim
批量添加 //注释：:10,50s#^#//#g ；批量删除 :10,50s#^//##g
定时的方法使用crontab -e，就可打开定时列表，设置成每天10点通知：
0 10 * * * /path/to/php /path/to/spta.php
spta.php
function get_spta(){
$content = ”;
$fp = fsockopen(‘www.spta.gov.cn’, 80);
fwrite($fp, “GET /appendix/wsbm.html HTTP/1.0\r\n”);
fwrite($fp, “Host: www.spta.gov.cn\r\n”);
fwrite($fp, “Content-Type: text/html; charset=utf-8\r\n”);
fwrite($fp, “Content-Length: “.strlen($content).”\r\n”);
fwrite($fp, “\r\n”);
fwrite($fp, $content);
$item = array();
while(!feof($fp)){
$result = iconv(‘GBK’, ‘UTF-8′, fgets($fp));
if(strpos($result, ‘
’) > 0){ preg_match(‘/>([^<]*)</’, $result, $matches); $title = $matches[1]; $url = iconv(‘GBK’, ‘UTF-8′, fgets($fp)); preg_match(‘/href=”([^"]*)”/’, $url, $matches); $url = $matches[1]; $item[] = array(‘title’ => $title, ‘url’ => $url); } } fclose($fp); return $item; } function sent_sms($mobile, $msg){ $vars = “&mobs=$mobile&msg=” . iconv(‘UTF-8′, ‘GBK’, $msg); $fp = fsockopen(‘smsserver.com‘, 80); fwrite($fp, “GET /sms?$vars HTTP/1.0\r\n”); fwrite($fp, “Host: smsserver.com\r\n”); fwrite($fp, “\r\n”); fwrite($fp, $content); fclose($fp); } $items = get_spta(); $title = ”; $path = ‘/path/to/spta’; if(file_exists($path)){ $file = fopen($path, ‘r’); $title = fgets($file); } foreach($items as $bean){ if($title != $bean['title']){ sent_sms(‘your mobile‘, $bean['title'] . ‘[考试院]‘); echo $bean['title'] . “\n”; } else { break; } } $file = fopen($path, ‘w’); fputs($file, $items[0]['title']);
’) > 0){ preg_match(‘/>([^<]*)</’, $result, $matches); $title = $matches[1]; $url = iconv(‘GBK’, ‘UTF-8′, fgets($fp)); preg_match(‘/href=”([^"]*)”/’, $url, $matches); $url = $matches[1]; $item[] = array(‘title’ => $title, ‘url’ => $url); } } fclose($fp); return $item; } function sent_sms($mobile, $msg){ $vars = “&mobs=$mobile&msg=” . iconv(‘UTF-8′, ‘GBK’, $msg); $fp = fsockopen(‘smsserver.com‘, 80); fwrite($fp, “GET /sms?$vars HTTP/1.0\r\n”); fwrite($fp, “Host: smsserver.com\r\n”); fwrite($fp, “\r\n”); fwrite($fp, $content); fclose($fp); } $items = get_spta(); $title = ”; $path = ‘/path/to/spta’; if(file_exists($path)){ $file = fopen($path, ‘r’); $title = fgets($file); } foreach($items as $bean){ if($title != $bean['title']){ sent_sms(‘your mobile‘, $bean['title'] . ‘[考试院]‘); echo $bean['title'] . “\n”; } else { break; } } $file = fopen($path, ‘w’); fputs($file, $items[0]['title']);
