Oft müssen wir einige Website-Ressourcen stapelweise crawlen, und zu diesem Zeitpunkt müssen wir einen Crawler verwenden. Die Grundlage des Crawlers besteht darin, CURL zum Simulieren von HTTP-Anfragen und zum anschließenden Parsen der Daten zu verwenden. In diesem Artikel lernen Sie PHPs CURL kennen, indem Sie einen einfachen Webcrawler schreiben.
Stellen Sie zunächst einige häufig verwendete Funktionen vor.
curl_init 初始化一个curl对话 curl_setopt 设置curl参数,即传输选项 curl_exec 执行请求 curl_close 关闭一个curl对话
Hauptsächlich die oben genannten vier
curl_errno 返回最后一次错误码,php已经定义了诸多错误枚举编码 curl_errror 返回一个保护当前会话最近一次错误的字符串
Kommen wir direkt zu den Beispielen unten
1. Laden Sie eine Webseite im Internet herunter und ersetzen Sie „Baidu“ im Inhalt durch „屌Si“ und geben Sie
<?php /** * 实例描述:在网络上下载一个网页并把内容中的“百度”替换为“屌丝”之后输出 */ $curlobj = curl_init(); // 初始化 curl_setopt($curlobj, CURLOPT_URL, "http://www.baidu.com"); // 设置访问网页的URL curl_setopt($curlobj, CURLOPT_RETURNTRANSFER, true); // 执行之后不直接打印出来 $output=curl_exec($curlobj); // 执行 curl_close($curlobj); // 关闭cURL echo str_replace("百度","屌丝",$output); ?>
<?php /** * 实例描述:通过调用WebService查询北京的当前天气 */ $data = 'theCityName=北京'; $curlobj = curl_init(); curl_setopt($curlobj, CURLOPT_URL, "http://www.webxml.com.cn/WebServices/WeatherWebService.asmx/getWeatherbyCityName"); curl_setopt($curlobj, CURLOPT_HEADER, 0); curl_setopt($curlobj, CURLOPT_RETURNTRANSFER, 1); curl_setopt($curlobj, CURLOPT_POST, 1); curl_setopt($curlobj, CURLOPT_POSTFIELDS, $data); curl_setopt($curlobj, CURLOPT_HTTPHEADER, array("application/x-www-form-urlencoded; charset=utf-8", "Content-length: ".strlen($data) )); $rtn = curl_exec($curlobj); if(!curl_errno($curlobj)){ // $info = curl_getinfo($curlobj); // print_r($info); echo $rtn; } else { echo 'Curl error: ' . curl_error($curlobj); } curl_close($curlobj); ?>
<?php /** * 实例描述:模拟需要登录的网址并抓取网页的内容 */ $data=array('username' => 'promonkey', 'password' => '1q2w3e', 'remember'=>1); $data='username=zjzhoufy@126.com&password=1q2w3e&remember=1'; $curlobj = curl_init(); // 初始化 curl_setopt($curlobj, CURLOPT_URL, "http://www.imooc.com/user/login"); // 设置访问网页的URL curl_setopt($curlobj, CURLOPT_RETURNTRANSFER, true); // 执行之后不直接打印出来 // Cookie相关设置,这部分设置需要在所有会话开始之前设置 date_default_timezone_set('PRC'); // 使用Cookie时,必须先设置时区 curl_setopt($curlobj, CURLOPT_COOKIESESSION, TRUE); curl_setopt($curlobj, CURLOPT_HEADER, 0); curl_setopt($curlobj, CURLOPT_FOLLOWLOCATION, 1); // 这样能够让cURL支持页面链接跳转 curl_setopt($curlobj, CURLOPT_POST, 1); curl_setopt($curlobj, CURLOPT_POSTFIELDS, $data); curl_setopt($curlobj, CURLOPT_HTTPHEADER, array("application/x-www-form-urlencoded; charset=utf-8", "Content-length: ".strlen($data) )); curl_exec($curlobj); // 执行 curl_setopt($curlobj, CURLOPT_URL, "http://www.imooc.com/space/index"); curl_setopt($curlobj, CURLOPT_POST, 0); curl_setopt($curlobj, CURLOPT_HTTPHEADER, array("Content-type: text/xml" )); $output=curl_exec($curlobj); // 执行 curl_close($curlobj); // 关闭cURL echo $output; ?>
<?php /** * 实例描述:登录网站的信息抓取并下载个人空间页面 * 自定义实现页面链接跳转抓取 * */ $data='username=demo_peter@126.com&password=123qwe&remember=1'; $curlobj = curl_init(); // 初始化 curl_setopt($curlobj, CURLOPT_URL, "http://www.imooc.com/user/login"); // 设置访问网页的URL curl_setopt($curlobj, CURLOPT_RETURNTRANSFER, true); // 执行之后不直接打印出来 // Cookie相关设置,这部分设置需要在所有会话开始之前设置 date_default_timezone_set('PRC'); // 使用Cookie时,必须先设置时区 curl_setopt($curlobj, CURLOPT_COOKIESESSION, TRUE); curl_setopt($curlobj, CURLOPT_HEADER, 0); // 注释掉这行,因为这个设置必须关闭安全模式 以及关闭open_basedir,对服务器安全不利 //curl_setopt($curlobj, CURLOPT_FOLLOWLOCATION, 1); curl_setopt($curlobj, CURLOPT_POST, 1); curl_setopt($curlobj, CURLOPT_POSTFIELDS, $data); curl_setopt($curlobj, CURLOPT_HTTPHEADER, array("application/x-www-form-urlencoded; charset=utf-8", "Content-length: ".strlen($data) )); curl_exec($curlobj); // 执行 curl_setopt($curlobj, CURLOPT_URL, "http://www.imooc.com/space/index"); curl_setopt($curlobj, CURLOPT_POST, 0); curl_setopt($curlobj, CURLOPT_HTTPHEADER, array("Content-type: text/xml" )); $output=curl_redir_exec($curlobj); // 执行 curl_close($curlobj); // 关闭cURL echo $output; /** * 自定义实现页面链接跳转抓取 */ function curl_redir_exec($ch,$debug="") { static $curl_loops = 0; static $curl_max_loops = 20; if ($curl_loops++ >= $curl_max_loops) { $curl_loops = 0; return FALSE; } curl_setopt($ch, CURLOPT_HEADER, true); // 开启header才能够抓取到重定向到的新URL curl_setopt($ch, CURLOPT_RETURNTRANSFER, true); $data = curl_exec($ch); // 分割返回的内容 $h_len = curl_getinfo($ch, CURLINFO_HEADER_SIZE); $header = substr($data,0,$h_len); $data = substr($data,$h_len - 1); $http_code = curl_getinfo($ch, CURLINFO_HTTP_CODE); if ($http_code == 301 || $http_code == 302) { $matches = array(); preg_match('/Location:(.*?)\n/', $header, $matches); $url = @parse_url(trim(array_pop($matches))); // print_r($url); if (!$url) { //couldn't process the url to redirect to $curl_loops = 0; return $data; } $last_url = parse_url(curl_getinfo($ch, CURLINFO_EFFECTIVE_URL)); if (!isset($url['scheme'])) $url['scheme'] = $last_url['scheme']; if (!isset($url['host'])) $url['host'] = $last_url['host']; if (!isset($url['path'])) $url['path'] = $last_url['path']; $new_url = $url['scheme'] . '://' . $url['host'] . $url['path'] . (isset($url['query'])?'?'.$url['query']:''); curl_setopt($ch, CURLOPT_URL, $new_url); return curl_redir_exec($ch); } else { $curl_loops=0; return $data; } } ?>
<?php /** * 实例描述:把本地文件上传到FTP服务器上 */ $curlobj = curl_init(); $localfile = 'ftp01.php'; $fp = fopen($localfile, 'r'); curl_setopt($curlobj, CURLOPT_URL, "ftp://192.168.1.100/ftp01_uploaded.php"); curl_setopt($curlobj, CURLOPT_HEADER, 0); curl_setopt($curlobj, CURLOPT_RETURNTRANSFER, 1); curl_setopt($curlobj, CURLOPT_TIMEOUT, 300); // times out after 300s curl_setopt($curlobj, CURLOPT_USERPWD, "peter.zhou:123456");//FTP用户名:密码 //上传和下载主要是下面子三个参数不一样 curl_setopt($curlobj, CURLOPT_UPLOAD, 1); curl_setopt($curlobj, CURLOPT_INFILE, $fp); curl_setopt($curlobj, CURLOPT_INFILESIZE, filesize($localfile)); $rtn = curl_exec($curlobj); fclose($fp); if(!curl_errno($curlobj)){ echo "Uploaded successfully."; } else { echo 'Curl error: ' . curl_error($curlobj); } curl_close($curlobj); ?>
<?php /** * 实例描述:下载网络上面的一个HTTPS的资源 */ $curlobj = curl_init(); // 初始化 curl_setopt($curlobj, CURLOPT_URL, "https://ajax.aspnetcdn.com/ajax/jquery.validate/1.12.0/jquery.validate.js"); // 设置访问网页的URL curl_setopt($curlobj, CURLOPT_RETURNTRANSFER, true); // 执行之后不直接打印出来 // 设置HTTPS支持 date_default_timezone_set('PRC'); // 使用Cookie时,必须先设置时区 curl_setopt($curlobj, CURLOPT_SSL_VERIFYPEER, 0); // 对认证证书来源的检查从证书中检查SSL加密算法是否存在 curl_setopt($curlobj, CURLOPT_SSL_VERIFYHOST, 2); // $output=curl_exec($curlobj); // 执行 curl_close($curlobj); // 关闭cURL echo $output; ?>
$data = array( 'foo'=>'bar', 'baz'=>'boom', 'site'=>'www.nowamagic.net', 'name'=>'nowa magic'); $data = http_build_query($data); //$postdata = http_build_query($data); $options = array( 'http' => array( 'method' => 'POST', 'header' => 'Content-type:application/x-www-form-urlencoded', 'content' => $data //'timeout' => 60 * 60 // 超时时间(单位:s) ) ); $url = "http://www.nowamagic.net/test2.php"; $context = stream_context_create($options); $result = file_get_contents($url, false, $context); echo $result;
$data = $_POST; echo '<pre class="brush:php;toolbar:false">'; print_r( $data ); echo '';
Array ( [foo] => bar [baz] => boom [site] => www.nowamagic.net [name] => nowa magic )
$context = stream_context_create(array( 'http' => array( 'method' => 'POST', 'header' => sprintf("Authorization: Basic %s\r\n", base64_encode($username.':'.$password)). "Content-type: application/x-www-form-urlencoded\r\n", 'content' => http_build_query(array('status' => $message)), 'timeout' => 5, ), )); $ret = file_get_contents('http://twitter.com/statuses/update.xml', false, $context);
$opts = array( 'http'=>array( 'method'=>"GET", 'timeout'=>60, ) ); //创建数据流上下文 $context = stream_context_create($opts); $html =file_get_contents('http://www.nowamagic.net', false, $context); //fopen输出文件指针处的所有剩余数据: //fpassthru($fp); //fclose()前使用
Das obige ist der detaillierte Inhalt vonBeispiel für einen PHP-Lern-CURL-Crawler. Für weitere Informationen folgen Sie bitte anderen verwandten Artikeln auf der PHP chinesischen Website!