Detailed explanation of CURL for PHP web crawler-PHP Tutorial-php.cn

php's curl can simulate various HTTP requests. This is also the basis for PHP to do web crawlers. It is also mostly used for calling interface APIs. At this time, someone will ask: Why don't you use file_get_contents?

curl's performance is better than it, and it can complete more complex operations, not just getting page data.

The following introduces some commonly used functions.

curl_init Initialize a curl conversation
##curl_setopt Set curl parameters, that is, transmission options
curl_exec Execute the request
##curl_close
Close a curl conversation

curl_errno returns the last error code, PHP has defined many error enumeration codes

1. Download a web page on the Internet and put the content After replacing "Baidu" in "Diansi", the output is

<?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URLcurl_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cURLecho str_replace("百度","屌丝",$output);?>

Copy after login

2. By calling WebService queries the current weather in Beijing

<?php/**
 * 实例描述：通过调用WebService查询北京的当前天气
 */$data = &#39;theCityName=北京&#39;;$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 $rtn;  
} else {  echo &#39;Curl error: &#39; . curl_error($curlobj);
}
curl_close($curlobj);?>

Copy after login

3. Simulate the URL that requires login and crawl it The content of the web page

<?php/**
 * 实例描述：模拟需要登录的网址并抓取网页的内容
 */$data=array(&#39;username&#39; => &#39;promonkey&#39;, 
    &#39;password&#39; => &#39;1q2w3e&#39;,    &#39;remember&#39;=>1);$data=&#39;username=zjzhoufy@126.com&password=1q2w3e&remember=1&#39;;$curlobj = curl_init();            // 初始化curl_setopt($curlobj, CURLOPT_URL, "http://www.imooc.com/user/login");     // 设置访问网页的URLcurl_setopt($curlobj, CURLOPT_RETURNTRANSFER, true);           // 执行之后不直接打印出来// Cookie相关设置，这部分设置需要在所有会话开始之前设置date_default_timezone_set(&#39;PRC&#39;); // 使用Cookie时，必须先设置时区curl_setopt($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cURLecho $output;?>

Copy after login

<?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
 * 
 */$data=&#39;username=demo_peter@126.com&password=123qwe&remember=1&#39;;$curlobj = curl_init();            // 初始化curl_setopt($curlobj, CURLOPT_URL, "http://www.imooc.com/user/login");     // 设置访问网页的URLcurl_setopt($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(&#39;PRC&#39;); // 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cURLecho $output;/**
 * 自定义实现页面链接跳转抓取
 */function curl_redir_exec($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(&#39;/Location:(.*?)\n/&#39;, $header, $matches); 
        $url = @parse_url(trim(array_pop($matches))); 
        // print_r($url); 
        if (!$url) 
        { 
            //couldn&#39;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[&#39;scheme&#39;])) 
            $url[&#39;scheme&#39;] = $last_url[&#39;scheme&#39;]; 
        if (!isset($url[&#39;host&#39;])) 
            $url[&#39;host&#39;] = $last_url[&#39;host&#39;]; 
        if (!isset($url[&#39;path&#39;])) 
            $url[&#39;path&#39;] = $last_url[&#39;path&#39;];        $new_url = $url[&#39;scheme&#39;] . &#39;://&#39; . $url[&#39;host&#39;] . $url[&#39;path&#39;] . (isset($url[&#39;query&#39;])?&#39;?&#39;.$url[&#39;query&#39;]:&#39;&#39;); 
        curl_setopt($ch, CURLOPT_URL, $new_url); 

        return curl_redir_exec($ch); 
    } else { 
        $curl_loops=0; 
        return $data; 
    } 
} 
?>

Copy after login

##Download a file from the FTP server To local

<?php/**
 * 实例描述：把本地文件上传到FTP服务器上
 */$curlobj = curl_init();    
$localfile = &#39;ftp01.php&#39;;$fp = fopen($localfile, &#39;r&#39;);

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 300scurl_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($curlobj)){    echo "Uploaded successfully.";  
} else {  echo &#39;Curl error: &#39; . curl_error($curlobj);
}
curl_close($curlobj);?>

Copy after login

6.下载网络上面的一个HTTPS的资源

<?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URLcurl_setopt($curlobj, CURLOPT_RETURNTRANSFER, true);           
   // 执行之后不直接打印出来// 设置HTTPS支持date_default_timezone_set(&#39;PRC&#39;); 
   // 使用Cookie时，必须先设置时区curl_setopt($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cURLecho $output;?>

Copy after login