PHP应用：php采集神器cURL使用方法详解

<?php
$url = "http://git.oschina.net/yunluo/API/raw/master/notice.txt";
$ch = curl_init();
curl_setopt($ch, CURLOPT_URL, $url);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
curl_setopt($ch, CURLOPT_CONNECTTIMEOUT, 10);
$notice = curl_exec($ch);
echo $notice;
?>

<?php
  if (function_exists('curl_init')) {
    $url = "http://git.oschina.net/yunluo/API/raw/master/notice.txt";
    $ch = curl_init();
    curl_setopt($ch, CURLOPT_URL, $url);
    curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
    curl_setopt($ch, CURLOPT_CONNECTTIMEOUT, 10);
    $dxycontent = curl_exec($ch);
    echo $dxycontent;
  } else {
    echo '汗!貌似您的服务器尚未开启curl扩展,无法收到来自云落的通知,请联系您的主机商开启,本地调试请无视';
  }
?>

<?php echo file_get_contents( "http://git.oschina.net/yunluo/API/raw/master/notice.txt" ); ?>

<?php
  $url = 'http://demo.zjmainstay.cn/php/curl/simple.html';
  $content = file_get_contents($url);
  echo $content;

<?php
  $url = 'http://demo.zjmainstay.cn/php/curl/simple.html';
  $ch = curl_init($url);
  curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1); //返回数据不直接输出
  $content = curl_exec($ch);          //执行并存储结果
  curl_close($ch);
  
  echo $content;
  

<?php
  $keyword  = 'PHP cURL';
  $url    = 'http://www.baidu.com/s?ie=utf-8&f=8&rsv_bp=1&ch=&tn=baidu&bar=&wd=' . urlencode($keyword);
  
  $ch = curl_init($url);
  curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1); //返回数据不直接输出
  $content = curl_exec($ch);          //执行并存储结果
  curl_close($ch);
  
  echo $content;

curl_setopt($ch, CURLOPT_POSTFIELDS, 'ie=utf-8&wd=PHP%20cURL');
或
curl_setopt($ch, CURLOPT_POSTFIELDS, array(
  'ie'  => 'utf-8',
  'wd'  => 'PHP%20cURL',
));

<?php
  $keyword  = 'PHP cURL';
  //参数方法一
  // $post    = 'wd=' . urlencode($keyword);
  
  //参数方法二
  $post    = array(
    'wd'    => urlencode($keyword),
  );
  $url    = 'http://demo.zjmainstay.cn/php/curl/search.php';
  
  $ch = curl_init($url);
  curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1); //返回数据不直接输出
  curl_setopt($ch, CURLOPT_POST, 1);      //发送POST类型数据
  curl_setopt($ch, CURLOPT_POSTFIELDS, $post); //POST数据,$post可以是数组,也可以是拼接
  $content = curl_exec($ch);          //执行并存储结果
  curl_close($ch);
  
  var_dump($content);

<?php
  $keyword  = 'PHP cURL';
  //参数办法一
  // $post    = 'wd=' . urlencode($keyword);
  
  //参数办法二
  $post    = array(
    'wd'    => urlencode($keyword),
  );
  $url    = 'http://demo.zjmainstay.cn/php/curl/search_refer.php';
  $refer   = 'http://demo.zjmainstay.cn/';  //来路地址
  
  $ch = curl_init($url);
  curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1); //返回数据不直接输出
  curl_setopt($ch, CURLOPT_REFERER, $refer);  //来路模拟
  curl_setopt($ch, CURLOPT_POST, 1);      //发送POST类型数据
  curl_setopt($ch, CURLOPT_POSTFIELDS, $post); //POST数据,$post可以是数组,也可以是拼接
  $content = curl_exec($ch);          //执行并存储结果
  curl_close($ch);
  
  var_dump($content);

<?php
  if(empty($_POST['wd'])) {
    exit('Deny empty params.');
  }
  
  //Referer判断
  if(stripos($_SERVER['HTTP_REFERER'], $_SERVER['HTTP_HOST']) === false) {
    exit('Deny');
  }
  
  $keyword  = addslashes(trim(strip_tags($_POST['wd'])));
  $url    = 'http://www.baidu.com/s?ie=utf-8&wd=' . urlencode($keyword);
  
  $ch = curl_init($url);
  curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1); //返回数据不直接输出
  $content = curl_exec($ch);          //执行并存储结果
  curl_close($ch);
  
  echo $content; 

<?php 
header("content-Type: text/html; charset=UTF-8");
$cookie_file = tempnam('./temp', 'cookie');
$login_url="http://bbs.php100.com/login.php";
$post_fields="cktime=36000&step=2&pwuser=username&pwpwd=password";
//提交登录表单哀求
$ch=curl_init($login_url);
curl_setopt($ch,CURLOPT_HEADER,0);
curl_setopt($ch,CURLOPT_RETURNTRANSFER,1);
curl_setopt($ch,CURLOPT_POST,1);
curl_setopt($ch,CURLOPT_POSTFIELDS,$post_fields);
curl_setopt($ch,CURLOPT_COOKIEJAR,$cookie_file); //存储提交后得到的cookie数据
curl_exec($ch);
curl_close($ch);
//登录成功后,获取bbs首页数据
$url="http://bbs.php100.com/index.php";
$ch=curl_init($url);
curl_setopt($ch,CURLOPT_HEADER,0);
curl_setopt($ch,CURLOPT_RETURNTRANSFER,1);
curl_setopt($ch,CURLOPT_COOKIEFILE,$cookie_file); //使用提交后得到的cookie数据做参数
$contents=curl_exec($ch);
curl_close($ch);
//转码显示
echo iconv('gbk', 'UTF-8', $contents);

<?php
  $url = 'http://news.sohu.com/';
  
  $ch = curl_init($url);
  curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1); //返回数据不直接输出
  curl_setopt($ch, CURLOPT_ENCODING, "gzip"); //指定gzip压缩
  $content = curl_exec($ch); //执行并存储结果
  curl_close($ch);
  echo $content;

<?php
  $searchStr = 'RC376981638HK';
  $post  = 'accion=LocalizaUno&numero='.$searchStr.'&ecorreo=&numeros=';
  $url  = 'https://aplicacionesweb.correos.es/localizadorenvios/track.asp';
  $ch         = curl_init($url);       //初始化curl
  curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);    //返回数据不直接输出
  curl_setopt($ch, CURLOPT_POST, 1);         //发送POST类型数据
  curl_setopt($ch, CURLOPT_POSTFIELDS, $post);    //POST数据,$post可以是数组,也可以是拼接参数串
  curl_setopt($ch, CURLOPT_SSL_VERIFYPEER, false);  //SSL 报错时使用
  curl_setopt($ch, CURLOPT_SSL_VERIFYHOST, false);  //SSL 报错时使用
  $contents = curl_exec($ch);               //执行并存储结果
  // var_dump(curl_error($ch));            //获取失败是使用(采集错误提示)
  curl_close($ch);
  echo $contents;

<?php
  $url = 'http://demo.zjmainstay.cn/php/curl/dump_ip.php?t=' . time();
  
  echo "本地IP：" . file_get_contents($url) . "\n伪造IP：";
  
  $ip   = '183.224.1.116';
  $port  = '80';
  
  //伪造哀求头参数,如果是高匿代理这里不需要提供
  $header = array(
    'X-FORWARDED-FOR: ' . $ip,
    'CLIENT-IP: ' . $ip,
  );
  
  $ch         = curl_init($url); //初始化curl
  curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
  curl_setopt($ch, CURLOPT_HTTPHEADER, $header);
  curl_setopt($ch, CURLOPT_PROXY, $ip);
  curl_setopt($ch, CURLOPT_PROXYPORT, $port);
  $content = curl_exec($ch); //执行并存储结果
  curl_close($ch);
  
  echo $content;

<?php
$urls = array(
  "http://demo.zjmainstay.cn/php/curl/curl_multi_1.php",
  "http://demo.zjmainstay.cn/php/curl/curl_multi_2.php",
);
$mh = curl_multi_init();
foreach ($urls as $i => $url) {
  $conn[$i] = curl_init($url);
  curl_setopt($conn[$i], CURLOPT_RETURNTRANSFER, 1); //不直接输出结果
  curl_multi_add_handle($mh, $conn[$i]);
}
$active = null;
$res = array();
do {
  $status = curl_multi_exec($mh, $active);
  $info = curl_multi_info_read($mh);
  if (false !== $info) {
    //采集信息处理
    $res[] = array(
      'content'  => curl_multi_getcontent($info['handle']),
      'info'   => $info,
    );
    curl_close($info['handle']);
  }
} while ($status === CURLM_CALL_MULTI_PERFORM || $active);
curl_multi_close($mh);
var_dump($res);

curl_setopt($ch, CURLOPT_FOLLOWLOCATION, true);

全部数据使用HTTP协议中的"POST"操作来发送.要发送文件,在文件名前面加上@前缀并使用完整路径.这个参数可以通过urlencoded后的字符串类似'para1=val1&para2=val2&...'或使用一个以字段名为键值,字段数据为值的数组.如果value是一个数组,Content-Type头将会被设置成multipart/form-data.

//上传D盘下的test.jpg文件,文件必须存在,否则curl处理失败且没有任何提示
$data = array('name' => 'Foo', 'file' => '@d:/test.jpg');
$ch = curl_init('http://localhost/upload.php');
curl_setopt($ch, CURLOPT_POST, 1);
curl_setopt($ch, CURLOPT_POSTFIELDS, $data);
curl_exec($ch);

Array ( [name] => Foo ) Array ( [file] => Array ( [name] => test.jpg [type] => application/octet-stream [tmp_name] => D:\xampp\tmp\php2EA0.tmp [error] => 0 [size] => 139999 ) )

curl_setopt(\(ch, CURLOPT_POSTFIELDS, 'param1=val1&param2=val2&...'); 和 curl_setopt(\)ch, CURLOPT_POSTFIELDS, array('param1' => 'val1', 'param2' => 'val2', ...));