为了给接下来的教程做好铺垫，本文将讲述如何用PHP发出Http请求进行模拟登录，顺带会讲一些Http请求原理。模拟登录…就是模拟浏览器登录嘛，所谓请求，只不过是你向网站发一些字，网站又给你回复一些字，这一般都是基于Http或Https协议的。平时是浏览器帮我们做好了这些工作，封装数据发送到指定网站，然后接收，最后编译成网页显示出来。在模拟登录中，呵呵，这些都要我们自己做，只是最后不用编译…只要提取到需要的数据就行了。
PHP中模拟登录有三种方式。第一是直接用file_get_contens(网站)这个函数，这个..用起来很简单，不说了；第二种是用socket，按照套接字的规定把要发送的字符一个个打上去，再发出去，这个..没多研究，也不说了；最后就当然是用PHP自带的CURL工具了。这个工具可以根据不同的需求，设置消息包头信息、发送字流等等，也很方便。至于Http数据包的格式是怎么样的，这是Http协议的基本内容，不多说。下面用CURL模拟发起一次对百度的请求：
1 $curl = curl_init() //初始化实例 2 curl_setopt($curl, CURLOPT_URL, http://www.baidu.com) //设置URL地址 3 curl_setopt($curl, CURLOPT_CONNECTTIMEOUT, 5); //5秒连接超时 4 curl_setopt($curl, CURLOPT_RETURNTRANSFER, 1); //设为1返回Http响应结果 5 //伪造客户端，最好设一下，有些网站会根据客户端来阻隔请求的 6 curl_setopt($curl, CURLOPT_USERAGENT, ‘User-Agent: Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; WOW64; Trident/5.0‘); 7 $response = curl_exec($curl); //curl执行http请求，响应存到$response变量中 8 $state = curl_getinfo($curl, CURLINFO_HTTP_CODE); //可以用这句来获取响应的状态码 9 curl_close($curl); //释放curl资源
至此一次请求就完成了，$response变量是响应结果，也就是百度页面的html源码(字符串)。Http请求中有两种请求方式，一是GET，另一是POST(具体的看Http原理去)，以上对百度的是GET方法，POST方法不同就在于，要把参数作为消息报内容发送出去，参数流按照Http协议的规定，p1=v1&p2=v2&p3=v3…，p是参数名v是值，搞不清楚的看懂Http原理再接着看。记参数为$param变量(字符串)，那就
curl_setopt($curl, CURLOPT_POSTFIELDS, $param);
如果要设置请求头部：
curl_setopt($curl, CURLOPT_HTTPHEADER, $header);
其中$header为数组类型，比如要写入CLIENT-IP和X_FORWARDED-FOR这两个头信息，那就$header = array(‘CLIENT-IP: ‘=>‘value‘, ‘X-FORWARDED-FOR: ‘=>‘value‘).
curl还有很多CURLOPT预设值给curl_setopt使用，具体的我不写出来了..自己找吧
接下来，既然curl已经知道怎么用了，能不能用curl写一个模拟登录的工具类呢？
我把这个类叫RequestClient，一般请求关系到三方面：url地址、请求方法、请求参数，请求头部可要可不要，所以也写下去；至于接收到的响应，就取响应数据报、状态码。综上，定义这个类的成员变量：
private $response = null;
private $url;
private $header = null;
private $parameter = null;
private $method = ‘GET‘; //默认使用GET方法请求
private $state = null;
实例化时要指定url，也可以通过set的方式设定
public function __construct($url) {
$this->url = $url;
}
public function setUrl($url) {
$this->url = $url;
}
Header的setter($header按照上面提到的格式)：
public function setHeader($header) {
$this->header = $header;
}
以及各种getter：
public function getUrl() { return $this->url; }
public function getParameter() { return $this->parameter; }
public function getHeader() { return $this->header; }public function getMethod() { return $this->method; }
public function getState() { return $this->state; }
public function getResponse() { return $this->response; }
接下来设置参数了，设置参数有两种方式，一是通过传递数组，再把数据信息转化为参数字符串，二是直接传递字符串，数组格式为array(“p1”=>”value1”, “p2”=>”value2”…)，encode可选择是否对参数进行url编码(默认是)
1 public function setParameter($parameter = null, $encode = true) {
2 if (is_array($parameter)) {
3 $temp = ‘‘;
4 if ($encode) {
5 foreach ($parameter as $key => $value) {
6 $temp .= "$key=".urlencode($value) ."&";
7 }
8 } else {
9 foreach ($parameter as $key => $value) {
10 $temp .= "$key=$value&";
11 }
12 }
13 $this->parameter = substr($temp, 0, -1);
14 } elseif (is_string($parameter)) {
15 $this->parameter = $parameter;
16 }
17 }
下面是get和post方法，模拟发出get、post请求，响应报文放在$response，状态码放在$state
1 public function get($timeout=5) {
2 $this->method = ‘GET‘;
3 if ($this->parameter != null) { //get在有参数的情况下，把参数附在url上
4 $this->url .= (‘?‘.$this->parameter);
5 }
6 $curl = curl_init();
7 curl_setopt($curl, CURLOPT_URL, $this->url);
8 curl_setopt($curl, CURLOPT_RETURNTRANSFER, 1);
9 curl_setopt($curl, CURLOPT_CONNECTTIMEOUT, $timeout);
10 if ($this->header!=null) { //有头信息时才设置
11 curl_setopt($curl, CURLOPT_HTTPHEADER, $this->header);
12 }
13 curl_setopt($curl, CURLOPT_USERAGENT, ‘User-Agent: Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; WOW64; Trident/5.0‘);
14 $this->response = curl_exec($curl);
15 $this->state = curl_getinfo($curl, CURLINFO_HTTP_CODE);
16 curl_close($curl);
17 return $this->response;
18 }
19
20 public function post($timeout=5) {
21 $this->method = ‘POST‘;
22 $curl = curl_init();
23 curl_setopt($curl, CURLOPT_URL, $this->url);
24 curl_setopt($curl, CURLOPT_HEADER, 1);
25 curl_setopt($curl, CURLOPT_RETURNTRANSFER, 1);
26 curl_setopt($curl, CURLOPT_CONNECTTIMEOUT, $timeout);
27 curl_setopt($curl, CURLOPT_POSTFIELDS, $this->parameter);
28 if ($this->header!=null) {
29 curl_setopt($curl, CURLOPT_HTTPHEADER, $this->header);
30 }
31 curl_setopt($curl, CURLOPT_USERAGENT, ‘User-Agent: Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; WOW64; Trident/5.0‘);
32 $this->response = curl_exec($curl);
33 $this->state = curl_getinfo($curl, CURLINFO_HTTP_CODE);
34 curl_close($curl);
35 return $this->response;
36 }
这样，一个用于Http请求的类就基本完成了，但是根据实际情况，对不同的需求可以提供不同的功能，比如说获取网页的标题(<title>的内容)：
1 public function getTitle() {
2 $source = $this->response;
3 $start = stripos($source, ‘<title‘);
4 $source = substr($source, $start);
5 $start = stripos($source, ‘>‘) + 1;
6 $end = stripos($source, ‘<‘, $start);
7 return substr($source, $start, $end-$start);
8 }
获取cookie返回字符串(CURL提供了一个获取Cookie很方便快捷的方法，在setopt中用CURLOPT_COOKIEJAR和CURLOPT_COOKIE变量获取就可以了，Cookie信息会写在指定的文件中，发出请求时直接调用这个文件上传就可以了，但是由于个人习惯，我还是喜欢把cookie当字符串提取出来，设置在$header头信息的Cookie中，这样比较灵活吧，以下函数就是把cookie串提取出来，以[cookie1=value1; cookie2=value2; …]这个格式返回string)：
1 public function getCookie() {
2 $content = $this->response; //$response中包含响应头信息
3 $start = 0;
4 $rt = ‘‘;
5 while (($start = stripos($content, ‘Set-Cookie: ‘, $start)) != false) { //不断搜索’Set-Cookie’字段
6 $start += 12; //从$start位置开始忽略Set-Cookie这12个字符
7 $end = stripos($content, ‘;‘, $start);
8 $rt .= substr($content, $start, $end-$start).‘; ‘;
9 }
10 return substr($rt, 0, -2); //丢掉最后的分号和空格
11 }
调用时就是
$client = new RequestClient(“这里是网址”);
$client->setHeader(头信息);
$client->setParameter(参数);
$client->get() 或者 $client->post();
至此这个类就完成了。最后要说的一点是，这个封装功能的思路和代码实现毕竟都是我凭经验总结出来的，不免会有一点差错或者有点不完善。总之就是，在实际应用中要根据自己的需求改善，增加一些功能，更好地去适应自己的程序。
最后的完整代码：
1 <?php
2 class RequestClient {
3 private $response = null;
4 private $url;
5 private $header = null; //type: array
6 private $parameter = null; //type String
7 private $proxy = null; //代理
8 private $method = ‘GET‘; //default GET method
9 private $state = null;
10
11
12 // a static function to create a new object with parameters url, parameters, and cookie(path)
13 public static function newClient($url, $parameter=null, $header=null) {
14 $client = new RequestClient($url);
15 $client->setParameter($parameter);
16 $client->setHeader($header);
17 return $client;
18 }
19
20 // constructor, with a only parameter url
21 public function __construct($url) {
22 $this->url = $url;
23 }
24
25 public function __destruct() {
26 $this->clear();
27 }
28
29 // setter
30 public function setUrl($url) {
31 $this->url = $url;
32 }
33
34 public function setHeader($header) {
35 $this->header = $header;
36 }
37
38 public function setProxy($proxy) {
39 $this->proxy = $proxy;
40 }
41
42 public function getCookie() {
43 $content = $this->response;
44 $start = 0;
45 $rt = ‘‘;
46 while (($start = stripos($content, ‘Set-Cookie: ‘, $start)) != false) {
47 $start += 12;
48 $end = stripos($content, ‘;‘, $start);
49 $rt .= substr($content, $start, $end-$start).‘; ‘;
50 }
51 return substr($rt, 0, -2);
52 }
53
54
55 public function setParameter($parameter = null, $encode = true) {
56 if (is_array($parameter)) { //change to ‘string‘ if the type is ‘array‘
57 $temp = ‘‘;
58 if ($encode) {
59 foreach ($parameter as $key => $value) {
60 $temp .= "$key=".urlencode($value) ."&"; //change to string
61 }
62 } else {
63 foreach ($parameter as $key => $value) {
64 $temp .= "$key=$value&";
65 }
66 }
67 $this->parameter = substr($temp, 0, -1);
68 } elseif (is_string($parameter)) {
69 $this->parameter = $parameter;
70 }
71 }
72
73 // request in method ‘GET‘, set the response content to $this->reponse and return it
74 public function get($timeout=5) {
75 $this->method = ‘GET‘;
76 $this->handleParameter();
77 $curl = curl_init();
78 curl_setopt($curl, CURLOPT_URL, $this->url);
79 curl_setopt($curl, CURLOPT_RETURNTRANSFER, 1);
80 curl_setopt($curl, CURLOPT_CONNECTTIMEOUT, $timeout);
81 if ($this->header!=null) {
82 curl_setopt($curl, CURLOPT_HTTPHEADER, $this->header);
83 }
84 if ($this->proxy!=null) {
85 curl_setopt($curl, CURLOPT_PROXY, $this->proxy);
86 }
87 curl_setopt($curl, CURLOPT_USERAGENT, ‘User-Agent: Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; WOW64; Trident/5.0‘);
88 $this->response = curl_exec($curl);
89 $this->state = curl_getinfo($curl, CURLINFO_HTTP_CODE);
90 curl_close($curl);
91 return $this->response;
92 }
93
94 // request in method ‘POST‘, set the response content to $this->reponse and return it
95 public function post($timeout=5) {
96 $this->method = ‘POST‘;
97 $curl = curl_init();
98 curl_setopt($curl, CURLOPT_URL, $this->url);
99 curl_setopt($curl, CURLOPT_HEADER, 1);
100 curl_setopt($curl, CURLOPT_RETURNTRANSFER, 1);
101 curl_setopt($curl, CURLOPT_CONNECTTIMEOUT, $timeout);
102 curl_setopt($curl, CURLOPT_POSTFIELDS, $this->parameter);
103 if ($this->header!=null) {
104 curl_setopt($curl, CURLOPT_HTTPHEADER, $this->header);
105 }
106 if ($this->proxy!=null) {
107 curl_setopt($curl, CURLOPT_PROXY, $this->proxy);
108 }
109 curl_setopt($curl, CURLOPT_USERAGENT, ‘User-Agent: Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; WOW64; Trident/5.0‘);
110 $this->response = curl_exec($curl);
111 $this->state = curl_getinfo($curl, CURLINFO_HTTP_CODE);
112 curl_close($curl);
113 return $this->response;
114 }
115
116 // get the title
117 public function getTitle() {
118 $source = $this->response;
119 $start = stripos($source, ‘<title‘);
120 $source = substr($source, $start);
121 $start = stripos($source, ‘>‘) + 1;
122 $end = stripos($source, ‘<‘, $start);
123 return substr($source, $start, $end-$start);
124 }
125
126 // reset state of the object, only url remain
127 public function clear() {
128 $this->parameter = null;
129 $this->header = null;
130 $this->response = null;
131 $this->proxy = null;
132 $this->method = ‘GET‘;
133 }
134
135 // getter
136 public function getUrl() { return $this->url; }
137 public function getParameter() { return $this->parameter; }
138 public function getHeader() { return $this->header; }
139 public function getProxy() { return $this->proxy; }
140 public function getMethod() { return $this->method; }
141 public function getState() { return $this->state; }
142 public function getResponse() { return $this->response; }
143
144 // private function, mix the parameter with url if the method is ‘GET‘
145 private function handleParameter() {
146 if ($this->parameter != null) {
147 if ($this->method == ‘GET‘) {
148 $this->url .= (‘?‘.$this->parameter);
149 }
150 }
151 }
152 }
153 ?>
Http原理及PHP中cURL的使用,布布扣,bubuko.com
时间： 2024-08-03 03:05:14