【发布时间】:2015-04-29 02:22:18
【问题描述】:
我正在使用 php 和 cURL 来抓取网页,但是这个网页设计得很糟糕(因为标签上没有类或 id),所以我需要搜索特定的文本,然后转到保存它的标签(即<p>)然后移动到下一个孩子(或下一个<p>)并获取文本。
我需要从页面中获取各种内容,其中一些也是 <a onclick="get this stuff here"> 中的文本。所以基本上我觉得我需要使用 cURL 将源代码抓取到一个 php 变量,然后我可以使用 php 进行解析并找到我需要的东西。
这听起来是不是最好的方法?有没有人有任何指针或可以演示我如何将源代码从 cURL 放入变量中?
谢谢!
编辑(工作/当前代码)-----------
<?php
class Scrape
{
public $cookies = 'cookies.txt';
private $user = null;
private $pass = null;
/*Data generated from cURL*/
public $content = null;
public $response = null;
/* Links */
private $url = array(
'login' => 'https://website.com/login.jsp',
'submit' => 'https://website.com/LoginServlet',
'page1' => 'https://website.com/page1',
'page2' => 'https://website.com/page2',
'page3' => 'https://website.com/page3'
);
/* Fields */
public $data = array();
public function __construct ($user, $pass)
{
$this->user = $user;
$this->pass = $pass;
}
public function login()
{
$this->cURL($this->url['login']);
if($form = $this->getFormFields($this->content, 'login'))
{
$form['login'] = $this->user;
$form['password'] =$this->pass;
// echo "<pre>".print_r($form,true);exit;
$this->cURL($this->url['submit'], $form);
//echo $this->content;//exit;
}
//echo $this->content;//exit;
}
// NEW TESTING
public function loadPage($page)
{
$this->cURL($this->url[$page]);
echo $this->content;//exit;
}
/* Scan for form */
private function getFormFields($data, $id)
{
if (preg_match('/(<form.*?name=.?'.$id.'.*?<\/form>)/is', $data, $matches)) {
$inputs = $this->getInputs($matches[1]);
return $inputs;
} else {
return false;
}
}
/* Get Inputs in form */
private function getInputs($form)
{
$inputs = array();
$elements = preg_match_all('/(<input[^>]+>)/is', $form, $matches);
if ($elements > 0) {
for($i = 0; $i < $elements; $i++) {
$el = preg_replace('/\s{2,}/', ' ', $matches[1][$i]);
if (preg_match('/name=(?:["\'])?([^"\'\s]*)/i', $el, $name)) {
$name = $name[1];
$value = '';
if (preg_match('/value=(?:["\'])?([^"\']*)/i', $el, $value)) {
$value = $value[1];
}
$inputs[$name] = $value;
}
}
}
return $inputs;
}
/* Perform curl function to specific URL provided */
public function cURL($url, $post = false)
{
$ch = curl_init();
curl_setopt($ch, CURLOPT_CONNECTTIMEOUT, 30);
curl_setopt($ch, CURLOPT_USERAGENT, "Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.13) Gecko/20080311 Firefox/2.0.0.13");
// "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_8_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/30.0.1599.101 Safari/537.36");
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
curl_setopt($ch, CURLOPT_SSL_VERIFYPEER, false);
curl_setopt($ch, CURLOPT_SSL_VERIFYHOST, false);
curl_setopt($ch, CURLOPT_VERBOSE, 1);
curl_setopt($ch, CURLOPT_FOLLOWLOCATION, 1);
curl_setopt($ch, CURLOPT_COOKIEJAR, $this->cookies);
curl_setopt($ch, CURLOPT_COOKIEFILE, $this->cookies);
curl_setopt($ch, CURLOPT_HEADER, 0);
curl_setopt($ch, CURLOPT_RETURNTRANSFER,1);
curl_setopt($ch, CURLOPT_CONNECTTIMEOUT, 120);
curl_setopt($ch, CURLOPT_TIMEOUT, 120);
if($post) //if post is needed
{
curl_setopt($ch, CURLOPT_POST, 1);
curl_setopt($ch, CURLOPT_POSTFIELDS, http_build_query($post));
}
curl_setopt($ch, CURLOPT_URL, $url);
$this->content = curl_exec($ch);
$this->response = curl_getinfo( $ch );
$this->url['last_url'] = curl_getinfo($ch, CURLINFO_EFFECTIVE_URL);
curl_close($ch);
}
}
$sc = new Scrape('user','pass');
$sc->login();
$sc->loadPage('page1');
echo "<h1>TESTTESTEST</h1>";
$sc->loadPage('page2');
echo "<h1>TESTTESTEST</h1>";
$sc->loadPage('page3');
echo "<h1>TESTTESTEST</h1>";
(注:感谢@Ramz scrape a website with secured login)
【问题讨论】:
-
请给我们一些代码,以便我们为您提供帮助。
标签: php parsing curl web-scraping