未定义函数 load_file() 简单 html dom 库
undefined function load_file() simple html dom library
我想使用简单 HTML DOM 库从网站上抓取内容。我正在编写脚本的第一页包含标题和文章内容的 links。所以我想应用的逻辑是我从第一页获取 links,然后从每个 link 指向的每个页面获取内容。我在第二个 load_file.
中收到 undefined function load_file() 错误
<?php
defined('BASEPATH') OR exit('No direct script access allowed');
class Crawler extends Frontend_controller {
public function __construct(){
parent::__construct();
require_once(APPPATH . 'libraries/simple_html_dom.php');
}
public function index(){
$target_url = "https://example.com/";
$html = new simple_html_dom();
$html->load_file($target_url);
foreach($html->find('article') as $post){
$title = $post->find('h1 a', 0)->innertext;
$link = $post->find('h1 a', 0);
//echo $title."<br />";
//echo $link->href."<br />";
$sample_html = new simple_html_dom();
$sample_html = load_file($link->href);
foreach ($sample_html->find('p') as $content) {
echo $content;
}
}
}//end method
}//end class
改变
$sample_html = load_file($link->href);
到
$sample_html->load_file($link->href);
我想使用简单 HTML DOM 库从网站上抓取内容。我正在编写脚本的第一页包含标题和文章内容的 links。所以我想应用的逻辑是我从第一页获取 links,然后从每个 link 指向的每个页面获取内容。我在第二个 load_file.
中收到 undefined function load_file() 错误 <?php
defined('BASEPATH') OR exit('No direct script access allowed');
class Crawler extends Frontend_controller {
public function __construct(){
parent::__construct();
require_once(APPPATH . 'libraries/simple_html_dom.php');
}
public function index(){
$target_url = "https://example.com/";
$html = new simple_html_dom();
$html->load_file($target_url);
foreach($html->find('article') as $post){
$title = $post->find('h1 a', 0)->innertext;
$link = $post->find('h1 a', 0);
//echo $title."<br />";
//echo $link->href."<br />";
$sample_html = new simple_html_dom();
$sample_html = load_file($link->href);
foreach ($sample_html->find('p') as $content) {
echo $content;
}
}
}//end method
}//end class
改变
$sample_html = load_file($link->href);
到
$sample_html->load_file($link->href);