用于纠正 SimpleHtmlDom 抓取的网页中损坏的链接的功能

如果您正在使用，simple HTML dom您可以使用以下代码段来调整 URL

<?php
    require 'simple_html_dom.php';

    class Parser {
        protected $url;
        protected $url_parts;

        protected $html_dom = null;
        protected $path = null;

        public function __construct($url) {
            $this->setUrl($url);
        }

        protected function setUrl($url) {
            $this->url = $url;
            $this->url_parts = parse_url($url);
            return $this;
        }

        protected function getUrl() {
            return $this->url;
        }

        protected function getUrlParts() {
            return $this->url_parts;
        }

        protected function getHtmlDom() {
            if ($this->html_dom === null) $this->html_dom = file_get_html($this->getUrl());
            return $this->html_dom;
        }

        /** ------------
            - path ends with /, e.g. foo/bar/foo/, so the full path for the relative image is foo/bar/foo
            - path doesn't end with / e.g. foo/bar/foo, so the full path the relative image is foo/bar
        ------------ **/
        public function getPath() {
            if ($this->path === null) $this->path = isset($this->getUrlParts()['path']) ? implode('/', explode('/', $this->getUrlParts()['path'], -1)) : '';
            return $this->path;
        }

        public function getHost() {
            return (isset($this->getUrlParts()['scheme']) ? $this->getUrlParts()['scheme'] : 'http').'://'.$this->getUrlParts()['host'];
        }

        public function adjust($tag, $attribute) {
            foreach($this->getHtmlDom()->find($tag) as $element) {
                if (parse_url($element->$attribute, PHP_URL_SCHEME) === null) {
                    // Test if SRC starts with /, if so only append host part of the URL cause image starts at root
                    if (strpos($element->$attribute, '/') === 0) {
                        $element->$attribute = $this->getHost().$element->$attribute;
                    }else{
                        $element->$attribute = $this->getHost().$this->getPath().'/'.$element->$attribute;
                    }
                }
            }

            return $this;
        }

        public function getHtml() {
            return (string)$this->getHtmlDom();
        }
    }

    $parser = new Parser('https://www.darkbee.be/stack/images/index.html');

    $parser->adjust('img', 'src')
           ->adjust('a', 'href')
           ->adjust('link', 'href')
           ->adjust('script', 'src');
           ;

    echo $parser->getHtml();