PHP WebsiteParser示例

示例#1

文件： Seo_websites.php 项目： Callquent/websites-management

 public function metawebsite($w_id = '', $wp_id = '')
 {
     if ($this->uri->total_segments() == 3) {
         $all_websites = $this->model_front->get_all_websites();
         $row = $all_websites->row($w_id);
         $parser = new WebsiteParser($row->w_url_rw);
         $meta_tags = $parser->getMetaTags(true);
         $meta_title = $parser->getTitle(true);
         $meta_description = "";
         foreach ($meta_tags as $meta_tag) {
             if ($meta_tag[0] == 'description') {
                 $meta_description = $meta_tag[1];
             }
         }
         $datatable = array(0 => $row->w_title, 1 => '<a href="https://www.google.com/search?q=info:' . $row->w_url_rw . '" target="_blank">' . $row->w_url_rw . '</a>', 2 => html_entity_decode($meta_title, ENT_QUOTES), 3 => html_entity_decode($meta_description, ENT_QUOTES), 4 => '<a href="' . site_url('seo-websites/' . $row->w_id) . '" class="viewdata btn btn-success btn-xs" data-toggle="modal"><span class="fa fa-eye"></a>');
         echo json_encode($datatable, JSON_FORCE_OBJECT);
     } elseif ($this->uri->total_segments() == 4) {
         $row = $this->model_front->get_website($w_id)->row();
         $parser = new WebsiteParser($this->arr[$wp_id]);
         $meta_tags = $parser->getMetaTags(true);
         $meta_title = $parser->getTitle(true);
         $meta_description = "";
         foreach ($meta_tags as $meta_tag) {
             if ($meta_tag[0] == 'description') {
                 $meta_description = $meta_tag[1];
             }
         }
         $datatable = array(0 => $row->w_title, 1 => '<a href="https://www.google.com/search?q=info:' . $this->arr[$wp_id] . '" target="_blank">' . $this->arr[$wp_id] . '</a>', 2 => html_entity_decode($meta_title, ENT_QUOTES), 3 => html_entity_decode($meta_description, ENT_QUOTES));
         echo json_encode($datatable, JSON_FORCE_OBJECT);
     }
 }

示例#2

文件： WebsiteParserTest.php 项目： helpfulrobot/ntb-silverstripe-website-parsing

 public function testNormalSite()
 {
     $result = WebsiteParser::parse("http://normal.site");
     $this->assertFalse($result->isError());
     $this->assertFalse($result->hasImage());
     $this->assertEquals("Normal Site", $result->Title);
     $this->assertEquals("The description", $result->Description);
 }

示例#3

文件： ParseWebsiteTask.php 项目： helpfulrobot/ntb-silverstripe-website-parsing

 /**
  * @param SS_HTTPRequest $request
  * @return string
  */
 public function run($request)
 {
     $target = urldecode($request->getVar('target'));
     if (!$target) {
         return "Please provide a target as GET param.";
     }
     $parsedData = WebsiteParser::parse($target);
     var_dump($parsedData);
 }

示例#4

文件： example.php 项目： fayazmiraz/url-scraper-php

<?php

include 'website_parser.php';
//Instance of WebsiteParser
$parser = new WebsiteParser('http://morshed-alam.com/');
//Get all hyper links
$links = $parser->getHrefLinks();
//Get all image sources
$images = $parser->getImageSources();
echo "<pre>";
print_r($links);
echo "<br />";
print_r($images);
echo "</pre>";
/**
* ==========================================
* Sample Output
* ==========================================
Array
(
   [0] => Array
       (
           [0] => https://github.com/joliss/jquery-ui-rails
           [1] => jquery-ui-rails
       )

   [1] => Array
       (
           [0] => http://gembundler.com/rails23.html
           [1] => Click here
       )

示例#5

文件： index.php 项目： fayazmiraz/url-scraper-php

<?php

include 'website_parser.php';
$links = $images = array();
$default_check = 'checked';
$href = isset($_GET['href']) ? 1 : 0;
$image = isset($_GET['image']) ? 1 : 0;
$meta = isset($_GET['meta']) ? 1 : 0;
$target_url = isset($_GET['target_url']) ? $_GET['target_url'] : '';
$link_type = isset($_GET['link_type']) ? $_GET['link_type'] : 'all';
$parser = new WebsiteParser($target_url, $link_type);
if (isset($_GET['target_url'])) {
    $default_check = '';
    $title = $parser->getTitle(true);
    if ($href) {
        $links = $parser->getHrefLinks(false);
    }
    if ($image) {
        $images = $parser->getImageSources();
    }
    if ($meta) {
        $meta_tags = $parser->getMetaTags();
    }
}
?>

<!DOCTYPE html>
<html lang="en">
<head>
    <title>Extract Urls</title>