Web scraper for vbulletin. Create pdf of pages and whole thread and downloads all attached images.

download.php

<?php

const BASE = '';
const COUNT = 1;

$pages = [];
for ($i = 1; $i <= COUNT; $i++) {
  $suffix = $i > 1 ? '/page' . $i : '';
  $pages[] = $page = 'page' . $i . '.pdf';
  $url = BASE . $suffix;
  execute('wkhtmltopdf ' . escapeshellarg($url) . ' ' . escapeshellarg($page));


  print_section('Extracting images...');
  if ($xml = load($url)) {
    if (!is_dir('images')) mkdir('images');

    $key = 1;
    foreach ($xml->xpath('//div[@id="postlist"]//div[@class="postrow"]//img[contains(@src, "attachment")]') as $image) {
      $src = (string) $image['src'];
      $out = 'images/page' . $i . '.' . $key++ . '.jpg';
      execute('wget -O ' . escapeshellarg($out) . ' ' . escapeshellarg($src));
    }
  }
  else {
    echo "FAILED TO LOAD $url\n";
  }
}

execute('pdfunite ' . implode(' ', $pages) . ' full.pdf');


function execute($command) {
  print_section($command);
  passthru($command);
}

function print_section($text) {
  echo "\n\n$text\n\n";
}

function load($url) {
  if ($contents = file_get_contents($url)) {
    $document = @DOMDocument::loadHTML($contents);
    if ($document) {
      return simplexml_import_dom($document);
    }
  }

  return false;
}