Wyszukiwarka plików HTML w PHP i SQLite

def get_data(html):
    """return dictionary with title url and content of the blog post"""
    tree = BeautifulSoup(html, 'html5lib')

    body = tree.body
    if body is None:
        return None

    for tag in body.select('script'):
        tag.decompose()
    for tag in body.select('style'):
        tag.decompose()
    for tag in body.select('figure'):
        tag.decompose()

    text = tree.findAll("div", {"class": "body"})
    if len(text) > 0:
      text = text[0].get_text(separator='\n')
    else:
      text = None
    title = tree.findAll("h2", {"itemprop" : "title"})
    url = tree.findAll("link", {"rel": "canonical"})
    if len(title) > 0:
      title = title[0].get_text()
    else:
      title = None
    if len(url) > 0:
      url = url[0]['href']
    else:
      url = None
    result = {
      "title": title,
      "url": url,
      "text": text
    }
    return result

import os, sys, re, sqlite3
from bs4 import BeautifulSoup

if __name__ == '__main__':
  if len(sys.argv) == 2:
    db_file = 'index.db'
    # usunięcie starego pliku
    if os.path.exists(db_file):
      os.remove(db_file)
    conn = sqlite3.connect(db_file)
    c = conn.cursor()
    c.execute('CREATE TABLE page(title text, url text, content text)')
    # traversowanie drzewa katalogów
    for root, dirs, files in os.walk(sys.argv[1]):
      for name in files:
        if name.endswith(".html") and re.search(r"[/\\]20[0-9]{2}", root):
          fname = os.path.join(root, name)
          f = open(fname, "r")
          data = get_data(f.read())
          f.close()
          if data is not None:
            data = (data['title'], data['url'], data['text']
            c.execute('INSERT INTO page VALUES(?, ?, ?)', data))
            print "indexed %s" % data['url']
            sys.stdout.flush() # flush wyświetli text z print na terminalu
    conn.commit() # bez tego nie zapiszą się dane
    conn.close()

<?php

function mark($query, $str) {
    return preg_replace("%(" . $query . ")%i", '<mark>$1</mark>', $str);
}

if (isset($_GET['q'])) {
  $db = new PDO('sqlite:index.db');
  $stmt = $db->prepare('SELECT * FROM page WHERE content LIKE :var OR title LIKE :var');
  $wildcarded = '%'. $_GET['q'] .'%';
  $stmt->bindParam(':var', $wildcarded); // trzeba użyć zmiennej w tym miejscu
  $stmt->execute();
  $data = $stmt->fetchAll(PDO::FETCH_ASSOC);
  // bez tego nie można byłoby wyszukać %
  $query = str_replace("%", "\\%", preg_quote($_GET['q']));
  $re = "%(?>\S+\s*){0,10}(" . $query . ")\s*(?>\S+\s*){0,10}%i";
  if (count($data) == 0) {
    echo "<p>Brak wyników</p>";
  } else {
    foreach ($data as $row) {
      if (preg_match($re, $row['content'], $match)) {
        echo '<h3><a href="' . $row['url'] . '">' . mark($query, $row['title']) . '</a></h2>';
        // usunięcie zbędnych znaków interpunkcyjnych oraz białych znaków
        $text = trim($match[0], " \t\n\r\0\x0B,.{}()-");
        echo '<p>' . mark($query, $text) . '</p>';
      }
    }
  }
}

?>

---
layout: default
---
<section class="search">
  <div>
    <header>
       <h2>
          Wyszukanie
          "<?= isset($_GET['q']) ? strip_tags($_GET['q']) : '' ?>"
       </h2>
    </header>
<?php /* kod php */ ?>
  </div>
</section>

<div id="search">
    <form action="https://jcubic.pl/search.php">
        <input name="q" placeholder="text do wyszukania"/>
        <input type="submit" value="wyszukaj"/>
    </form>
</div>

#search button {
    background-color: #171f32;
    color: #E9E9E8;
    width: 90px;
}
#search input {
    border: 1px solid #171f32;
    /* 90 button width + 10 padding + 2 border input + 4 border button */
    width: calc(100% - 106px);
}
#search {
    margin-bottom: 20px;
}
#search input, #search button {
    padding: 3px 5px;
    font-size: 1em;
}