[HaBo]

  32    $scrap = scraper {
  33       process '//div[@id="bodyContent"]/p', 'text[]' => 'TEXT';
  34       process '//img', 'img[]' => '@src';
  35       process '//div[@id="bodyContent"]/ul/li', 'list[]' => 'TEXT';
  36       process '//table/tr/td', 'table[]' => 'TEXT';
  37    };
  38    $url = URI->new($wikiurl);
  39 
  40    my $res = $scrap->scrape($url);
  41    my $text = $res->{'text'};
  42    my $img = $res->{'img'};
  43    my $list = $res->{'list'};
  44    my $table = $res->{'table'};

>>> from xml.etree.ElementTree import ElementTree
>>> import urllib
>>> content=urllib.urlopen("http://hackerboard.de").read()
>>> tree=ElementTree.fromstring(content)

>easy_install BeautifulSoup
>python
>>> import urllib
>>> content=urllib.urlopen("http://hackerboard.de").read()
>>> from BeautifulSoup import BeautifulSoup
>>> soup = BeautifulSoup(content)
>>> divs = soup.findAll('div', id="wrapper")
>>> divs[0].contents[1]
<div id="header-tabs"><a href="http://wiki.hackerboard.de" title="Hackerboard Wi
ki"><img src="http://www.hackerboard.de/images/habo/misc/wiki_tab.png" border="0" alt="Hackerboard Wiki" /
></a><a href="http://www.haboweb.de" title="HaboWeb Linkverzeichnis"><img src="i
mages/habo/misc/haboweb_tab.png" border="0" alt="HaboWeb Linkverzeichnis" /></a>
</div>
>>> divs[0].contents[1].find("img")
<img src="http://www.hackerboard.de/images/habo/misc/wiki_tab.png" border="0" alt="Hackerboard Wiki" />

>>> all_divs = soup.findAll("div", id = re.compile("w.*"))
>>> [div.get("id") for div in all_divs]
[u'wrapper', u'rounded-wrap']
>>> all_divs[0].find("img")
<img src="http://www.hackerboard.de/images/habo/misc/wiki_tab.png" border="0" alt="Hackerboard Wiki" />

>>> divs = dict([(div.get("id"), div.contents) for div in soup.findAll("div")])
>>> divs.keys()
[u'wrapper', u'rounded-wrap', u'navbsr', u'footer', u'rounded-top', u'footer-tex
t', u'rounded-bottom', None, u'naeXTReMe', u'header-tabs']
>>> import sys
>>> from xml.dom.minidom import *
>>> doc = Document();
>>> root = doc.createElement("mydivs")
>>> doc.appendChild(root)
<DOM Element: mydivs at 0x35ed688>
>>> for id, contents in divs.items():
...   if not(id):
...       continue
...   node = doc.createElement(id)
...   root.appendChild(node)
...   for content in contents:
...     try:
...       node.appendChild(doc.createTextNode(str(content.text[:20])))
...     except AttributeError:
...       pass