- matches = re.findall("(https?://[^\s]+)", msg)
- for i in range(len(matches)):
- url = matches[i]
- webpage = urllib.request.urlopen(url)
- content_type = webpage.info().get_content_type()
- charset = webpage.info().get_content_charset()
- if not charset or not content_type in ('text/html', 'text/xml',
- 'application/xhtml+xml'):
- continue
- content = webpage.read().decode(charset)
- title = str(content).split('<title>')[1].split('</title>')[0]
- title = html.unescape(title)
- io.send_line("PRIVMSG "
- + target + " :page title for url: " + title)