modules/youtube.py

   1 # Erebus IRC bot - Author: Conny Sjoblom
   2 # Spotify URL Checker
   3 # This file is released into the public domain; see http://unlicense.org/
   4
   5 # module info
   6 modinfo = {
   7         'author': 'Conny Sjoblom',
   8         'license': 'public domain',
   9         'compatible': [1], # compatible module API versions
  10         'depends': [], # other modules required to work properly?
  11 }
  12
  13 # preamble
  14 import modlib
  15 lib = modlib.modlib(__name__)
  16 modstart = lib.modstart
  17 modstop = lib.modstop
  18
  19 # module code
  20 import re
  21 import urllib2
  22 import HTMLParser
  23 from BeautifulSoup import BeautifulSoup
  24
  25 checkfor = "youtube"
  26 hostmask_regex = re.compile('^(.*)!(.*)@(.*)$')
  27 url_regex = re.compile('http[s]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\(\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+')
  28 def parser_hostmask(hostmask):
  29         if isinstance(hostmask, dict):
  30                 return hostmask
  31
  32         nick = None
  33         user = None
  34         host = None
  35
  36         if hostmask is not None:
  37                 match = hostmask_regex.match(hostmask)
  38
  39                 if not match:
  40                         nick = hostmask
  41                 else:
  42                         nick = match.group(1)
  43                         user = match.group(2)
  44                         host = match.group(3)
  45
  46         return {
  47                 'nick': nick,
  48                 'user': user,
  49                 'host': host
  50         }
  51
  52 @lib.hooknum("PRIVMSG")
  53 def privmsg_hook(bot, line):
  54         sender = parser_hostmask(line[1:line.find(' ')])
  55
  56         try:
  57                 linetx = line.split(None, 3)[3][1:]
  58         except IndexError:
  59                 linetx = ''
  60
  61         if checkfor not in line:
  62                 return # doesn't concern us
  63
  64         for url in url_regex.findall(linetx):
  65                 if checkfor in url:
  66                         html_parser = HTMLParser.HTMLParser()
  67                         respdata = urllib2.urlopen(url).read()
  68                         soup = BeautifulSoup(respdata)
  69                         try:
  70                                 bot.msg(line.split()[2], BeautifulSoup(soup.title.string, convertEntities=BeautifulSoup.HTML_ENTITIES))
  71                         except:
  72                                 pass