modules/urls.py

   1 # Erebus IRC bot - Author: Erebus Team
   2 # URL Checker
   3 # This file is released into the public domain; see http://unlicense.org/
   4
   5 # module info
   6 modinfo = {
   7         'author': 'Erebus Team',
   8         'license': 'public domain',
   9         'compatible': [1], # compatible module API versions
  10         'depends': [], # other modules required to work properly?
  11 }
  12
  13 # http://embed.ly/tools/generator
  14
  15 # preamble
  16 import modlib
  17 lib = modlib.modlib(__name__)
  18 modstart = lib.modstart
  19 modstop = lib.modstop
  20
  21 # module code
  22 import re, urllib2, urlparse, json, HTMLParser
  23 from BeautifulSoup import BeautifulSoup
  24
  25 html_parser = HTMLParser.HTMLParser()
  26
  27 hostmask_regex = re.compile(r'^(.*)!(.*)@(.*)$')
  28 url_regex = re.compile(r'((?:https?://|spotify:)[^\s]+)')
  29 spotify_regex = (
  30         re.compile(r'spotify:(?P<type>\w+):(?P<track_id>\w{22})'),
  31         re.compile(r'https?://open.spotify.com/(?P<type>\w+)/(?P<track_id>\w{22})')
  32 )
  33 youtube_regex = (
  34         re.compile(r'https?://(?:www\.)?youtube\.com/watch\?[a-zA-Z0-9=&_\-]+'),
  35 )
  36 twitch_regex = (
  37         re.compile(r'https?://(?:www\.)?twitch.tv/(.*)\w{1,}'),
  38 )
  39
  40 def parser_hostmask(hostmask):
  41         if isinstance(hostmask, dict):
  42                 return hostmask
  43
  44         nick = None
  45         user = None
  46         host = None
  47
  48         if hostmask is not None:
  49                 match = hostmask_regex.match(hostmask)
  50
  51                 if not match:
  52                         nick = hostmask
  53                 else:
  54                         nick = match.group(1)
  55                         user = match.group(2)
  56                         host = match.group(3)
  57
  58         return {
  59                 'nick': nick,
  60                 'user': user,
  61                 'host': host
  62         }
  63
  64 @lib.hooknum("PRIVMSG")
  65 def privmsg_hook(bot, textline):
  66         user = parser_hostmask(textline[1:textline.find(' ')])
  67         chan = textline.split()[2]
  68
  69         try:
  70                 line = textline.split(None, 3)[3][1:]
  71         except IndexError:
  72                 line = ''
  73
  74         for match in url_regex.findall(line):
  75                 if match:
  76                         print match
  77                         if 'open.spotify.com' in match or 'spotify:' in match:
  78                                 for r in spotify_regex:
  79                                         for sptype, track in r.findall(match):
  80                                                 bot.msg(chan, unescape(gotspotify(sptype, track)))
  81
  82                         elif 'youtube.com' in match or 'youtu.be' in match:
  83                                 for r in youtube_regex:
  84                                         for url in r.findall(match):
  85                                                 bot.msg(chan, unescape(gotyoutube(url)))
  86
  87                         elif 'twitch.tv' in match:
  88                                 for r in twitch_regex:
  89                                         for uri in r.findall(match):
  90                                                 bot.msg(chan, unescape(gottwitch(uri)))
  91
  92                         else:
  93                                 bot.msg(chan, unescape(goturl(match)))
  94
  95 def unescape(line):
  96         return html_parser.unescape(line)
  97
  98 def gotspotify(type, track):
  99         url = 'http://ws.spotify.com/lookup/1/?uri=spotify:%s:%s' % (type, track)
 100         xml = urllib2.urlopen(url).read()
 101         soup = BeautifulSoup(xml, convertEntities=BeautifulSoup.HTML_ENTITIES)
 102         lookup_type = soup.contents[2].name
 103
 104         if lookup_type == 'track':
 105                 name = soup.find('name').string
 106                 album_name = soup.find('album').find('name').string
 107                 artist_name = soup.find('artist').find('name').string
 108                 popularity = soup.find('popularity')
 109                 if popularity:
 110                         popularity = float(popularity.string)*100
 111                 length = float(soup.find('length').string)
 112                 minutes = int(length)/60
 113                 seconds =  int(length)%60
 114
 115                 return 'Track: %s - %s / %s %s:%.2d %2d%%' % (artist_name, name, album_name, minutes, seconds, popularity)
 116
 117         elif lookup_type == 'album':
 118                 album_name = soup.find('album').find('name').string
 119                 artist_name = soup.find('artist').find('name').string
 120                 released = soup.find('released').string
 121                 return 'Album: %s - %s - %s' % (artist_name, album_name, released)
 122
 123         else:
 124                 return 'Unsupported type.'
 125
 126 def gotyoutube(url):
 127         url_data = urlparse.urlparse(url)
 128         query = urlparse.parse_qs(url_data.query)
 129         video = query["v"][0]
 130         api_url = 'http://gdata.youtube.com/feeds/api/videos/%s?alt=json&v=2' % video
 131         try:
 132                 respdata = urllib2.urlopen(api_url).read()
 133                 video_info = json.loads(respdata)
 134
 135                 title = video_info['entry']['title']["$t"]
 136                 author = video_info['entry']['author'][0]['name']['$t']
 137
 138                 return "Youtube: %s (%s)" % (title, author)
 139         except:
 140                 pass
 141
 142 def gottwitch(uri):
 143                 url = 'http://api.justin.tv/api/stream/list.json?channel=%s' % uri.split('/')[0]
 144                 respdata = urllib2.urlopen(url).read()
 145                 twitch = json.loads(respdata)
 146                 try:
 147                         return 'Twitch: %s (%s playing %s)' % (twitch[0]['channel']['status'], twitch[0]['channel']['login'], twitch[0]['channel']['meta_game'])
 148                 except:
 149                         return 'Twitch: Channel offline.'
 150
 151 def goturl(url):
 152         soup = BeautifulSoup(urllib2.urlopen(url))
 153         return soup.title.string