modules/urls.py

   1 # Erebus IRC bot - Author: Erebus Team
   2 # vim: fileencoding=utf-8
   3 # URL Checker
   4 # This file is released into the public domain; see http://unlicense.org/
   5
   6 # module info
   7 modinfo = {
   8         'author': 'Erebus Team',
   9         'license': 'public domain',
  10         'compatible': [0],
  11         'depends': [],
  12         'softdeps': [],
  13 }
  14
  15 # http://embed.ly/tools/generator
  16
  17 # preamble
  18 import modlib
  19 lib = modlib.modlib(__name__)
  20 modstart = lib.modstart
  21 modstop = lib.modstop
  22
  23 # module code
  24 import sys
  25 if sys.version_info.major < 3:
  26         import urllib2
  27         import urlparse
  28         import HTMLParser
  29         from BeautifulSoup import BeautifulSoup
  30 else:
  31         import urllib.request as urllib2
  32         import urllib.parse as urlparse
  33         import html.parser as HTMLParser
  34         from bs4 import BeautifulSoup
  35
  36 import re, json
  37
  38 html_parser = HTMLParser.HTMLParser()
  39
  40 hostmask_regex = re.compile(r'^(.*)!(.*)@(.*)$')
  41 url_regex = re.compile(r'https?://[^/\s]+\.[^/\s]+(?:/\S+)?')
  42 spotify_regex = (
  43         re.compile(r'spotify:(?P<type>\w+):(?P<track_id>\w{22})'),
  44         re.compile(r'https?://open.spotify.com/(?P<type>\w+)/(?P<track_id>\w+)')
  45 )
  46 youtube_regex = (
  47         re.compile(r'https?://(?:www\.)?youtube\.com/watch\?[a-zA-Z0-9=&_\-]+'),
  48 )
  49 twitch_regex = (
  50         re.compile(r'https?:\/\/(?:www\.)?twitch.tv\/([A-Za-z0-9]*)'),
  51 )
  52
  53 def parser_hostmask(hostmask):
  54         if isinstance(hostmask, dict):
  55                 return hostmask
  56
  57         nick = None
  58         user = None
  59         host = None
  60
  61         if hostmask is not None:
  62                 match = hostmask_regex.match(hostmask)
  63
  64                 if not match:
  65                         nick = hostmask
  66                 else:
  67                         nick = match.group(1)
  68                         user = match.group(2)
  69                         host = match.group(3)
  70
  71         return {
  72                 'nick': nick,
  73                 'user': user,
  74                 'host': host
  75         }
  76
  77 class SmartRedirectHandler(urllib2.HTTPRedirectHandler):
  78         def http_error_301(self, req, fp, code, msg, headers):
  79                 result = urllib2.HTTPRedirectHandler.http_error_301(
  80                                 self, req, fp, code, msg, headers)
  81                 result.status = code
  82                 return result
  83
  84         def http_error_302(self, req, fp, code, msg, headers):
  85                 result = urllib2.HTTPRedirectHandler.http_error_302(
  86                                 self, req, fp, code, msg, headers)
  87                 result.status = code
  88                 return result
  89
  90 @lib.hooknum("PRIVMSG")
  91 def privmsg_hook(bot, textline):
  92         user = parser_hostmask(textline[1:textline.find(' ')])
  93         chan = textline.split()[2]
  94
  95         try:
  96                 line = textline.split(None, 3)[3][1:]
  97         except IndexError:
  98                 line = ''
  99
 100         for match in url_regex.findall(line):
 101                 if match:
 102                         response = goturl(match)
 103                         if response is not None:
 104                                 bot.msg(chan, response)
 105
 106 def unescape(line):
 107         return html_parser.unescape(line)
 108
 109 def gotspotify(type, track):
 110         url = 'http://ws.spotify.com/lookup/1/?uri=spotify:%s:%s' % (type, track)
 111         xml = urllib2.urlopen(url).read()
 112         soup = BeautifulSoup(xml, convertEntities=BeautifulSoup.HTML_ENTITIES)
 113         lookup_type = soup.contents[2].name
 114
 115         if lookup_type == 'track':
 116                 name = soup.find('name').string
 117                 album_name = soup.find('album').find('name').string
 118                 artist_name = soup.find('artist').find('name').string
 119                 popularity = soup.find('popularity')
 120                 if popularity:
 121                         popularity = float(popularity.string)*100
 122                 length = float(soup.find('length').string)
 123                 minutes = int(length)/60
 124                 seconds =  int(length)%60
 125
 126                 return unescape('Track: %s - %s / %s %s:%.2d %2d%%' % (artist_name, name, album_name, minutes, seconds, popularity))
 127
 128         elif lookup_type == 'album':
 129                 album_name = soup.find('album').find('name').string
 130                 artist_name = soup.find('artist').find('name').string
 131                 released = soup.find('released').string
 132                 return unescape('Album: %s - %s - %s' % (artist_name, album_name, released))
 133
 134         else:
 135                 return 'Unsupported type.'
 136
 137 def gotyoutube(url):
 138         url_data = urlparse.urlparse(url)
 139         query = urlparse.parse_qs(url_data.query)
 140         video = query["v"][0]
 141         api_url = 'http://gdata.youtube.com/feeds/api/videos/%s?alt=json&v=2' % video
 142         try:
 143                 respdata = urllib2.urlopen(api_url).read()
 144                 video_info = json.loads(respdata)
 145
 146                 title = video_info['entry']['title']["$t"]
 147                 author = video_info['entry']['author'][0]['name']['$t']
 148
 149                 return unescape("Youtube: %s (%s)" % (title, author))
 150         except:
 151                 pass
 152
 153 def gottwitch(uri):
 154                 url = 'http://api.justin.tv/api/stream/list.json?channel=%s' % uri.split('/')[0]
 155                 respdata = urllib2.urlopen(url).read()
 156                 twitch = json.loads(respdata)
 157                 try:
 158                         return unescape('Twitch: %s (%s playing %s)' % (twitch[0]['channel']['status'], twitch[0]['channel']['login'], twitch[0]['channel']['meta_game']))
 159                 except:
 160                         return 'Twitch: Channel offline.'
 161
 162 def goturl(url):
 163         request = urllib2.Request(url)
 164         opener = urllib2.build_opener(SmartRedirectHandler())
 165         try:
 166                 soup = BeautifulSoup(opener.open(request, timeout=2))
 167                 return unescape('Title: %s' % (soup.title.string))
 168         except:
 169                 return None