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