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, datetime
  37
  38 html_parser = HTMLParser.HTMLParser()
  39
  40 hostmask_regex = re.compile(r'^(.*)!(.*)@(.*)$')
  41
  42 def parser_hostmask(hostmask):
  43         if isinstance(hostmask, dict):
  44                 return hostmask
  45
  46         nick = None
  47         user = None
  48         host = None
  49
  50         if hostmask is not None:
  51                 match = hostmask_regex.match(hostmask)
  52
  53                 if not match:
  54                         nick = hostmask
  55                 else:
  56                         nick = match.group(1)
  57                         user = match.group(2)
  58                         host = match.group(3)
  59
  60         return {
  61                 'nick': nick,
  62                 'user': user,
  63                 'host': host
  64         }
  65
  66 class SmartRedirectHandler(urllib2.HTTPRedirectHandler):
  67         def http_error_301(self, req, fp, code, msg, headers):
  68                 result = urllib2.HTTPRedirectHandler.http_error_301(
  69                                 self, req, fp, code, msg, headers)
  70                 result.status = code
  71                 return result
  72
  73         def http_error_302(self, req, fp, code, msg, headers):
  74                 result = urllib2.HTTPRedirectHandler.http_error_302(
  75                                 self, req, fp, code, msg, headers)
  76                 result.status = code
  77                 return result
  78
  79 def process_line(line):
  80         responses = []
  81         num_found = 0
  82         limit = lib.parent.cfg.getint('urls', 'limit', 2)
  83         for action, group, prefix in regexes:
  84                 for regex in group:
  85                         for match in regex.findall(line):
  86                                 if match:
  87                                         num_found += 1
  88                                         if num_found > limit:
  89                                                 return responses
  90                                         resp = action(match)
  91                                         if resp is not None:
  92                                                 responses.append("%s: %s" % (prefix, action(match)))
  93         return responses
  94
  95 @lib.hooknum("PRIVMSG")
  96 def privmsg_hook(bot, textline):
  97         user = parser_hostmask(textline[1:textline.find(' ')])
  98         chan = textline.split()[2]
  99
 100         try:
 101                 line = textline.split(None, 3)[3][1:]
 102         except IndexError:
 103                 line = ''
 104
 105         responses = process_line(line)
 106         if len(responses) > 0:
 107                 if lib.parent.cfg.getboolean('urls', 'multiline'):
 108                         for r in responses:
 109                                 bot.msg(chan, r, True)
 110                 else:
 111                         bot.msg(chan, ' | '.join(responses), True)
 112
 113 def unescape(line):
 114         return re.sub('\s+', ' ', html_parser.unescape(line))
 115
 116 def gotspotify(type, track):
 117         url = 'http://ws.spotify.com/lookup/1/?uri=spotify:%s:%s' % (type, track)
 118         xml = urllib2.urlopen(url).read()
 119         soup = BeautifulSoup(xml, convertEntities=BeautifulSoup.HTML_ENTITIES)
 120         lookup_type = soup.contents[2].name
 121
 122         if lookup_type == 'track':
 123                 name = soup.find('name').string
 124                 album_name = soup.find('album').find('name').string
 125                 artist_name = soup.find('artist').find('name').string
 126                 popularity = soup.find('popularity')
 127                 if popularity:
 128                         popularity = float(popularity.string)*100
 129                 length = float(soup.find('length').string)
 130                 minutes = int(length)/60
 131                 seconds = int(length)%60
 132
 133                 return unescape('Track: %s - %s / %s %s:%.2d %2d%%' % (artist_name, name, album_name, minutes, seconds, popularity))
 134
 135         elif lookup_type == 'album':
 136                 album_name = soup.find('album').find('name').string
 137                 artist_name = soup.find('artist').find('name').string
 138                 released = soup.find('released').string
 139                 return unescape('Album: %s - %s - %s' % (artist_name, album_name, released))
 140
 141         else:
 142                 return 'Unsupported type.'
 143
 144 def _yt_duration(s):
 145         mo = re.match(r'P(\d+D)?T(\d+H)?(\d+M)?(\d+S)?', s)
 146         pcs = [x for x in mo.groups() if x]
 147         return ''.join(pcs).lower()
 148 def _yt_date(s, f):
 149         mo = re.match(r'(\d{4})-(\d{2})-(\d{2})T(\d{2}):(\d{2}):(\d{2})\.(\d+)Z', s)
 150         return datetime.datetime(*(int(x) for x in mo.groups())).strftime(f)
 151 def _yt_round(n):
 152         n = float(n)
 153         if n >= 10**12:
 154                 return '%.1ft' % (n/10**12)
 155         elif n >= 10**9:
 156                 return '%.1fb' % (n/10**9)
 157         elif n >= 10**6:
 158                 return '%.1fm' % (n/10**6)
 159         elif n >= 10**3:
 160                 return '%.1fk' % (n/10**3)
 161         else:
 162                 return int(n)
 163
 164 def gotyoutube(url):
 165         url_data = urlparse.urlparse(url)
 166         query = urlparse.parse_qs(url_data.query)
 167         video = query["v"][0]
 168         api_url = 'https://www.googleapis.com/youtube/v3/videos?part=snippet,contentDetails,statistics&id=%s&key=%s' % (video, lib.parent.cfg.get('urls', 'api_key'))
 169         try:
 170                 respdata = urllib2.urlopen(api_url).read()
 171                 v = json.loads(respdata)
 172                 v = v['items'][0]
 173
 174                 return unescape(lib.parent.cfg.get('urls', 'yt_format', "\002%(author)s\002: \037%(title)s\037 [%(duration)s, uploaded %(uploaded)s, %(views)s v/%(likes)s l/%(dislikes)s d]") % {
 175                         'title': v['snippet']['title'],
 176                         'author': v['snippet']['channelTitle'],
 177                         'duration': _yt_duration(v['contentDetails']['duration']),
 178                         'uploaded': _yt_date(v['snippet']['publishedAt'], lib.parent.cfg.get('urls', 'yt_date_format', '%b %d %Y')),
 179                         'views': _yt_round(v['statistics']['viewCount']),
 180                         'likes': _yt_round(v['statistics']['likeCount']),
 181                         'dislikes': _yt_round(v['statistics']['dislikeCount']),
 182                 })
 183         except urllib2.HTTPError as e:
 184                 if e.getcode() == 403:
 185                         return 'API limit exceeded'
 186                 else:
 187                         return str(e)
 188         except IndexError:
 189                 return 'no results'
 190         except Exception as e:
 191                 return str(e)
 192
 193 def gottwitch(uri):
 194         url = 'https://api.twitch.tv/helix/streams?user_login=%s' % uri.split('/')[0]
 195         opener = urllib2.build_opener()
 196         opener.addheaders = [('Client-ID', lib.parent.cfg.get('urls', 'twitch_api_key'))]
 197         respdata = opener.open(url).read()
 198         twitch = json.loads(respdata)['data']
 199         try:
 200                 # TODO: add current game.
 201                 return unescape('\037%s\037 is %s (%s)' % (twitch[0]['user_name'], twitch[0]['type'], twitch[0]['title']))
 202         except:
 203                 return 'Channel offline.'
 204
 205 def goturl(url):
 206         for _, group, _ in other_regexes:
 207                 for regex in group:
 208                         if regex.match(url):
 209                                 return None
 210         request = urllib2.Request(url)
 211         opener = urllib2.build_opener(SmartRedirectHandler())
 212         try:
 213                 soup = BeautifulSoup(opener.open(request, timeout=0.5))
 214                 return unescape('%s' % (soup.title.string))
 215         except urllib2.HTTPError as e:
 216                 return 'Error: %s %s' % (e.code, e.reason)
 217         except Exception as e:
 218                 return 'Error: %r' % (e.message)
 219
 220 url_regex = (
 221         re.compile(r'https?://[^/\s]+\.[^/\s]+(?:/\S+)?'),
 222 )
 223 spotify_regex = (
 224         re.compile(r'spotify:(?P<type>\w+):(?P<track_id>\w{22})'),
 225         re.compile(r'https?://open.spotify.com/(?P<type>\w+)/(?P<track_id>\w+)')
 226 )
 227 youtube_regex = (
 228         re.compile(r'https?://(?:www\.)?youtube\.com/watch\?[a-zA-Z0-9=&_\-]+'),
 229 )
 230 twitch_regex = (
 231         re.compile(r'https?:\/\/(?:www\.)?twitch.tv\/([A-Za-z0-9]*)'),
 232 )
 233 other_regexes = (
 234         (gotspotify, spotify_regex, 'Spotify'),
 235         (gotyoutube, youtube_regex, 'YouTube'),
 236         (gottwitch, twitch_regex, 'Twitch'),
 237 )
 238 regexes = other_regexes + (
 239         (goturl, url_regex, 'Title'),
 240 )