X-Git-Url: https://jfr.im/git/erebus.git/blobdiff_plain/390fbad48dc38d92c4c2c7db89beab407b4c3ad8..04d483534a020aca9f4879f11c743b775bbdb5f2:/modules/urls.py

diff --git a/modules/urls.py b/modules/urls.py
index 4a1f5f3..72bdb99 100644
--- a/modules/urls.py
+++ b/modules/urls.py
@@ -1,4 +1,5 @@
 # Erebus IRC bot - Author: Erebus Team
+# vim: fileencoding=utf-8
 # URL Checker
 # This file is released into the public domain; see http://unlicense.org/
 
@@ -6,8 +7,9 @@
 modinfo = {
 	'author': 'Erebus Team',
 	'license': 'public domain',
-	'compatible': [1], # compatible module API versions
-	'depends': [], # other modules required to work properly?
+	'compatible': [0],
+	'depends': [],
+	'softdeps': [],
 }
 
 # http://embed.ly/tools/generator
@@ -19,22 +21,35 @@ modstart = lib.modstart
 modstop = lib.modstop
 
 # module code
-import re, urllib2, urlparse, json, HTMLParser
-from BeautifulSoup import BeautifulSoup
+import sys
+if sys.version_info.major < 3:
+	import urllib2
+	import urlparse
+	import HTMLParser
+	from BeautifulSoup import BeautifulSoup
+	import re
+else:
+	import urllib.request as urllib2
+	import urllib.parse as urlparse
+	import html.parser as HTMLParser
+	from bs4 import BeautifulSoup
+	import re
+
+import re, json
 
 html_parser = HTMLParser.HTMLParser()
 
 hostmask_regex = re.compile(r'^(.*)!(.*)@(.*)$')
-url_regex = re.compile(r'((?:https?://|spotify:)[^\s]+)')
+url_regex = re.compile(r'https?://[^/\s]+\.[^/\s]+(?:/\S+)?')
 spotify_regex = (
 	re.compile(r'spotify:(?P<type>\w+):(?P<track_id>\w{22})'),
-	re.compile(r'https?://open.spotify.com/(?P<type>\w+)/(?P<track_id>\w{22})')
+	re.compile(r'https?://open.spotify.com/(?P<type>\w+)/(?P<track_id>\w+)')
 )
 youtube_regex = (
 	re.compile(r'https?://(?:www\.)?youtube\.com/watch\?[a-zA-Z0-9=&_\-]+'),
 )
 twitch_regex = (
-	re.compile(r'https?://(?:www\.)?twitch.tv/(.*)\w{1,}'),
+	re.compile(r'https?:\/\/(?:www\.)?twitch.tv\/([A-Za-z0-9]*)'),
 )
 
 def parser_hostmask(hostmask):
@@ -61,6 +76,19 @@ def parser_hostmask(hostmask):
 		'host': host
 	}
 
+class SmartRedirectHandler(urllib2.HTTPRedirectHandler):
+	def http_error_301(self, req, fp, code, msg, headers):
+		result = urllib2.HTTPRedirectHandler.http_error_301(
+				self, req, fp, code, msg, headers)
+		result.status = code
+		return result
+
+	def http_error_302(self, req, fp, code, msg, headers):
+		result = urllib2.HTTPRedirectHandler.http_error_302(
+				self, req, fp, code, msg, headers)
+		result.status = code
+		return result
+
 @lib.hooknum("PRIVMSG")
 def privmsg_hook(bot, textline):
 	user = parser_hostmask(textline[1:textline.find(' ')])
@@ -71,29 +99,15 @@ def privmsg_hook(bot, textline):
 	except IndexError:
 		line = ''
 
+	responses = []
 	for match in url_regex.findall(line):
 		if match:
-			print match
-			if 'open.spotify.com' in match or 'spotify:' in match:
-				for r in spotify_regex:
-					for sptype, track in r.findall(match):
-						bot.msg(chan, unescape(gotspotify(sptype, track)))
-
-			elif 'youtube.com' in match or 'youtu.be' in match:
-				for r in youtube_regex:
-					for url in r.findall(match):
-						bot.msg(chan, unescape(gotyoutube(url)))
-
-			elif 'twitch.tv' in match:
-				for r in twitch_regex:
-					for uri in r.findall(match):
-						bot.msg(chan, unescape(gottwitch(uri)))
-
-			else:
-				bot.msg(chan, unescape(goturl(match)))
+			responses.append(goturl(match))
+	if len(responses) > 0:
+		bot.msg(chan, ' | '.join(responses), True)
 
 def unescape(line):
-	return html_parser.unescape(line)
+	return re.sub('\s+', ' ', html_parser.unescape(line))
 
 def gotspotify(type, track):
 	url = 'http://ws.spotify.com/lookup/1/?uri=spotify:%s:%s' % (type, track)
@@ -112,13 +126,13 @@ def gotspotify(type, track):
 		minutes = int(length)/60
 		seconds =  int(length)%60
 
-		return 'Track: %s - %s / %s %s:%.2d %2d%%' % (artist_name, name, album_name, minutes, seconds, popularity)
+		return unescape('Track: %s - %s / %s %s:%.2d %2d%%' % (artist_name, name, album_name, minutes, seconds, popularity))
 
 	elif lookup_type == 'album':
 		album_name = soup.find('album').find('name').string
 		artist_name = soup.find('artist').find('name').string
 		released = soup.find('released').string
-		return 'Album: %s - %s - %s' % (artist_name, album_name, released)
+		return unescape('Album: %s - %s - %s' % (artist_name, album_name, released))
 
 	else:
 		return 'Unsupported type.'
@@ -135,7 +149,7 @@ def gotyoutube(url):
 		title = video_info['entry']['title']["$t"]
 		author = video_info['entry']['author'][0]['name']['$t']
 
-		return "Youtube: %s (%s)" % (title, author)
+		return unescape("Youtube: %s (%s)" % (title, author))
 	except:
 		pass
 
@@ -144,10 +158,17 @@ def gottwitch(uri):
 		respdata = urllib2.urlopen(url).read()
 		twitch = json.loads(respdata)
 		try:
-			return 'Twitch: %s (%s playing %s)' % (twitch[0]['channel']['status'], twitch[0]['channel']['login'], twitch[0]['channel']['meta_game'])
+			return unescape('Twitch: %s (%s playing %s)' % (twitch[0]['channel']['status'], twitch[0]['channel']['login'], twitch[0]['channel']['meta_game']))
 		except:
 			return 'Twitch: Channel offline.'
 
 def goturl(url):
-	soup = BeautifulSoup(urllib2.urlopen(url))
-	return soup.title.string
\ No newline at end of file
+	request = urllib2.Request(url)
+	opener = urllib2.build_opener(SmartRedirectHandler())
+	try:
+		soup = BeautifulSoup(opener.open(request, timeout=0.5))
+		return unescape('Title: %s' % (soup.title.string))
+	except urllib2.HTTPError as e:
+		return 'Error: %s %s' % (e.code, e.reason)
+	except Exception as e:
+		return 'Error: %r' % (e.message)