urls.py module redone

diff --git a/modules/urls.py b/modules/urls.py
index 2908dc0af1e20d29830d3377db8c1a7539d85557..4a1f5f31dbecf98ed82eb230226719591d07f3ba 100644 (file)
--- a/modules/urls.py
+++ b/modules/urls.py
@@ -19,20 +19,22 @@ modstart = lib.modstart
 modstop = lib.modstop
 
 # module code
-import re, json, urllib2, urlparse, HTMLParser
+import re, urllib2, urlparse, json, HTMLParser
 from BeautifulSoup import BeautifulSoup
 
-hostmask_regex = re.compile(r'^(.*)!(.*)@(.*)$')
+html_parser = HTMLParser.HTMLParser()
 
+hostmask_regex = re.compile(r'^(.*)!(.*)@(.*)$')
+url_regex = re.compile(r'((?:https?://|spotify:)[^\s]+)')
 spotify_regex = (
        re.compile(r'spotify:(?P<type>\w+):(?P<track_id>\w{22})'),
-       re.compile(r'http://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{22})')
 )
 youtube_regex = (
        re.compile(r'https?://(?:www\.)?youtube\.com/watch\?[a-zA-Z0-9=&_\-]+'),
 )
 twitch_regex = (
-       re.compile('(http|ftp|https):\/\/([\w\-_]+(?:(?:\.[\w\-_]+)+))([\w\-\.,@?^=%&amp;:/~\+#]*[\w\-\@?^=%&amp;/~\+#])?'), #TODO
+       re.compile(r'https?://(?:www\.)?twitch.tv/(.*)\w{1,}'),
 )
 
 def parser_hostmask(hostmask):
@@ -60,38 +62,45 @@ def parser_hostmask(hostmask):
        }
 
 @lib.hooknum("PRIVMSG")
-def privmsg_hook(bot, line):
-       sender = parser_hostmask(line[1:line.find(' ')])
+def privmsg_hook(bot, textline):
+       user = parser_hostmask(textline[1:textline.find(' ')])
+       chan = textline.split()[2]
 
        try:
-               linetx = line.split(None, 3)[3][1:]
+               line = textline.split(None, 3)[3][1:]
        except IndexError:
-               linetx = ''
+               line = ''
 
-       chan = line.split()[2]
+       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)))
 
-       if 'open.spotify.com' in line or 'spotify:' in line:
-               for r in spotify_regex:
-                       for sptype, track in r.findall(linetx):
-                               bot.msg(chan, 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 'youtube.com' in line or 'youtu.be' in line:
-               print "got youtube!"
-               for r in youtube_regex:
-                       for url in r.findall(linetx):
-                               bot.msg(chan, gotyoutube(url))
+                       elif 'twitch.tv' in match:
+                               for r in twitch_regex:
+                                       for uri in r.findall(match):
+                                               bot.msg(chan, unescape(gottwitch(uri)))
 
-       elif 'twitch.tv' in line: pass #TODO fix twitch
-
-       else: pass #TODO generic <title> checker
+                       else:
+                               bot.msg(chan, unescape(goturl(match)))
 
+def unescape(line):
+       return html_parser.unescape(line)
 
 def gotspotify(type, track):
        url = 'http://ws.spotify.com/lookup/1/?uri=spotify:%s:%s' % (type, track)
        xml = urllib2.urlopen(url).read()
-       soup = BeautifulSoup(xml)
+       soup = BeautifulSoup(xml, convertEntities=BeautifulSoup.HTML_ENTITIES)
        lookup_type = soup.contents[2].name
-               
+
        if lookup_type == 'track':
                name = soup.find('name').string
                album_name = soup.find('album').find('name').string
@@ -102,15 +111,15 @@ def gotspotify(type, track):
                length = float(soup.find('length').string)
                minutes = int(length)/60
                seconds =  int(length)%60
-       
+
                return '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)
-       
+
        else:
                return 'Unsupported type.'
 
@@ -130,25 +139,15 @@ def gotyoutube(url):
        except:
                pass
 
-
-def gottwitch(url):
-       return ""
-       #FIXME:
-       try:
-               linetx = line.split(None, 3)[3][1:]
-       except IndexError:
-               linetx = ''
-
-       if checkfor not in line:
-               return # doesn't concern us
-
-       for p, h, c in url_regex.findall(linetx):
-               if checkfor in h:
-                       url = 'http://api.justin.tv/api/stream/list.json?channel=%s' % c[1:]
-                       respdata = urllib2.urlopen(url).read()
-                       twitch = json.loads(respdata)
-                       try:
-                               bot.msg(line.split()[2], 'Twitch: %s (%s playing %s)' % (twitch[0]['channel']['status'], twitch[0]['channel']['login'], twitch[0]['channel']['meta_game']))
-                       except:
-                               bot.msg(line.split()[2], 'Twitch: Channel offline.')
-
+def gottwitch(uri):
+               url = 'http://api.justin.tv/api/stream/list.json?channel=%s' % uri.split('/')[0]
+               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'])
+               except:
+                       return 'Twitch: Channel offline.'
+
+def goturl(url):
+       soup = BeautifulSoup(urllib2.urlopen(url))
+       return soup.title.string
\ No newline at end of file