]> jfr.im git - erebus.git/blobdiff - modules/urls.py
trivia - add last win to topic
[erebus.git] / modules / urls.py
index c6d939f2a712bd61abe5c962bbd55aaf1e657078..3b418707dcd8d297e79284342a6f806cba9dec03 100644 (file)
@@ -34,7 +34,7 @@ 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 +61,19 @@ 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(' ')])
@@ -73,24 +86,23 @@ def privmsg_hook(bot, textline):
 
        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)))
+                                               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)))
+                                               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)))
+                                               bot.msg(chan, gottwitch(uri))
 
                        else:
-                               bot.msg(chan, unescape(goturl(match)))
+                               bot.msg(chan, goturl(match))
 
 def unescape(line):
        return html_parser.unescape(line)
@@ -112,13 +124,13 @@ 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 +147,7 @@ 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
 
@@ -144,13 +156,15 @@ 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):
+       request = urllib2.Request(url)
+       opener = urllib2.build_opener(SmartRedirectHandler())
        try:
-               soup = BeautifulSoup(urllib2.urlopen(url))
-               return "Title: %s" % soup.title.string
+               soup = BeautifulSoup(opener.open(request, timeout=2))
+               return unescape('Title: %s' % (soup.title.string))
        except:
-               return "Bad URL"
+               return 'Invalid URL/Timeout'