]>
Commit | Line | Data |
---|---|---|
1 | # Erebus IRC bot - Author: Erebus Team | |
2 | # URL Checker | |
3 | # This file is released into the public domain; see http://unlicense.org/ | |
4 | ||
5 | # module info | |
6 | modinfo = { | |
7 | 'author': 'Erebus Team', | |
8 | 'license': 'public domain', | |
9 | 'compatible': [1], # compatible module API versions | |
10 | 'depends': [], # other modules required to work properly? | |
11 | } | |
12 | ||
13 | # http://embed.ly/tools/generator | |
14 | ||
15 | # preamble | |
16 | import modlib | |
17 | lib = modlib.modlib(__name__) | |
18 | modstart = lib.modstart | |
19 | modstop = lib.modstop | |
20 | ||
21 | # module code | |
22 | import re, urllib2, urlparse, json, HTMLParser | |
23 | from BeautifulSoup import BeautifulSoup | |
24 | ||
25 | html_parser = HTMLParser.HTMLParser() | |
26 | ||
27 | hostmask_regex = re.compile(r'^(.*)!(.*)@(.*)$') | |
28 | url_regex = re.compile(r'((?:https?://|spotify:)[^\s]+)') | |
29 | spotify_regex = ( | |
30 | re.compile(r'spotify:(?P<type>\w+):(?P<track_id>\w{22})'), | |
31 | re.compile(r'https?://open.spotify.com/(?P<type>\w+)/(?P<track_id>\w{22})') | |
32 | ) | |
33 | youtube_regex = ( | |
34 | re.compile(r'https?://(?:www\.)?youtube\.com/watch\?[a-zA-Z0-9=&_\-]+'), | |
35 | ) | |
36 | twitch_regex = ( | |
37 | re.compile(r'https?:\/\/(?:www\.)?twitch.tv\/([A-Za-z0-9]*)'), | |
38 | ) | |
39 | ||
40 | def parser_hostmask(hostmask): | |
41 | if isinstance(hostmask, dict): | |
42 | return hostmask | |
43 | ||
44 | nick = None | |
45 | user = None | |
46 | host = None | |
47 | ||
48 | if hostmask is not None: | |
49 | match = hostmask_regex.match(hostmask) | |
50 | ||
51 | if not match: | |
52 | nick = hostmask | |
53 | else: | |
54 | nick = match.group(1) | |
55 | user = match.group(2) | |
56 | host = match.group(3) | |
57 | ||
58 | return { | |
59 | 'nick': nick, | |
60 | 'user': user, | |
61 | 'host': host | |
62 | } | |
63 | ||
64 | class SmartRedirectHandler(urllib2.HTTPRedirectHandler): | |
65 | def http_error_301(self, req, fp, code, msg, headers): | |
66 | result = urllib2.HTTPRedirectHandler.http_error_301( | |
67 | self, req, fp, code, msg, headers) | |
68 | result.status = code | |
69 | return result | |
70 | ||
71 | def http_error_302(self, req, fp, code, msg, headers): | |
72 | result = urllib2.HTTPRedirectHandler.http_error_302( | |
73 | self, req, fp, code, msg, headers) | |
74 | result.status = code | |
75 | return result | |
76 | ||
77 | @lib.hooknum("PRIVMSG") | |
78 | def privmsg_hook(bot, textline): | |
79 | user = parser_hostmask(textline[1:textline.find(' ')]) | |
80 | chan = textline.split()[2] | |
81 | ||
82 | try: | |
83 | line = textline.split(None, 3)[3][1:] | |
84 | except IndexError: | |
85 | line = '' | |
86 | ||
87 | for match in url_regex.findall(line): | |
88 | if match: | |
89 | if 'open.spotify.com' in match or 'spotify:' in match: | |
90 | for r in spotify_regex: | |
91 | for sptype, track in r.findall(match): | |
92 | bot.msg(chan, gotspotify(sptype, track)) | |
93 | ||
94 | elif 'youtube.com' in match or 'youtu.be' in match: | |
95 | for r in youtube_regex: | |
96 | for url in r.findall(match): | |
97 | bot.msg(chan, gotyoutube(url)) | |
98 | ||
99 | elif 'twitch.tv' in match: | |
100 | for r in twitch_regex: | |
101 | for uri in r.findall(match): | |
102 | bot.msg(chan, gottwitch(uri)) | |
103 | ||
104 | else: | |
105 | bot.msg(chan, goturl(match)) | |
106 | ||
107 | def unescape(line): | |
108 | return html_parser.unescape(line) | |
109 | ||
110 | def gotspotify(type, track): | |
111 | url = 'http://ws.spotify.com/lookup/1/?uri=spotify:%s:%s' % (type, track) | |
112 | xml = urllib2.urlopen(url).read() | |
113 | soup = BeautifulSoup(xml, convertEntities=BeautifulSoup.HTML_ENTITIES) | |
114 | lookup_type = soup.contents[2].name | |
115 | ||
116 | if lookup_type == 'track': | |
117 | name = soup.find('name').string | |
118 | album_name = soup.find('album').find('name').string | |
119 | artist_name = soup.find('artist').find('name').string | |
120 | popularity = soup.find('popularity') | |
121 | if popularity: | |
122 | popularity = float(popularity.string)*100 | |
123 | length = float(soup.find('length').string) | |
124 | minutes = int(length)/60 | |
125 | seconds = int(length)%60 | |
126 | ||
127 | return unescape('Track: %s - %s / %s %s:%.2d %2d%%' % (artist_name, name, album_name, minutes, seconds, popularity)) | |
128 | ||
129 | elif lookup_type == 'album': | |
130 | album_name = soup.find('album').find('name').string | |
131 | artist_name = soup.find('artist').find('name').string | |
132 | released = soup.find('released').string | |
133 | return unescape('Album: %s - %s - %s' % (artist_name, album_name, released)) | |
134 | ||
135 | else: | |
136 | return 'Unsupported type.' | |
137 | ||
138 | def gotyoutube(url): | |
139 | url_data = urlparse.urlparse(url) | |
140 | query = urlparse.parse_qs(url_data.query) | |
141 | video = query["v"][0] | |
142 | api_url = 'http://gdata.youtube.com/feeds/api/videos/%s?alt=json&v=2' % video | |
143 | try: | |
144 | respdata = urllib2.urlopen(api_url).read() | |
145 | video_info = json.loads(respdata) | |
146 | ||
147 | title = video_info['entry']['title']["$t"] | |
148 | author = video_info['entry']['author'][0]['name']['$t'] | |
149 | ||
150 | return unescape("Youtube: %s (%s)" % (title, author)) | |
151 | except: | |
152 | pass | |
153 | ||
154 | def gottwitch(uri): | |
155 | url = 'http://api.justin.tv/api/stream/list.json?channel=%s' % uri.split('/')[0] | |
156 | respdata = urllib2.urlopen(url).read() | |
157 | twitch = json.loads(respdata) | |
158 | try: | |
159 | return unescape('Twitch: %s (%s playing %s)' % (twitch[0]['channel']['status'], twitch[0]['channel']['login'], twitch[0]['channel']['meta_game'])) | |
160 | except: | |
161 | return 'Twitch: Channel offline.' | |
162 | ||
163 | def goturl(url): | |
164 | request = urllib2.Request(url) | |
165 | opener = urllib2.build_opener(SmartRedirectHandler()) | |
166 | try: | |
167 | soup = BeautifulSoup(opener.open(request, timeout=2)) | |
168 | return unescape('Title: %s' % (soup.title.string)) | |
169 | except: | |
170 | return 'Invalid URL/Timeout' |