[erebus.git] / modules / urls.py

# Erebus IRC bot - Author: Erebus Team
# URL Checker
# This file is released into the public domain; see http://unlicense.org/

# module info
modinfo = {
	'author': 'Erebus Team',
	'license': 'public domain',
	'compatible': [1], # compatible module API versions
	'depends': [], # other modules required to work properly?
}

# preamble
import modlib
lib = modlib.modlib(__name__)
modstart = lib.modstart
modstop = lib.modstop

# module code
import re, json, urllib2, urlparse, HTMLParser
from BeautifulSoup import BeautifulSoup

hostmask_regex = re.compile(r'^(.*)!(.*)@(.*)$')

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})')
)
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
)

def parser_hostmask(hostmask):
	if isinstance(hostmask, dict):
		return hostmask

	nick = None
	user = None
	host = None

	if hostmask is not None:
		match = hostmask_regex.match(hostmask)

		if not match:
			nick = hostmask
		else:
			nick = match.group(1)
			user = match.group(2)
			host = match.group(3)

	return {
		'nick': nick,
		'user': user,
		'host': host
	}

@lib.hooknum("PRIVMSG")
def privmsg_hook(bot, line):
	sender = parser_hostmask(line[1:line.find(' ')])

	try:
		linetx = line.split(None, 3)[3][1:]
	except IndexError:
		linetx = ''

	chan = line.split()[2]

	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 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 line: pass #TODO fix twitch

	else: pass #TODO generic <title> checker


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)
	lookup_type = soup.contents[2].name
		
	if lookup_type == 'track':
		name = soup.find('name').string
		album_name = soup.find('album').find('name').string
		artist_name = soup.find('artist').find('name').string
		popularity = soup.find('popularity')
		if popularity:
			popularity = float(popularity.string)*100
		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.'

def gotyoutube(url):
	url_data = urlparse.urlparse(url)
	query = urlparse.parse_qs(url_data.query)
	video = query["v"][0]
	api_url = 'http://gdata.youtube.com/feeds/api/videos/%s?alt=json&v=2' % video
	try:
		respdata = urllib2.urlopen(api_url).read()
		video_info = json.loads(respdata)

		title = video_info['entry']['title']["$t"]
		author = video_info['entry']['author'][0]['name']['$t']

		return "Youtube: %s (%s)" % (title, author)
	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.')
Commit	Line	Data
a83e1f9c	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	# preamble
	14	import modlib
	15	lib = modlib.modlib(__name__)
	16	modstart = lib.modstart
	17	modstop = lib.modstop
	18
	19	# module code
	20	import re, json, urllib2, urlparse, HTMLParser
	21	from BeautifulSoup import BeautifulSoup
	22
	23	hostmask_regex = re.compile(r'^(.)!(.)@(.*)$')
	24
	25	spotify_regex = (
	26	re.compile(r'spotify:(?P<type>\w+):(?P<track_id>\w{22})'),
	27	re.compile(r'http://open.spotify.com/(?P<type>\w+)/(?P<track_id>\w{22})')
	28	)
	29	youtube_regex = (
	30	re.compile(r'https?://(?:www\.)?youtube\.com/watch\?[a-zA-Z0-9=&_\-]+'),
	31	)
	32	twitch_regex = (
	33	re.compile('(http\|ftp\|https):\/\/([\w\-_]+(?:(?:\.[\w\-_]+)+))([\w\-\.,@?^=%&:/~\+#]*[\w\-\@?^=%&/~\+#])?'), #TODO
	34	)
	35
	36	def parser_hostmask(hostmask):
	37	if isinstance(hostmask, dict):
	38	return hostmask
	39
	40	nick = None
	41	user = None
	42	host = None
	43
	44	if hostmask is not None:
	45	match = hostmask_regex.match(hostmask)
	46
	47	if not match:
	48	nick = hostmask
	49	else:
	50	nick = match.group(1)
	51	user = match.group(2)
	52	host = match.group(3)
	53
	54	return {
	55	'nick': nick,
	56	'user': user,
	57	'host': host
	58	}
	59
	60	@lib.hooknum("PRIVMSG")
	61	def privmsg_hook(bot, line):
	62	sender = parser_hostmask(line[1:line.find(' ')])
	63
	64	try:
65	linetx = line.split(None, 3)[3][1:]
66	except IndexError:
67	linetx = ''
68
69	chan = line.split()[2]
70
71	if 'open.spotify.com' in line or 'spotify:' in line:
72	for r in spotify_regex:
73	for sptype, track in r.findall(linetx):
74	bot.msg(chan, gotspotify(sptype, track))
75
76	elif 'youtube.com' in line or 'youtu.be' in line:
77	print "got youtube!"
78	for r in youtube_regex:
79	for url in r.findall(linetx):
80	bot.msg(chan, gotyoutube(url))
81
82	elif 'twitch.tv' in line: pass #TODO fix twitch
83
84	else: pass #TODO generic <title> checker
85
86
87	def gotspotify(type, track):
88	url = 'http://ws.spotify.com/lookup/1/?uri=spotify:%s:%s' % (type, track)
89	xml = urllib2.urlopen(url).read()
90	soup = BeautifulSoup(xml)
91	lookup_type = soup.contents[2].name
92
93	if lookup_type == 'track':
94	name = soup.find('name').string
95	album_name = soup.find('album').find('name').string
96	artist_name = soup.find('artist').find('name').string
97	popularity = soup.find('popularity')
98	if popularity:
99	popularity = float(popularity.string)*100
100	length = float(soup.find('length').string)
101	minutes = int(length)/60
102	seconds = int(length)%60
103
104	return 'Track: %s - %s / %s %s:%.2d %2d%%' % (artist_name, name, album_name, minutes, seconds, popularity)
105
106	elif lookup_type == 'album':
107	album_name = soup.find('album').find('name').string
108	artist_name = soup.find('artist').find('name').string
109	released = soup.find('released').string
110	return 'Album: %s - %s - %s' % (artist_name, album_name, released)
111
112	else:
113	return 'Unsupported type.'
114
115	def gotyoutube(url):
116	url_data = urlparse.urlparse(url)
117	query = urlparse.parse_qs(url_data.query)
118	video = query["v"][0]
119	api_url = 'http://gdata.youtube.com/feeds/api/videos/%s?alt=json&v=2' % video
120	try:
121	respdata = urllib2.urlopen(api_url).read()
122	video_info = json.loads(respdata)
123
124	title = video_info['entry']['title']["$t"]
125	author = video_info['entry']['author'][0]['name']['$t']
126
127	return "Youtube: %s (%s)" % (title, author)
128	except:
129	pass
130
131
132	def gottwitch(url):
133	return ""
134	#FIXME:
135	try:
136	linetx = line.split(None, 3)[3][1:]
137	except IndexError:
138	linetx = ''
139
140	if checkfor not in line:
141	return # doesn't concern us
142
143	for p, h, c in url_regex.findall(linetx):
144	if checkfor in h:
145	url = 'http://api.justin.tv/api/stream/list.json?channel=%s' % c[1:]
146	respdata = urllib2.urlopen(url).read()
147	twitch = json.loads(respdata)
148	try:
149	bot.msg(line.split()[2], 'Twitch: %s (%s playing %s)' % (twitch[0]['channel']['status'], twitch[0]['channel']['login'], twitch[0]['channel']['meta_game']))
150	except:
151	bot.msg(line.split()[2], 'Twitch: Channel offline.')