From dcebcafcc52ae847077890b551b8319d80d36d91 Mon Sep 17 00:00:00 2001
From: Jon Bergli Heier <snakebite@jvnv.net>
Date: Sat, 14 Nov 2009 01:28:23 +0100
Subject: A much needed inital import.

---
 modules/__init__.py   |   0
 modules/anidb.py      | 100 +++++++++++++++++++++++++++++++++++++++++++
 modules/quotes.py     |  33 +++++++++++++++
 modules/url_titles.py | 115 ++++++++++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 248 insertions(+)
 create mode 100644 modules/__init__.py
 create mode 100644 modules/anidb.py
 create mode 100644 modules/quotes.py
 create mode 100644 modules/url_titles.py

(limited to 'modules')

diff --git a/modules/__init__.py b/modules/__init__.py
new file mode 100644
index 0000000..e69de29
diff --git a/modules/anidb.py b/modules/anidb.py
new file mode 100644
index 0000000..c5862e8
--- /dev/null
+++ b/modules/anidb.py
@@ -0,0 +1,100 @@
+info = {
+	'author': 'Jon Bergli Heier',
+	'title': 'anidb',
+	'description': 'Fetches anime info from anidb.net.',
+}
+
+import urllib2, gzip, os, time
+from pyPgSQL import PgSQL
+from lxml import etree
+import pyanidb
+import ConfigParser
+import marshal
+
+anidb_cfg = {}
+cp = ConfigParser.ConfigParser()
+cp.read(os.path.expanduser('~/.pyanidb.conf'))
+for option in ('username', 'password'):
+	anidb_cfg[option] = cp.get('pyanidb', option)
+
+class Module:
+	def __init__(self, bot):
+		self.irc = bot
+		self.db = PgSQL.connect()
+
+	def get_aid(self, msg, short = False):
+		if msg.isdigit():
+			return [(int(msg), 'N/A')]
+		search = '%'.join(msg.split())
+		if not search:
+			return
+		if not short:
+			search = '%%%s%%' % search
+		cur = self.db.cursor()
+		if short:
+			cur.execute('select * from anidb.anidb where aid in (select distinct aid from anidb.anidb where title ~~* %s and type in (2, 3)) and type = 1', (search,))
+		else:
+			cur.execute('select * from anidb.anidb where aid in (select distinct aid from anidb.anidb where title ~~* %s) and type = 1', (search,))
+		r = cur.fetchall()
+		cur.close()
+		return [(r[0][0], r[0][3])] if len(r) == 1 else [(x[0], x[3]) for x in r]
+
+	def get_info(self, aid):
+		cachepath = os.path.expanduser('~/.fotanidbcache/a%d.dat' % aid)
+		if os.access(cachepath, os.F_OK | os.R_OK) and time.time() - os.stat(cachepath).st_mtime < 60*60*24*7:
+			cache = open(cachepath, 'r').read()
+			data = marshal.loads(cache)
+		else:
+			amask = '33a0c0f0000080'
+			try:
+				anidb = pyanidb.AniDB(anidb_cfg['username'], anidb_cfg['password'])
+				anidb.auth()
+				data = anidb.get_anime(aid = aid, amask = amask)
+				anidb.logout()
+				open(cachepath, 'w').write(marshal.dumps(data))
+			except:
+				return 'Failed to get data from anidb'
+		year, type, catlist, catweight, romaji, english, epcount, normalep, rating, ratingcount, temprating, tempcount, specialep = data
+		if '-' in year:
+			syear, eyear = [int(x) for x in year.split('-')]
+			if syear == eyear:
+				year = syear
+		catlist = catlist.split(',')
+		catweight = catweight.split(',')
+		try:
+			catn = max(catweight.index(str(int(catweight[0]-1))), 10)
+		except:
+			catn = 10
+		rating = float(rating) / 100
+		temprating = float(temprating) / 100
+		catl = ', '.join(catlist[:catn] + (['+%d more' % (len(catlist)-catn)] if len(catlist) > catn else []))
+		return '%s%s is: %s, year %s, %s%s eps%s, cats: %s | rating: %.2f (%s), temp: %.2f (%s) | http://anidb.net/a%d' % (romaji, ' aka. %s' % english if english else '', type, year, normalep, '+%s' % specialep if int(specialep) > 0 else '', ' (ongoing)' if int(epcount) == 0 else '', catl or '(None)', rating, ratingcount, temprating, tempcount, aid)
+
+	def get_anime(self, msg):
+		short = msg.startswith('-s ')
+		if short:
+			msg = ' '.join(msg.split()[1:])
+		aid = self.get_aid(msg, short)
+		if len(aid) == 1:
+			return self.get_info(aid[0][0])
+		else:
+			if len(aid) == 0:
+				return 'anidb: No results'
+			else:
+				return 'anidb: %s%s' % ('%d/%d results: ' % (5, len(aid)) if len(aid) > 5 else '', ', '.join(['%s (%d)' % (x[1], x[0]) for x in aid[:5]]))
+
+	def __call__(self, nick, channel, msg):
+		if msg.startswith('!anidb'):
+			target = channel if not channel == self.irc.nickname else nick.split('!')[0]
+			args = msg.split()
+			if len(args) == 1:
+				self.irc.msg(target, 'Usage: !anidb [-s] search|aid')
+				return
+			info = self.get_anime(' '.join(args[1:]))
+			if info:
+				self.irc.msg(target, info)
+
+if __name__ == '__main__':
+	import sys
+	m = Module(None)
+	print m.get_anime(' '.join(sys.argv[1:]))
diff --git a/modules/quotes.py b/modules/quotes.py
new file mode 100644
index 0000000..b8eb988
--- /dev/null
+++ b/modules/quotes.py
@@ -0,0 +1,33 @@
+info = {
+	'author': 'Jon Bergli Heier',
+	'title': 'IRC Quotes',
+	'description': 'Allows users to access a quote database.',
+}
+
+import sys
+sys.path.insert(0, '/home/snakebite/py')
+from quotelib import IRCHandler as Quote_IRCHandler
+quote_handler = Quote_IRCHandler('/home/snakebite/quotes.db')
+
+class Module:
+	def __init__(self, bot):
+		self.irc = bot
+
+	def __call__(self, nick, channel, msg):
+		if not msg.startswith('!quote'):
+			return
+		args = msg.split(' ')
+		if msg.startswith('!quote'):
+			args = args[1:]
+		cmd = args[0] if len(args) and len(args[0].strip()) else 'random'
+		args = args[1:]
+	
+		if cmd.isdigit() or (cmd[0] == '#' and cmd[1:].isdigit()):
+			cmd, args = 'get', [cmd]
+	
+		quote_handler.nick = nick.split('!')[0]
+		if hasattr(quote_handler, cmd) and callable(getattr(quote_handler, cmd)):
+			for line in getattr(quote_handler, cmd)(*args):
+				self.irc.msg(channel if not channel == self.irc.nickname else nick.split('!')[0], line)
+		else:
+			self.irc.msg(channel if not channel == self.irc.nickname else nick.split('!')[0], '%s, invalid command "%s"' % (nick.split('!')[0], cmd))
diff --git a/modules/url_titles.py b/modules/url_titles.py
new file mode 100644
index 0000000..fe5181c
--- /dev/null
+++ b/modules/url_titles.py
@@ -0,0 +1,115 @@
+info = {
+	'author': 'Jon Bergli Heier',
+	'title': 'URL Titles',
+	'description': 'Fetches the title tags off of URLs.',
+}
+
+import re, urllib2, htmlentitydefs, gzip, cStringIO, spotimeta
+
+class Module:
+	re_http = re.compile(r'(http://[^\ ]+)')
+	re_title = re.compile(r'<title>(.*?)</title>', re.S | re.I)
+	metadata = spotimeta.Metadata(cache = {})
+
+	def __init__(self, bot):
+		self.irc = bot
+
+	def spotify(self, s):
+		try:
+			data = self.metadata.lookup(s)
+		except:
+			return 'Failed to fetch metadata from spotify.'
+		if data['type'] == 'artist':
+			return 'Spotify: %s' % data['result']['name']
+		else:
+			return 'Spotify: %s - %s' % (data['result']['artist']['name'], data['result']['name'])
+
+	def get_titles(self, s):
+		def parse_url(url):
+			s = url[7:].split('/', 1)[0:]
+			host = s[0]
+			path = '/' if len(s) == 1 else '/' + s[1]
+			return host, path
+
+		def unescape(text):
+			def fixup(m):
+				text = m.group(0)
+				if text[:2] == "&#":
+					# character reference
+					try:
+						if text[:3] == "&#x":
+							return unichr(int(text[3:-1], 16)).encode('utf-8')
+						else:
+							return unichr(int(text[2:-1])).encode('utf-8')
+					except ValueError:
+						pass
+				else:
+					# named entity
+					try:
+						text = unichr(htmlentitydefs.name2codepoint[text[1:-1]]).encode('utf-8')
+					except KeyError:
+						pass
+				return text # leave as is
+			return re.sub("&#?\w+;", fixup, text)
+
+		def format_text(s):
+			s = s.replace('\n', ' ').replace('\r', ' ').replace('\t', ' ')
+			while '  ' in s:
+				s = s.replace('  ', ' ')
+			s = unescape(s)
+			return s
+
+		m = self.re_http.findall(s)
+		if not m:
+			return
+		titles = []
+		for url in m:
+			if any([x in url for x in ('open.spotify.com', 'spotify:track:', 'spotify:artist:', 'spotify:album:')]):
+				titles.append(self.spotify(url).encode('utf8'))
+				continue
+			try:
+				u = urllib2.urlopen(url)
+			except:
+				return
+			#enc = ct.split('encoding=')
+			#if len(enc) == 2:
+				#enc = enc[1]
+			#else:
+				#enc = None
+			if u.headers['content-type'].startswith('text/html'):
+				#s = u.read()
+				if 'content-encoding' in u.headers and u.headers['content-encoding'] == 'gzip':
+					s = cStringIO.StringIO(u.read())
+					s.seek(0)
+					s = gzip.GzipFile(fileobj = s).read()
+					m = self.re_title.search(s)
+				else:
+					s = ''
+					m = None
+					buf = u.read(1024)
+					while buf:
+						s += buf
+						m = self.re_title.search(s)
+						if m:
+							break
+						buf = u.read(1024)
+				if m:
+					titles.append(m.groups()[0])
+			u.close()
+		if len(titles) == 1:
+			s = format_text(titles[0])
+		else:
+			s = ''
+			for i in range(len(titles)):
+				s += '\002[%d]\002 %s ' % (i+1, format_text(titles[i]))
+		return s.strip()
+
+	def __call__(self, nick, channel, msg):
+		titles = self.get_titles(msg)
+		if titles:
+			self.irc.msg(channel if not channel == self.irc.nickname else nick.split('!')[0], titles)
+
+if __name__ == '__main__':
+	import sys
+	m = Module(None)
+	print m.get_titles(' '.join(sys.argv[1:]))
-- 
cgit v1.2.3