A much needed inital import.

1 files changed, 115 insertions, 0 deletions

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:]))