[erebus.git] / modules / youtube.py

# Erebus IRC bot - Author: Erebus Team
# Youtube 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
import urllib2
import HTMLParser
from BeautifulSoup import BeautifulSoup

checkfor = "youtube"
url_regex = re.compile('http[s]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\(\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+')

@lib.hooknum("PRIVMSG")
def privmsg_hook(bot, line):
	try:
		linetx = line.split(None, 3)[3][1:]
	except IndexError:
		linetx = ''

	if checkfor not in line:
		return # doesn't concern us

	for url in url_regex.findall(linetx):
		if checkfor in url:
			html_parser = HTMLParser.HTMLParser()
			respdata = urllib2.urlopen(url).read()
			soup = BeautifulSoup(respdata)
			bot.msg(line.split()[2], BeautifulSoup(soup.title.string, convertEntities=BeautifulSoup.HTML_ENTITIES))
Commit	Line	Data
9bd05cf6	1	# Erebus IRC bot - Author: Erebus Team
c6b4a177	2	# Youtube URL Checker
c3502e73 CS	3	# This file is released into the public domain; see http://unlicense.org/
	4
	5	# module info
	6	modinfo = {
9bd05cf6	7	'author': 'Erebus Team',
c3502e73 CS	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
	21	import urllib2
	22	import HTMLParser
	23	from BeautifulSoup import BeautifulSoup
	24
	25	checkfor = "youtube"
c3502e73	26	url_regex = re.compile('http[s]?://(?:[a-zA-Z]\|[0-9]\|[$-_@.&+]\|[!*\(\),]\|(?:%[0-9a-fA-F][0-9a-fA-F]))+')
c3502e73 CS	27
	28	@lib.hooknum("PRIVMSG")
	29	def privmsg_hook(bot, line):
c3502e73 CS	30	try:
	31	linetx = line.split(None, 3)[3][1:]
	32	except IndexError:
	33	linetx = ''
	34
	35	if checkfor not in line:
	36	return # doesn't concern us
	37
	38	for url in url_regex.findall(linetx):
	39	if checkfor in url:
	40	html_parser = HTMLParser.HTMLParser()
	41	respdata = urllib2.urlopen(url).read()
	42	soup = BeautifulSoup(respdata)
c6b4a177	43	bot.msg(line.split()[2], BeautifulSoup(soup.title.string, convertEntities=BeautifulSoup.HTML_ENTITIES))