This repository has been archived on 2023-04-13. You can view files and clone it, but cannot push or open issues or pull requests.
CloudBot/plugins/urlparse.py

50 lines
1.6 KiB
Python
Raw Normal View History

2011-11-20 10:23:31 +01:00
from util import hook, http, urlnorm
import urllib
from urllib2 import urlopen, Request, HTTPError
2011-11-20 10:23:31 +01:00
import re
import BeautifulSoup
2012-02-29 07:58:10 +01:00
ignored_urls = ["http://google.com", "http://youtube.com",
"http://pastebin.com", "http://mibpaste.com",
2012-02-29 08:32:42 +01:00
"http://fpaste.com", "http://git.io"]
2011-11-20 10:23:31 +01:00
def parse(match):
url = urlnorm.normalize(match.encode('utf-8'))
if url not in ignored_urls:
url = url.decode('utf-8')
try:
soup = BeautifulSoup.BeautifulSoup(http.get(url))
2011-11-20 10:23:31 +01:00
return soup.title.string
except:
return "fail"
2011-11-20 10:23:31 +01:00
# there should be " after the ' in the regex string but I was unable to escape it properly
@hook.regex(r"(?i)\b((?:https?://|www\d{0,3}[.]|[a-z0-9.\-]+[.][a-z]{2,4}/)(?:[^\s()<>]+|\(([^\s()<>]+|(\([^\s()<>]+\)))*\))+(?:\(([^\s()<>]+|(\([^\s()<>]+\)))*\)|[^\s`!()\[\]{};:'.,<>?«»“”‘’]))")
def urlparser(match, say=None, bot=None):
try:
enabled = bot.config["plugins"]["urlparse"]["enabled"]
except KeyError:
enabled = False
if not enabled:
return
url = urlnorm.normalize(match.group().encode('utf-8'))
2012-02-29 07:58:10 +01:00
if url[:7] != "http://":
if url[:8] != "https://":
url = "http://" + url
for x in ignored_urls:
if x in url:
return
title = parse(url)
if title == "fail":
return
title = http.unescape(title)
2011-11-30 13:51:43 +01:00
realurl = http.get_url(url)
if realurl == url:
say(u"(Link) %s" % title)
2011-11-30 13:51:43 +01:00
return
else:
say(u"(Link) %s [%s]" % (title, realurl))
2011-11-30 13:51:43 +01:00
return