/usr/share/weechat/python/pagetitle.py is in weechat-scripts 20120603-1.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 | # pagetitle plugin for weechat-0.3.0
#
# /pt http://tech.slashdot.org/tech/08/11/12/199215.shtml
# <user> http://tech.slashdot.org/tech/08/11/12/199215.shtml
# ('Slashdot | Microsoft's "Dead Cow" Patch Was 7 Years In the Making')
#
# xororand @ irc://irc.freenode.net/#weechat
#
# 2009-05-02, FlashCode <flashcode@flashtux.org>:
# version 0.5: sync with last API changes
import htmllib
import re
import socket
import sys
import urllib2
limit_title_length = 100
debug = True
# user agent
opener = urllib2.build_opener()
opener.addheaders = [('User-agent', 'Mozilla/5.0 (weechat/pagetitle)')]
urllib2._urlopener = opener
# set a short timeout to avoid freezing weechat [seconds]
socket.setdefaulttimeout(5)
regex_url = re.compile("""https?://[^ ]+""")
def unescape(s): #{{{
"""Unescape HTML entities"""
p = htmllib.HTMLParser(None)
p.save_bgn()
p.feed(s)
return p.save_end() #}}}
def getPageTitle(url):
"""Retrieve the HTML <title> from a webpage"""
try:
u = urllib2.urlopen(url)
except urllib2.HTTPError, e:
raise NameError(str(e))
except urllib2.URLError, e:
raise NameError(str(e))
info = u.info()
try:
content_type = info['Content-Type']
if not re.match(".*/html.*",content_type):
return ""
except:
return ""
head = u.read(8192)
head = re.sub("[\r\n\t ]"," ",head)
title = re.search('(?i)\<title\>(.*?)\</title\>', head)
if title:
title = title.group(1)
return unescape(title)
else:
return ""
# /pt http://foo
def on_pagetitle(data, buffer, args):
if len(args) == 0:
return weechat.WEECHAT_RC_ERROR
msg = args
def urlReplace(match):
url = match.group()
try:
if debug:
weechat.prnt(buffer, "pagetitle: retrieving '%s'" % url)
title = getPageTitle(url)
if len(title) > limit_title_length:
title = "%s [...]" % title[0:limit_title_length]
url = "%s ('%s')" % (url, title)
except NameError, e:
weechat.prnt(buffer, "pagetitle: URL: '%s', Error: '%s'" % (url, e))
return url
msg = regex_url.sub(urlReplace, msg)
weechat.command(buffer, "/say %s" % msg)
return weechat.WEECHAT_RC_OK
# Register plugin
import weechat
weechat.register ('pagetitle', 'xororand', '0.5', 'GPL3', """Adds HTML titles to http:// urls in your message.""", "", "")
desc = """Sends a message to the current buffer and adds HTML titles to http:// URLs.
Example: /pt check this out: http://xkcd.com/364/
<you> check this out: http://xkcd.com/364/ (xkcd - A webcomic of romance, sarcasm, math and language)"""
weechat.hook_command ('pt', desc, 'message', 'message containing an URL', '', 'on_pagetitle', '')
# vim:set ts=4 sw=4 noexpandtab nowrap foldmethod=marker:
|