def val(ircbot, input):
"""Check a webpage using the W3C Markup Validator."""
if not input.group(2):
return ircbot.reply("Nothing to validate.")
uri = input.group(2)
if not uri.startswith('http://'):
uri = 'http://' + uri
path = '/check?uri=%s;output=xml' % web.urllib.quote(uri)
info = web.head('http://validator.w3.org' + path)
result = uri + ' is '
if isinstance(info, list):
return ircbot.say('Got HTTP response %s' % info[1])
if info.has_key('X-W3C-Validator-Status'):
result += str(info['X-W3C-Validator-Status'])
if info['X-W3C-Validator-Status'] != 'Valid':
if info.has_key('X-W3C-Validator-Errors'):
n = int(info['X-W3C-Validator-Errors'].split(' ')[0])
if n != 1:
result += ' (%s errors)' % n
else:
result += ' (%s error)' % n
else:
result += 'Unvalidatable: no X-W3C-Validator-Status'
ircbot.reply(result)
def head(ircbot, input):
"""Provide HTTP HEAD information."""
uri = input.group(2)
uri = (uri or '').encode('utf-8')
if ' ' in uri:
uri, header = uri.rsplit(' ', 1)
else:
uri, header = uri, None
if not uri and hasattr(ircbot, 'last_seen_uri'):
try:
uri = ircbot.last_seen_uri[input.sender]
except KeyError:
return ircbot.say('?')
if not uri.startswith('htt'):
uri = 'http://' + uri
try:
info = web.head(uri)
except IOError:
return ircbot.say("Can't connect to %s" % uri)
except httplib.InvalidURL:
return ircbot.say("Not a valid URI, sorry.")
if not isinstance(info, list):
try:
info = dict(info)
except TypeError:
return ircbot.reply(
'Try .head http://example.org/ [optional header]')
info['Status'] = '200'
else:
newInfo = dict(info[0])
newInfo['Status'] = str(info[1])
info = newInfo
if header is None:
data = []
if info.has_key('Status'):
data.append(info['Status'])
if info.has_key('content-type'):
data.append(info['content-type'].replace('; charset=', ', '))
if info.has_key('last-modified'):
modified = info['last-modified']
modified = time.strptime(modified, '%a, %d %b %Y %H:%M:%S %Z')
data.append(time.strftime('%Y-%m-%d %H:%M:%S UTC', modified))
if info.has_key('content-length'):
data.append(info['content-length'] + ' bytes')
ircbot.reply(', '.join(data))
else:
headerlower = header.lower()
if info.has_key(headerlower):
ircbot.say(header + ': ' + info.get(headerlower))
else:
msg = 'There was no %s header in the response.' % header
ircbot.say(msg)
def head(ircbot, input):
"""Provide HTTP HEAD information."""
uri = input.group(2)
uri = (uri or '').encode('utf-8')
if ' ' in uri:
uri, header = uri.rsplit(' ', 1)
else:
uri, header = uri, None
if not uri and hasattr(ircbot, 'last_seen_uri'):
try:
uri = ircbot.last_seen_uri[input.sender]
except KeyError:
return ircbot.say('?')
if not uri.startswith('htt'):
uri = 'http://' + uri
try:
info = web.head(uri)
except IOError:
return ircbot.say("Can't connect to %s" % uri)
except httplib.InvalidURL:
return ircbot.say("Not a valid URI, sorry.")
if not isinstance(info, list):
try:
info = dict(info)
except TypeError:
return ircbot.reply('Try .head http://example.org/ [optional header]')
info['Status'] = '200'
else:
newInfo = dict(info[0])
newInfo['Status'] = str(info[1])
info = newInfo
if header is None:
data = []
if info.has_key('Status'):
data.append(info['Status'])
if info.has_key('content-type'):
data.append(info['content-type'].replace('; charset=', ', '))
if info.has_key('last-modified'):
modified = info['last-modified']
modified = time.strptime(modified, '%a, %d %b %Y %H:%M:%S %Z')
data.append(time.strftime('%Y-%m-%d %H:%M:%S UTC', modified))
if info.has_key('content-length'):
data.append(info['content-length'] + ' bytes')
ircbot.reply(', '.join(data))
else:
headerlower = header.lower()
if info.has_key(headerlower):
ircbot.say(header + ': ' + info.get(headerlower))
else:
msg = 'There was no %s header in the response.' % header
ircbot.say(msg)
def service(ircbot, input, command, args):
t = o.services[command]
template = t.replace('${args}', urllib.quote(args.encode('utf-8'), ''))
template = template.replace('${nick}', urllib.quote(input.nick, ''))
uri = template.replace('${sender}', urllib.quote(input.sender, ''))
info = web.head(uri)
if isinstance(info, list):
info = info[0]
if not 'text/plain' in info.get('content-type', '').lower():
return ircbot.reply("Sorry, the service didn't respond in plain text.")
bytes = web.get(uri)
lines = bytes.splitlines()
if not lines:
return ircbot.reply("Sorry, the service didn't respond any output.")
ircbot.say(lines[0][:350])
