/usr/share/pyshared/gplugs/snarf.py is in gozerbot 0.99.1-2.
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 | # gozerplugs/plugs/snarf.py
#
#
__author__ = "Wijnand 'tehmaze' Modderman - http://tehmaze.com"
__license__ = 'BSD'
__gendoclast__ = ['snarf-disable', ]
__depend__ = ['url', ]
from gozerbot.callbacks import callbacks, jcallbacks
from gozerbot.plughelp import plughelp
from gozerbot.aliases import aliases
from gozerbot.commands import cmnds
from gozerbot.examples import examples
from gozerbot.generic import decode_html_entities, get_encoding, geturl, \
geturl2, rlog, handle_exception
from gozerbot.persist.persist import Persist
from gozerbot.persist.persistconfig import PersistConfig
from gozerbot.plugins import plugins
import urllib
import urllib2
import urlparse
import copy
import re
import socket
plughelp.add('snarf', 'the snarf plugin gets the title of the web page of \
the provided url or the last url in the log')
cfg = Persist('snarf', {})
pcfg = PersistConfig()
pcfg.define('allow', ['text/plain', 'text/html', 'application/xml'])
re_html_title = re.compile(u'<title>(.*?)</title>', re.I | re.M | re.S)
re_url_match = re.compile(u'((?:http|https)://\S+)')
re_html_valid = {
'result': re.compile('(Failed validation, \
\d+ errors?|Passed validation)', re.I | re.M),
'modified': re.compile('<th>Modified:</th>\
<td colspan="2">([^<]+)</td>', re.I | re.M),
'server': re.compile('<th>Server:</th>\
<td colspan="2">([^<]+)</td>', re.I | re.M),
'size': re.compile('<th>Size:</th><td colspan="2">\
([^<]+)</td>', re.I | re.M),
'content': re.compile('<th>Content-Type:</th><td colspan="2">\
([^<]+)</td>', re.I | re.M),
'encoding': re.compile('<td>([^<]+)</td><td><select name="charset" \
id="charset">', re.I | re.M),
'doctype': re.compile('<td>([^<]+)</td><td><select id="doctype" \
name="doctype">', re.I | re.M)
}
urlvalidate = 'http://validator.w3.org/check?charset=%%28\
detect+automatically%%29&doctype=Inline&verbose=1&%s'
class SnarfException(Exception):
pass
def geturl_title(url):
""" fetch title of url """
try:
result = geturl2(url)
except urllib2.HTTPError, ex:
rlog(10, 'snarf', str(ex))
return False
except urllib2.URLError, ex:
rlog(10, 'snarf', str(ex))
return False
except IOError, ex:
try:
errno = ex[0]
except IndexError:
handle_exception()
return
return False
if not result:
return False
test_title = re_html_title.search(result)
if test_title:
# try to find an encoding and standardize it to utf-8
encoding = get_encoding(result)
title = test_title.group(1).decode(encoding, 'replace').replace('\n', ' ')
title = title.strip()
return decode_html_entities(title)
return False
def geturl_validate(url):
""" validate url """
url = urlvalidate % urllib.urlencode({'uri': url})
try:
result = geturl(url)
except IOError, ex:
try:
errno = ex[0]
except IndexError:
handle_exception()
return
return False
if not result:
return False
results = {}
for key in re_html_valid.keys():
results[key] = re_html_valid[key].search(result)
if results[key]:
results[key] = results[key].group(1)
else:
results[key] = '(unknown)'
return results
def valid_url(url):
""" check if url is valid """
if not re_url_match.match(url):
return False
parts = urlparse.urlparse(url)
# do a HEAD request to get the content-type
request = urllib2.Request(url)
request.get_method = lambda: "HEAD"
content = urllib2.urlopen(request)
if content.headers['content-type']:
type = content.headers['content-type'].split(';', 1)[0].strip()
if type not in pcfg.get('allow'):
raise SnarfException, "Content-Type %s is not allowed" % type
cleanurl = '%s://%s' % (parts[0], parts[1])
if parts[2]:
cleanurl = '%s%s' % (cleanurl, parts[2])
if parts[3]:
cleanurl = '%s;%s' % (cleanurl, parts[3])
if parts[4]:
cleanurl = '%s?%s' % (cleanurl, parts[4])
return cleanurl
def handle_snarf(bot, ievent, direct=True):
""" snarf provided url or last url in log """
url = None
if ievent.rest:
url = ievent.rest
else:
if plugins['url']:
url = plugins['url'].cache.fetch(bot, ievent)
if not url:
ievent.missing('<url>')
return
try:
url = valid_url(url)
except KeyError:
ievent.reply("can't detect content type")
return
except SnarfException, e:
if direct:
ievent.reply('unable to snarf: %s' % str(e))
return
except urllib2.HTTPError, e:
ievent.reply('unable to snarf: %s' % str(e))
return
except urllib2.URLError, ex:
ievent.reply('unable to snarf: %s' % str(ex))
return False
if not url:
ievent.reply('invalid url')
return
try:
title = geturl_title(url)
except socket.timeout:
ievent.reply('%s socket timeout' % url)
return
except urllib2.HTTPError, e:
ievent.reply('error: %s' % e)
return
if title:
host = urlparse.urlparse(url)[1]
if len(host) > 20:
host = host[0:20] + '...'
ievent.reply('%s: %s' % (host, title))
else:
ievent.reply('no title found at %s' % urlparse.urlparse(url)[1])
cmnds.add('snarf', handle_snarf, 'USER')
examples.add('snarf', 'fetch the title from an URL', \
'snarf http://gozerbot.org')
aliases.data['@'] = 'snarf'
aliases.data['title'] = 'snarf'
def handle_snarf_enable(bot, ievent):
""" enable snarfing in channel """
if not cfg.data.has_key(bot.name):
cfg.data[bot.name] = {}
cfg.data[bot.name][ievent.printto] = True
cfg.save()
ievent.reply('ok')
cmnds.add('snarf-enable', handle_snarf_enable, 'OPER')
examples.add('snarf-enable', 'enable snarfing in the channel', 'snarf-enable')
aliases.data['snarf-on'] = 'snarf-enable'
def handle_snarf_disable(bot, ievent):
""" disable snarfing in channel """
if not cfg.data.has_key(bot.name):
ievent.reply('ok')
return
cfg.data[bot.name][ievent.printto] = False
cfg.save()
ievent.reply('ok')
cmnds.add('snarf-disable', handle_snarf_disable, 'OPER')
examples.add('snarf-disable', 'disable snarfing in the channel', \
'snarf-disable')
aliases.data['snarf-off'] = 'snarf-disable'
def handle_snarf_list(bot, ievent):
""" show channels in which snarfing is enabled """
snarfs = []
names = cfg.data.keys()
names.sort()
for name in names:
targets = cfg.data[name].keys()
targets.sort()
snarfs.append('%s: %s' % (name, ' '.join(targets)))
if not snarfs:
ievent.reply('none')
else:
ievent.reply('snarfers enable on: %s' % ', '.join(snarfs))
cmnds.add('snarf-list', handle_snarf_list, 'OPER')
examples.add('snarf-list', 'show in which channels snarfing is enabled', \
'snarf-list')
def handle_validate(bot, ievent):
""" validate provided url or last url in log """
url = None
if ievent.rest:
url = ievent.rest
else:
if plugins['url']:
url = plugins['url'].cache.fetch(bot, ievent)
if not url:
ievent.missing('<url>')
return
try:
url = valid_url(url)
except urllib2.HTTPError, e:
ievent.reply('error: %s' % e)
return
if not url:
ievent.reply('invalid or bad URL')
return
result = geturl_validate(url)
if result:
host = urlparse.urlparse(url)[1]
if len(host) > 20:
host = host[0:20] + '...'
ievent.reply('%s: %s | modified: %s | server: %s | size: %s | \
content-type: %s | encoding: %s | doctype: %s' % \
tuple([host] + [result[x] for x in ['result', 'modified', \
'server', 'size', 'content', 'encoding', 'doctype']]))
cmnds.add('validate', handle_validate, 'USER')
examples.add('validate', 'validate an URL', 'validate http://gozerbot.org')
aliases.data['valid'] = 'validate'
|