Limnoria/plugins/Google/plugin.py

380 lines
15 KiB
Python
Raw Normal View History

2005-02-01 13:09:12 +01:00
###
# Copyright (c) 2002-2004, Jeremiah Fincher
# Copyright (c) 2008-2010, James McCoy
2005-02-01 13:09:12 +01:00
# All rights reserved.
#
# Redistribution and use in source and binary forms, with or without
# modification, are permitted provided that the following conditions are met:
#
# * Redistributions of source code must retain the above copyright notice,
# this list of conditions, and the following disclaimer.
# * Redistributions in binary form must reproduce the above copyright notice,
# this list of conditions, and the following disclaimer in the
# documentation and/or other materials provided with the distribution.
# * Neither the name of the author of this software nor the name of
# contributors to this software may be used to endorse or promote products
# derived from this software without specific prior written consent.
#
# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
# ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
# LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
# CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
# SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
# INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
# CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
# POSSIBILITY OF SUCH DAMAGE.
###
import re
2013-01-06 16:46:21 +01:00
import sys
2005-02-01 13:09:12 +01:00
import cgi
import json
2005-02-01 13:09:12 +01:00
import time
import socket
import supybot.conf as conf
import supybot.utils as utils
import supybot.world as world
from supybot.commands import *
2015-08-11 16:50:23 +02:00
import supybot.utils.minisix as minisix
2005-02-01 13:09:12 +01:00
import supybot.ircmsgs as ircmsgs
import supybot.ircutils as ircutils
import supybot.callbacks as callbacks
from supybot.i18n import PluginInternationalization, internationalizeDocstring
_ = PluginInternationalization('Google')
2005-02-01 13:09:12 +01:00
import json
class Google(callbacks.PluginRegexp):
"""This is a simple plugin to provide access to the Google services we
all know and love from our favorite IRC bot."""
2005-02-01 13:09:12 +01:00
threaded = True
callBefore = ['Web']
regexps = ['googleSnarfer']
2005-02-01 13:09:12 +01:00
_colorGoogles = {}
def _getColorGoogle(self, m):
s = m.group(1)
ret = self._colorGoogles.get(s)
if not ret:
L = list(s)
L[0] = ircutils.mircColor(L[0], 'blue')[:-1]
L[1] = ircutils.mircColor(L[1], 'red')[:-1]
L[2] = ircutils.mircColor(L[2], 'yellow')[:-1]
L[3] = ircutils.mircColor(L[3], 'blue')[:-1]
L[4] = ircutils.mircColor(L[4], 'green')[:-1]
L[5] = ircutils.mircColor(L[5], 'red')
ret = ''.join(L)
self._colorGoogles[s] = ret
return ircutils.bold(ret)
_googleRe = re.compile(r'\b(google)\b', re.I)
def outFilter(self, irc, msg):
if msg.command == 'PRIVMSG' and \
self.registryValue('colorfulFilter', msg.args[0]):
s = msg.args[1]
s = re.sub(self._googleRe, self._getColorGoogle, s)
msg = ircmsgs.privmsg(msg.args[0], s, msg=msg)
return msg
_decode_re = re.compile(r'<h3 class="r"><a href="/url\?q=(?P<url>[^"]+)&[^"]+">(?P<title>.*?)</a></h3>.*?<a class="[^"]+" href="/url\?q=(?P<cacheUrl>http://webcache[^"]+)">.*?<span class="st">(?P<content>.*?)</span>', re.DOTALL | re.MULTILINE)
@classmethod
def decode(cls, text):
matches = cls._decode_re.findall(text)
results = []
for match in matches:
r = dict(zip(('url', 'title', 'cacheUrl', 'content'), match))
r['url'] = utils.web.htmlToText(r['url'].split('&amp;')[0])
results.append(r)
return results
2016-05-05 08:03:10 +02:00
_gsearchUrl = 'https://www.google.com/search?gbv=2'
@internationalizeDocstring
def search(self, query, channel, options={}):
"""Perform a search using Google's AJAX API.
search("search phrase", options={})
Valid options are:
smallsearch - True/False (Default: False)
filter - {active,moderate,off} (Default: "moderate")
language - Restrict search to documents in the given language
(Default: "lang_en")
"""
ref = self.registryValue('referer')
if not ref:
ref = 'http://%s/%s' % (dynamic.irc.server,
dynamic.irc.nick)
headers = dict(utils.web.defaultHeaders)
headers['Referer'] = ref
2016-05-05 08:03:10 +02:00
opts = {'q': query}
2015-08-08 22:20:14 +02:00
for (k, v) in options.items():
if k == 'smallsearch':
if v:
opts['rsz'] = 'small'
else:
opts['rsz'] = 'large'
elif k == 'filter':
opts['safe'] = v
elif k == 'language':
2016-05-05 08:03:10 +02:00
opts['hl'] = v
defLang = self.registryValue('defaultLanguage', channel)
2016-05-05 08:03:10 +02:00
if 'hl' not in opts and defLang:
opts['hl'] = defLang.strip('lang_')
if 'safe' not in opts:
opts['safe'] = self.registryValue('searchFilter', dynamic.channel)
if 'rsz' not in opts:
opts['rsz'] = 'large'
text = utils.web.getUrl('%s?%s' % (self._gsearchUrl,
utils.web.urlencode(opts)),
headers=headers).decode('utf8')
return text
def formatData(self, data, bold=True, max=0, onetoone=False):
data = self.decode(data)
2005-02-01 13:09:12 +01:00
results = []
if max:
data = data[:max]
for result in data:
title = utils.web.htmlToText(result['title']\
.encode('utf-8'))
url = result['url']
if minisix.PY2:
2013-01-06 16:46:21 +01:00
url = url.encode('utf-8')
2005-02-01 13:09:12 +01:00
if title:
if bold:
title = ircutils.bold(title)
results.append(format('%s: %u', title, url))
else:
results.append(url)
if minisix.PY2:
2013-05-13 14:18:22 +02:00
repl = lambda x:x if isinstance(x, unicode) else unicode(x, 'utf8')
results = list(map(repl, results))
2005-02-01 13:09:12 +01:00
if not results:
2013-05-13 14:18:22 +02:00
return [_('No matches found.')]
elif onetoone:
return results
2005-02-01 13:09:12 +01:00
else:
return [minisix.u('; ').join(results)]
2005-02-01 13:09:12 +01:00
@internationalizeDocstring
def lucky(self, irc, msg, args, opts, text):
"""[--snippet] <search>
2005-02-01 13:09:12 +01:00
Does a google search, but only returns the first result.
If option --snippet is given, returns also the page text snippet.
2005-02-01 13:09:12 +01:00
"""
opts = dict(opts)
data = self.search(text, msg.args[0], {'smallsearch': True})
if data:
url = data['url']
if 'snippet' in opts:
snippet = data['content']
snippet = " | " + utils.web.htmlToText(snippet, tagReplace='')
else:
snippet = ""
result = url + snippet
irc.reply(result)
2005-02-01 13:09:12 +01:00
else:
irc.reply(_('Google found nothing.'))
lucky = wrap(lucky, [getopts({'snippet':'',}), 'text'])
2005-02-01 13:09:12 +01:00
@internationalizeDocstring
2005-02-01 13:09:12 +01:00
def google(self, irc, msg, args, optlist, text):
"""<search> [--{filter,language} <value>]
2005-02-01 13:09:12 +01:00
Searches google.com for the given string. As many results as can fit
are included. --language accepts a language abbreviation; --filter
accepts a filtering level ('active', 'moderate', 'off').
2005-02-01 13:09:12 +01:00
"""
if 'language' in optlist and optlist['language'].lower() not in \
conf.supybot.plugins.Google.safesearch.validStrings:
irc.errorInvalid('language')
data = self.search(text, msg.args[0], dict(optlist))
2005-02-01 13:09:12 +01:00
bold = self.registryValue('bold', msg.args[0])
max = self.registryValue('maximumResults', msg.args[0])
# We don't use supybot.reply.oneToOne here, because you generally
# do not want @google to echo ~20 lines of results, even if you
# have reply.oneToOne enabled.
onetoone = self.registryValue('oneToOne', msg.args[0])
for result in self.formatData(data,
bold=bold, max=max, onetoone=onetoone):
irc.reply(result)
2005-02-01 13:09:12 +01:00
google = wrap(google, [getopts({'language':'something',
'filter':''}),
'text'])
2005-02-01 13:09:12 +01:00
@internationalizeDocstring
2005-02-01 13:09:12 +01:00
def cache(self, irc, msg, args, url):
"""<url>
Returns a link to the cached version of <url> if it is available.
"""
data = self.search(url, msg.args[0], {'smallsearch': True})
if data:
m = data[0]
if m['cacheUrl']:
url = m['cacheUrl'].encode('utf-8')
irc.reply(url)
return
irc.error(_('Google seems to have no cache for that site.'))
2005-02-01 13:09:12 +01:00
cache = wrap(cache, ['url'])
_fight_re = re.compile(r'id="resultStats"[^>]*>(?P<stats>[^<]*)')
@internationalizeDocstring
2005-02-01 13:09:12 +01:00
def fight(self, irc, msg, args):
"""<search string> <search string> [<search string> ...]
Returns the results of each search, in order, from greatest number
of results to least.
"""
channel = msg.args[0]
2005-02-01 13:09:12 +01:00
results = []
for arg in args:
text = self.search(arg, channel, {'smallsearch': True})
i = text.find('id="resultStats"')
stats = utils.web.htmlToText(self._fight_re.search(text).group('stats'))
if stats == '':
results.append((0, args))
continue
count = ''.join(filter('0123456789'.__contains__, stats))
results.append((int(count), arg))
2005-02-01 13:09:12 +01:00
results.sort()
results.reverse()
if self.registryValue('bold', msg.args[0]):
bold = ircutils.bold
else:
bold = repr
s = ', '.join([format('%s: %i', bold(s), i) for (i, s) in results])
irc.reply(s)
2015-07-04 01:42:01 +02:00
def _translate(self, sourceLang, targetLang, text):
2015-07-04 01:42:01 +02:00
headers = dict(utils.web.defaultHeaders)
headers['User-Agent'] = ('Mozilla/5.0 (X11; U; Linux i686) '
'Gecko/20071127 Firefox/2.0.0.11')
sourceLang = utils.web.urlquote(sourceLang)
targetLang = utils.web.urlquote(targetLang)
2015-07-04 01:42:01 +02:00
text = utils.web.urlquote(text)
2015-07-04 01:42:01 +02:00
result = utils.web.getUrlFd('http://translate.googleapis.com/translate_a/single'
'?client=gtx&dt=t&sl=%s&tl=%s&q='
'%s' % (sourceLang, targetLang, text),
headers).read().decode('utf8')
while ',,' in result:
result = result.replace(',,', ',null,')
while '[,' in result:
result = result.replace('[,', '[')
data = json.loads(result)
try:
language = data[2]
except:
language = 'unknown'
if data[0]:
return (''.join(x[0] for x in data[0]), language)
else:
return (_('No translations found.'), language)
@internationalizeDocstring
def translate(self, irc, msg, args, sourceLang, targetLang, text):
"""<source language> [to] <target language> <text>
Returns <text> translated from <source language> into <target
language>.
"""
channel = msg.args[0]
(text, language) = self._translate(sourceLang, targetLang, text)
irc.reply(text, language)
2015-07-04 01:42:01 +02:00
translate = wrap(translate, ['something', 'to', 'something', 'text'])
2005-02-01 13:09:12 +01:00
def googleSnarfer(self, irc, msg, match):
r"^google\s+(.*)$"
if not self.registryValue('searchSnarfer', msg.args[0]):
return
searchString = match.group(1)
data = self.search(searchString, msg.args[0], {'smallsearch': True})
if data['responseData']['results']:
url = data['responseData']['results'][0]['unescapedUrl']
2013-02-24 01:51:40 +01:00
irc.reply(url, prefixNick=False)
2005-02-01 13:09:12 +01:00
googleSnarfer = urlSnarfer(googleSnarfer)
2013-05-30 15:16:36 +02:00
def _googleUrl(self, s, channel):
s = utils.web.urlquote_plus(s)
url = r'http://%s/search?q=%s' % \
(self.registryValue('baseUrl', channel), s)
return url
2013-11-29 16:09:37 +01:00
_calcRe1 = re.compile(r'<span class="cwcot".*?>(.*?)</span>', re.I)
_calcRe2 = re.compile(r'<div class="vk_ans.*?>(.*?)</div>', re.I | re.S)
_calcRe3 = re.compile(r'<div class="side_div" id="rhs_div">.*?<input class="ucw_data".*?value="(.*?)"', re.I)
2013-02-03 08:53:55 +01:00
@internationalizeDocstring
def calc(self, irc, msg, args, expr):
"""<expression>
Uses Google's calculator to calculate the value of <expression>.
"""
2013-05-30 13:13:19 +02:00
channel = msg.args[0]
2013-05-30 15:16:36 +02:00
if not ircutils.isChannel(channel):
2013-05-30 13:13:19 +02:00
channel = None
2014-05-02 21:36:03 +02:00
url = self._googleUrl(expr, channel)
2013-11-29 16:09:37 +01:00
h = {"User-Agent":"Mozilla/5.0 (Windows NT 6.2; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/32.0.1667.0 Safari/537.36"}
2014-05-02 21:36:03 +02:00
html = utils.web.getUrl(url, headers=h).decode('utf8')
2013-02-03 08:53:55 +01:00
match = self._calcRe1.search(html)
2013-11-29 16:09:37 +01:00
if not match:
2013-02-03 08:53:55 +01:00
match = self._calcRe2.search(html)
2013-11-29 16:09:37 +01:00
if not match:
match = self._calcRe3.search(html)
if not match:
irc.reply("I could not find an output from Google Calc for: %s" % expr)
return
else:
s = match.group(1)
else:
s = match.group(1)
else:
2013-02-03 08:53:55 +01:00
s = match.group(1)
2013-11-29 16:09:37 +01:00
# do some cleanup of text
s = re.sub(r'<sup>(.*)</sup>&#8260;<sub>(.*)</sub>', r' \1/\2', s)
s = re.sub(r'<sup>(.*)</sup>', r'^\1', s)
s = utils.web.htmlToText(s)
irc.reply("%s = %s" % (expr, s))
2013-02-03 08:53:55 +01:00
calc = wrap(calc, ['text'])
_phoneRe = re.compile(r'Phonebook.*?<font size=-1>(.*?)<a href')
@internationalizeDocstring
def phonebook(self, irc, msg, args, phonenumber):
"""<phone number>
Looks <phone number> up on Google.
"""
2013-05-30 15:16:36 +02:00
channel = msg.args[0]
if not ircutils.isChannel(channel):
channel = None
url = self._googleUrl(phonenumber, channel)
2013-02-03 08:53:55 +01:00
html = utils.web.getUrl(url).decode('utf8')
m = self._phoneRe.search(html)
if m is not None:
s = m.group(1)
s = s.replace('<b>', '')
s = s.replace('</b>', '')
s = utils.web.htmlToText(s)
irc.reply(s)
else:
irc.reply(_('Google\'s phonebook didn\'t come up with anything.'))
phonebook = wrap(phonebook, ['text'])
2005-02-01 13:09:12 +01:00
Class = Google
# vim:set shiftwidth=4 softtabstop=4 expandtab textwidth=79: