Phoney

__module_name__ = "Phoney"
__module_author__ = "NovaSquirrel"
__module_description__ = "Misc phenny/skybot theft module"
__module_version__ = "0.05"

import xchat
import random
import re, urllib, urllib2, httplib, urlparse, gzip, StringIO, socket, hashlib
from htmlentitydefs import name2codepoint

#######################################################################################

class Grab(urllib.URLopener):
   def __init__(self, *args):
      self.version = 'Mozilla/5.0 (Phenny)'
      urllib.URLopener.__init__(self, *args)
      self.addheader('Referer', 'https://github.com/sbp/phenny')
   def http_error_default(self, url, fp, errcode, errmsg, headers):
      return urllib.addinfourl(fp, [headers, errcode], "http:" + url)
urllib._urlopener = Grab()

def webget(uri):
   if not uri.startswith('http'):
      return
   u = urllib.urlopen(uri)
   bytes = u.read()
   u.close()
   return bytes

def webhead(uri):
   if not uri.startswith('http'):
      return
   u = urllib.urlopen(uri)
   info = u.info()
   u.close()
   return info

def webpost(uri, query):
   if not uri.startswith('http'):
      return
   data = urllib.urlencode(query)
   u = urllib.urlopen(uri, data)
   bytes = u.read()
   u.close()
   return bytes

r_entity = re.compile(r'&([^;\s]+);')

def webentity(match):
   value = match.group(1).lower()
   if value.startswith('#x'):
      return unichr(int(value[2:], 16))
   elif value.startswith('#'):
      return unichr(int(value[1:]))
   elif name2codepoint.has_key(value):
      return unichr(name2codepoint[value])
   return '[' + value + ']'

def webdecode(html):
   return r_entity.sub(entity, html)

r_string = re.compile(r'("(\\.|[^"\\])*")')
r_json = re.compile(r'^[,:{}\[\]0-9.\-+Eaeflnr-u \n\r\t]+$')
env = {'__builtins__': None, 'null': None, 'true': True, 'false': False}

def webjson(text):
   """Evaluate JSON text safely (we hope)."""
   if r_json.match(r_string.sub('', text)):
      text = r_string.sub(lambda m: 'u' + m.group(1), text)
      return eval(text.strip(' \t\r\n'), env, {})
   raise ValueError('Input must be serialised JSON.')
#######################################################################################
r_title = re.compile(r'(?ims)<title[^>]*>(.*?)</title\s*>')
r_entity = re.compile(r'&[A-Za-z0-9#]+;')

def WebTitle(uri):
   if not uri:
      return 'I need a URI to give the title of...'

   if not ':' in uri:
      uri = 'http://' + uri
   uri = uri.replace('#!', '?_escaped_fragment_=')

   try:
      redirects = 0
      while True:
         headers = {
            'Accept': 'text/html',
            'User-Agent': 'Mozilla/5.0 (Phoney)'
         }
         req = urllib2.Request(uri, headers=headers)
         u = urllib2.urlopen(req)
         info = u.info()
         u.close()

         if not isinstance(info, list):
            status = '200'
         else:
            status = str(info[1])
            info = info[0]
         if status.startswith('3'):
            uri = urlparse.urljoin(uri, info['Location'])
         else: break

         redirects += 1
         if redirects >= 25:
            return 'Too many redirects'

      try: mtype = info['content-type']
      except:
         return "Couldn't get the Content-Type, sorry"
      if not (('/html' in mtype) or ('/xhtml' in mtype)):
         return "Document isn't HTML"

      u = urllib2.urlopen(req)
      bytes = u.read(262144)
      u.close()

   except IOError:
      return "Can't connect"

   m = r_title.search(bytes)
   if m:
      title = m.group(1)
      title = title.strip()
      title = title.replace('\t', ' ')
      title = title.replace('\r', ' ')
      title = title.replace('\n', ' ')
      while '  ' in title:
         title = title.replace('  ', ' ')
      if len(title) > 200:
         title = title[:200] + '[...]'

      if title:
         try: title.decode('utf-8')
         except:
            try: title = title.decode('iso-8859-1').encode('utf-8')
            except: title = title.decode('cp1252').encode('utf-8')
         else: pass
      else: title = '[The title is empty.]'

      title = title.replace('\n', '')
      title = title.replace('\r', '')
      return title
   else: return 'No title found';

#######################################################################################

def SafeAnswer(answer):
    answer = (answer[:420] + '..') if len(answer) > 420 else answer
    return answer.replace('\n', '').replace('\r', '')

def Suggest(query):
    uri = 'http://websitedev.de/temp-bin/suggest.pl?q='
    answer = webget(uri + urllib.quote(query).replace('+', '%2B'))
    if answer:
        return SafeAnswer(answer)
    else:
        return 'Sorry, no result.'

def google_ajax(query):
   if isinstance(query, unicode):
      query = query.encode('utf-8')
   uri = 'http://ajax.googleapis.com/ajax/services/search/web'
   args = '?v=1.0&safe=off&q=' + urllib.quote(query)
   bytes = webget(uri + args)
   return webjson(bytes)

def google_search(query, number):
   results = google_ajax(query)
   try:
     result = results['responseData']['results'][number]['unescapedUrl']
     try:
       result = result + ' "' + WebTitle(result) + '"'
     except:
       result = result + ' ?'
     return result
   except IndexError: return None
   except TypeError:
      print results
      return False

def Google4(query, ReplyCmd):
   results = google_ajax(query)
   try:
     xchat.command(ReplyCmd + "1. " + results['responseData']['results'][0]['unescapedUrl']);
     xchat.command(ReplyCmd + "2. " + results['responseData']['results'][1]['unescapedUrl']);
     xchat.command(ReplyCmd + "3. " + results['responseData']['results'][2]['unescapedUrl']);
     xchat.command(ReplyCmd + "4. " + results['responseData']['results'][3]['unescapedUrl']);
   except IndexError: return None
   except TypeError:
      print results
      return False

def GoogleSearch(query, number):
   uri = google_search(query, number)
   if uri:
      return uri
   elif uri is False: return "Problem getting data from Google."
   else: return "No results found for '" + query + "'"

def Python(query):
   uri = 'http://tumbolia.appspot.com/py/'
   answer = webget(uri + urllib.quote(query))
   if answer:
     return SafeAnswer(answer)
   else: return "Sorry, no result"

def ExtCmdHandler(word, word_eol, userdata):
    ReplyCmd = word[1] + " "
    NBCmd = word[2]
    Nick = word[3]

    ArgStart = 0
    ArgString = ""
    for i in range(4,len(word)):
        if word[i] == "-A":
            if len(word) >= i+2:
                ArgStart = i+1
                ArgString = word_eol[i+1]
                break

    takes_string = ["py","suggest","g","g4","dns","md5","sha1"]
    if NBCmd in takes_string:
        if ArgStart == 0:
            xchat.command(ReplyCmd + "Oops, that command needs parameters after the command name to work")
            return xchat.EAT_ALL
    if NBCmd == "py": xchat.command(ReplyCmd + Python(ArgString)); return xchat.EAT_ALL
    if NBCmd == "suggest": xchat.command(ReplyCmd + Suggest(ArgString)); return xchat.EAT_ALL
    if NBCmd == "g": xchat.command(ReplyCmd + GoogleSearch(ArgString, 0)); return xchat.EAT_ALL
    if NBCmd == "title": xchat.command(ReplyCmd + WebTitle(ArgString)); return xchat.EAT_ALL
    if NBCmd == "g4": Google4(ArgString, ReplyCmd); return xchat.EAT_ALL
    if NBCmd == "dns": xchat.command(ReplyCmd + socket.gethostbyname(ArgString)); return xchat.EAT_ALL
    if NBCmd == "md5": xchat.command(ReplyCmd + hashlib.md5(ArgString).hexdigest()); return xchat.EAT_ALL
    if NBCmd == "sha1": xchat.command(ReplyCmd + hashlib.sha1(ArgString).hexdigest()); return xchat.EAT_ALL

    return xchat.EAT_NONE

xchat.hook_command("NB_ExtCmd", ExtCmdHandler)