Apkawa/pygooglesearch.py

   1 # -*- coding: utf-8 -*-
   2 import urllib
   3 from json import loads
   4
   5 class GoogleSearchApi:
   6     def __init__(self):
   7         self.api_url = 'http://ajax.googleapis.com/ajax/services/search/%(type)s?%(query)s'
   8         self.query = {'v':1.0, 'rsz':'small','hl':'en'}
   9         pass
  10     def __get_result(self, type):
  11         search_url = self.api_url%{'type':type,'query': urllib.urlencode( self.query) }
  12         resp = urllib.urlopen(  search_url ).read()
  13         self.__parse( resp)
  14
  15         if self.status == 200:
  16             return True
  17         else:
  18             return False
  19     def __parse(self, resp):
  20         response = loads( resp)
  21         self.status = response['responseStatus']
  22         self.cursor = response['responseData']['cursor']
  23         self.results = response['responseData']['results']
  24     def __check_args(self, args, const):
  25         c_a_key = const.keys()
  26         result_args = {}
  27
  28         for a in args.keys():
  29             if a in c_a_key:
  30                 val = const[a]['val']
  31                 if val:
  32                     if args[a] in val.keys():
  33                         result_args.update( {a, args[a]} )
  34
  35
  36     def search(self, word, lang='en'):
  37         self.query['q'] = urllib.quote(word)
  38         self.query['hl'] = lang
  39         return True
  40     def web(self, help=True, **args):
  41         const_arguments = {
  42                 'cx': {
  43                     'desc':'This optional argument supplies the unique id for the Custom Search Engine that should be used for this request (e.g., cx=000455696194071821846:reviews).'
  44                     'val': None,}
  45                 'cref': {
  46                     'desc':'This optional argument supplies the url of a linked Custom Search Engine specification that should be used to satisfy this request (e.g., cref=http%3A%2F%2Fwww.google.com%2Fcse%2Fsamples%2Fvegetarian.xml).',
  47                     'val':None}
  48                 'safe':{
  49                     'desc':'This optional argument supplies the search safety level which may be one of:',
  50                     'val':{'active':'enables the highest level of safe search filtering',
  51                         'moderate':'enables moderate safe search filtering (default)',
  52                         'off':'disables safe search filtering'},}
  53                 'lr':{
  54                     'desc':'This optional argument allows the caller to restrict the search to documents written in a particular language (e.g., lr=lang_ja). This list contains the permissible set of values.',
  55                     'val':None}
  56                 }
  57
  58         self.check_args( args, const_arguments )
  59
  60
  61         self.query.update( {'lr':'lang_'+lr, 'safe': safe })
  62         return self.__get_result('web')
  63
  64     def image(self, help=False,**args )# imgz = None, imgc=None, imgtype=None, as_filetype=None, as_sitesearch=None):
  65         arguments = {
  66             'imgz':{
  67                 'desc':'This optional argument tells the image search system to restrict the search to images of the specified size, where size can be one of',
  68                 'val':{
  69                     'icon':'restrict to small images',
  70                     'small|medium|large|xlarge':'restrict to medium images',
  71                     'xxlarge':'restrict to large images',
  72                     'huge':'restrict to extra large images'
  73                 },
  74             'imgc':{},
  75             'imgtype':{},
  76             'as_filetype':{},
  77             'as_sitesearch':{},
  78             'lr':{}}
  79         self.query.update( {'lr':'lang_'+lr, 'safe': safe })
  80         return self.__get_result('image')
  81
  82
  83 def google(word):
  84     def web(results):
  85         if results:
  86             url = urllib.unquote(results[0]['url'])
  87             title1 = results[0]['titleNoFormatting']
  88             title2 = results[0]['title']
  89             content = re.sub('(<b>)|(</b>)','',results[0]['content'])
  90             text = '%s\n%s\n%s'%(title1,content,url)
  91             text = re.sub('&#39;','\'',unescape(text))
  92             #print text
  93
  94             extra = '''<a href="%s">%s</a>
  95             <p>%s</p>
  96             '''%(url,title2,content)
  97             return True, text, extra
  98         else: return True, 'Nyaaa... Ничего не нашла.', ''
  99     def images(results):
 100         if results:
 101             imgurl = results[0]['unescapedUrl']
 102             return imgurl
 103         else: return None
 104     #http://code.google.com/apis/ajaxsearch/documentation/reference.html#_intro_fonje
 105     _type = 'images'
 106     #word = urllib.quote(word.encode('utf-8'))
 107     word = urllib.quote(word)
 108     src =  urllib.urlopen('http://ajax.googleapis.com/ajax/services/search/%s?v=1.0&q=%s'%(_type,word)).read()
 109     convert = loads(src)
 110     results = convert['responseData']['results']
 111     return images(results)
 112     #if type == 'web':
 113         #return web(results)
 114     #if type == 'images':
 115    #     return images(results)
 116
 117 if __name__ == '__main__':
 118     search = GoogleSearchApi()
 119     search.search('nya')
 120     search.web()
 121     print search.results