_find() method (using ajax api) added to google module

oxweb/google.py

@@ -1,13 +1,15 @@
-# -*- coding: utf-8 -*-
+# -*- coding: utf-8 -*-
 # vi:si:et:sw=4:sts=4:ts=4
-import re
-import time
-import urllib
-import urllib2
-import weakref
-import threading
-import Queue
-
+import re
+import time
+import urllib
+import urllib2
+import weakref
+import threading
+import Queue
+import simplejson
+
+
 import oxlib 
 from oxlib import stripTags
 
@@ -25,26 +27,31 @@ google.find(query, max_results)
 
 FIXME: how search depper than first page?
 '''
-DEFAULT_MAX_RESULTS = 10
+DEFAULT_MAX_RESULTS = 10
 
 def getUrl(url, data=None, headers=oxlib.net.DEFAULT_HEADERS):
     google_timeout=24*60*60
     return oxlib.cache.getUrl(url, data, headers, google_timeout)
 
-def quote_plus(s):
-    return urllib.quote_plus(s.encode('utf-8'))
+def quote_plus(s):
+    return urllib.quote_plus(s.encode('utf-8'))
 
 def find(query, max_results=DEFAULT_MAX_RESULTS):
     url = "http://www.google.com/search?q=%s" % quote_plus(query)
     data = getUrl(url)
-    link_re = r'<a href="(?P<url>[^"]*?)" class=l.*?>(?P<name>.*?)</a>' +  \
-              r'.*?(?:<br>|<table.*?>)' +  \
-              r'(?P<desc>.*?)' + '(?:<font color=#008000>|<a)'
-    results = []
-    for match in re.compile(link_re, re.DOTALL).finditer(data):
-        (name, url, desc) = match.group('name', 'url', 'desc')
+    link_re = r'<a href="(?P<url>[^"]*?)" class=l.*?>(?P<name>.*?)</a>' +  \
+              r'.*?(?:<br>|<table.*?>)' +  \
+              r'(?P<desc>.*?)' + '(?:<font color=#008000>|<a)'
+    results = []
+    for match in re.compile(link_re, re.DOTALL).finditer(data):
+        (name, url, desc) = match.group('name', 'url', 'desc')
         results.append((stripTags(name), url, stripTags(desc)))
     if len(results) > max_results:
-        results = results[:max_results]
+        results = results[:max_results]
+    return results
+
+def _find(query):
+    url = 'http://ajax.googleapis.com/ajax/services/search/web?v=1.0&q=%s' % quote_plus(query)
+    results = simplejson.loads(getUrlUnicode(url))['responseData']['results']
     return results