Fix for Issue #42

stamparm · stamparm · commit 2a72fcce2b68 · 2012-06-28T13:55:30.000+02:00
diff --git a/lib/core/option.py b/lib/core/option.py
@@ -1154,14 +1154,14 @@ def __setHTTPUserAgent():
         conf.httpHeaders.append(("User-Agent", conf.agent))
 
     elif not conf.randomAgent:
-        addDefaultUserAgent = True
+        _ = True
 
         for header, _ in conf.httpHeaders:
             if header == "User-Agent":
-                addDefaultUserAgent = False
+                _ = False
                 break
 
-        if addDefaultUserAgent:
+        if _:
             conf.httpHeaders.append(("User-Agent", __defaultHTTPUserAgent()))
 
     else:
diff --git a/lib/core/settings.py b/lib/core/settings.py
@@ -63,7 +63,7 @@
 PRINTABLE_CHAR_REGEX = r"[^\x00-\x1f\x7e-\xff]"
 
 # regular expression used for extracting results from google search
-GOOGLE_REGEX = r"url\?q=(http[^>]+)&amp;sa=U&amp"
+GOOGLE_REGEX = r"url\?\w+=(http[^>]+)&amp;(sa=U|rct=j)"
 
 # regular expression used for extracting content from "textual" tags
 TEXT_TAG_REGEX = r"(?si)<(abbr|acronym|b|blockquote|br|center|cite|code|dt|em|font|h\d|i|li|p|pre|q|strong|sub|sup|td|th|title|tt|u)(?!\w).*?>(?P<result>[^<]+)"
diff --git a/lib/utils/google.py b/lib/utils/google.py
@@ -46,7 +46,7 @@ def _parsePage(self, page):
         HTTP addresses
         """
 
-        retVal = re.findall(GOOGLE_REGEX, page, re.I | re.S)
+        retVal = [match.group(1) for match in re.finditer(GOOGLE_REGEX, page, re.I | re.S)]
 
         return retVal
 
