diff --git a/lib/core/settings.py b/lib/core/settings.py index 6b01a4b0c..d31422753 100644 --- a/lib/core/settings.py +++ b/lib/core/settings.py @@ -53,7 +53,7 @@ PERMISSION_DENIED_REGEX = r"(command|permission|access)\s*(was|is)?\s*denied" MAX_CONNECTIONS_REGEX = r"max.+connections" # Regular expression used for extracting results from google search -GOOGLE_REGEX = r"url\?\w+=(http[^>]+)&(sa=U|rct=j)" +GOOGLE_REGEX = r"url\?\w+=((?![^>]+webcache\.googleusercontent\.com)http[^>]+)&(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[^<]+)"