X-Git-Url: http://www.privoxy.org/gitweb/?p=privoxy.git;a=blobdiff_plain;f=default.filter;h=8fa455b8f5176ae2940738a50c6551811af0c5cf;hp=b4e77ad8aef9fa45343834aadeabaafa4c6eb07f;hb=19e04ffa314b697a88f51fbc9a5c7cfc812397bc;hpb=2f190a24b298322d5a9190bd7da38199a881b0f6 diff --git a/default.filter b/default.filter index b4e77ad8..8fa455b8 100644 --- a/default.filter +++ b/default.filter @@ -2,11 +2,11 @@ # # File : $Source: /cvsroot/ijbswa/current/default.filter,v $ # -# $Id: default.filter,v 1.52 2007/11/27 18:35:48 fabiankeil Exp $ +# $Id: default.filter,v 1.67 2008/08/06 17:38:06 fabiankeil Exp $ # # Purpose : Rules to process the content of web pages # -# Copyright : Written by and Copyright (C) 2001 - 2007 the +# Copyright : Written by and Copyright (C) 2001-2008 the # Privoxy team. http://www.privoxy.org/ # # We value your feedback. However, to provide you with the best support, @@ -219,14 +219,17 @@ s/\starget\s*=\s*(['"]?)_?(blank|new)\1?/ /ig # (X)HTML FILTER: img-reorder Reorder attributes in tags to make the banners-by-* filters more effective. # In the first step src is moved to the start, then width is moved to the second -# place to guarantee an order of src, width, height. +# place to guarantee an order of src, width, height. Also does some white-space +# normalization. +# # This makes banners-by-size more effective and allows both banners-by-size # and banners-by-link to preserve the original image URL in the title attribute. -s|]*) src\s*=\s*(['"])([^>\\\2]+)\2|]*) src\s*=\s*([^'">\\\s]+)|]*)\ssrc\s*=\s*(['"])([^>\\\2]+)\2|]*)\ssrc\s*=\s*([^'">\\\s]+)|]+height)\s*=\s*|$1=|sig -s|\\\\2]*\2\|[^'">\\\s]+?))([^>]*)\s+width\s*=\s*(["']?)(\d+?)\4|\\\\2]*\2\|[^'">\\\s]+?))([^>]*)\s+width\s*=\s*((["']?)\d+?\5)(?=[\s>])|\1\s]*?(?:\ adclick # See www.dn.se \ | advert # see dict.leo.org \ | atwola\.com/(?:link|redir) # see www.cnn.com \ -| /jump/ # redirs for doublecklick.net ads \ +| doubleclick\.net/jump/ # redirs for doublecklick.net ads \ | counter # common \ | (?)/$1ädchen/Ug # Pages are "blocked" based on keyword matching. # ################################################################################# -FILTER: crude-parental Crude parental filtering. Note that this filter doesn't work reliable. +FILTER: crude-parental Crude parental filtering. Note that this filter doesn't work reliably. # (Note: Middlesex, Sussex and Essex are counties in the UK, not rude words) # (Note #2: Is 'sex' a rude word?!) @@ -458,7 +461,7 @@ s+^.*warez.*$+
@\n\n$0@
@@ -607,14 +609,13 @@ s@@\n\n$0@
+# Are these ids still in use?
s@( ]*) id=(["']?)ads_[^\2]*\2@$1 class="msn_ads"@Uig
+s@( ]*) class=(["']?)sb_ads[^\2]*\2@$1 class="msn_ads"@Uig
s@(]*href=\")http://g.msn.com/.*\?(http://.*)(&&DI=.*)(\")@$1$2$4@Ug
s@(]*)gping=\".*\"@$1 title="URL cleaned up by Privoxy's msn filter"@Ug
@@ -636,6 +640,9 @@ s@(]*)gping=\".*\"@$1 title="URL cleaned up by Privoxy's msn filter"@Ug
# appear to early or not at all and as fixing this would require a browser
# that understands background-size (CSS3), they are removed instead.
#
+# When applied to feeds, it removes comment titles that
+# only contain the beginning of the actual comment.
+#
#################################################################################
FILTER: blogspot Cleans up some Blogspot blogs. Read the fine print before using this.
@@ -654,6 +661,8 @@ s@ |(([^\s]*).*?\.\.\.\s*( |