From 158acb2979b91ffc534764a194eb2da1318a3ad7 Mon Sep 17 00:00:00 2001
From: Francois Marier <francois@fmarier.org>
Date: Fri, 3 Apr 2015 17:50:26 +1300
Subject: [PATCH] Ignore RSS post titles unless there are blacklisted titles or
 authors

---
 planetfilter | 79 +++++++++++++++++++++++++++++++++---------------------------
 1 file changed, 43 insertions(+), 36 deletions(-)

diff --git a/planetfilter b/planetfilter
index 47090ae..6433fdd 100755
--- a/planetfilter
+++ b/planetfilter
@@ -102,22 +102,25 @@ def filter_rss2(xmldocument, blacklist):
     for item in items:
         deleted = False
         titles = item.getElementsByTagName('title')
-        for title in titles:
-            textnode = title.firstChild
-            if textnode and Node.TEXT_NODE == textnode.nodeType:
-                titlestring = textnode.nodeValue
-                if blacklist['authors']:
-                    for author in blacklist['authors']:
-                        if 0 == titlestring.find(author):
-                            delete_node(item)
-                            deleted = True
-                            break
-                if not deleted and blacklist['titles']:
-                    for title in blacklist['titles']:
-                        if titlestring.find(title) > -1:
-                            delete_node(item)
-                            deleted = True
-                            break
+        if blacklist['authors'] or blacklist['titles']:
+            for title in titles:
+                textnode = title.firstChild
+                if textnode and Node.TEXT_NODE == textnode.nodeType:
+                    titlestring = textnode.nodeValue
+                    if blacklist['authors']:
+                        for author in blacklist['authors']:
+                            if 0 == titlestring.find(author):
+                                delete_node(item)
+                                deleted = True
+                                break
+                    if not deleted and blacklist['titles']:
+                        for title in blacklist['titles']:
+                            if titlestring.find(title) > -1:
+                                delete_node(item)
+                                deleted = True
+                                break
+                if deleted:
+                    break
 
         if not deleted and blacklist['urls']:
             links = item.getElementsByTagName('link')
@@ -153,8 +156,9 @@ def filter_atom(xmldocument, blacklist):
                             delete_node(entry)
                             deleted = True
                             break
-                    if deleted:
-                        break
+                if deleted:
+                    break
+
         if not deleted and blacklist['titles']:
             titles = entry.getElementsByTagName('title')
             for title in titles:
@@ -166,8 +170,8 @@ def filter_atom(xmldocument, blacklist):
                             delete_node(entry)
                             deleted = True
                             break
-                    if deleted:
-                        break
+                if deleted:
+                    break
 
         if not deleted and blacklist['urls']:
             links = entry.getElementsByTagName('link')
@@ -193,22 +197,25 @@ def filter_rss1(xmldocument, blacklist):
     for item in items:
         deleted = False
         titles = item.getElementsByTagName('title')
-        for title in titles:
-            textnode = title.firstChild
-            if textnode and Node.TEXT_NODE == textnode.nodeType:
-                titlestring = textnode.nodeValue
-                if blacklist['authors']:
-                    for author in blacklist['authors']:
-                        if 0 == titlestring.find(author):
-                            delete_rss1_item(item)
-                            deleted = True
-                            break
-                if not deleted and blacklist['titles']:
-                    for title in blacklist['titles']:
-                        if titlestring.find(title) > -1:
-                            delete_rss1_item(item)
-                            deleted = True
-                            break
+        if blacklist['authors'] or blacklist['titles']:
+            for title in titles:
+                textnode = title.firstChild
+                if textnode and Node.TEXT_NODE == textnode.nodeType:
+                    titlestring = textnode.nodeValue
+                    if blacklist['authors']:
+                        for author in blacklist['authors']:
+                            if 0 == titlestring.find(author):
+                                delete_rss1_item(item)
+                                deleted = True
+                                break
+                    if not deleted and blacklist['titles']:
+                        for title in blacklist['titles']:
+                            if titlestring.find(title) > -1:
+                                delete_rss1_item(item)
+                                deleted = True
+                                break
+                if deleted:
+                    break
 
         if not deleted and blacklist['urls']:
             links = item.getElementsByTagName('link')
-- 
2.11.4.GIT