Add --filter-toc option

src/calibre/ebooks/conversion/plumber.py

@@ -176,6 +176,15 @@ OptionRecommendation(name='max_toc_links',
                 )
         ),
 
+OptionRecommendation(name='toc_filter',
+            recommended_value=None, level=OptionRecommendation.LOW,
+            help=_('Remove entries from the Table of Contents whose titles '
+            'match the specified regular expression. Matching entries and all '
+            'their children are removed.'
+                )
+        ),
+
+
 OptionRecommendation(name='chapter',
         recommended_value="//*[((name()='h1' or name()='h2') and "
               "re:test(., 'chapter|book|section|part', 'i')) or @class "

src/calibre/ebooks/oeb/base.py

@@ -1276,6 +1276,16 @@ class TOC(object):
         self.nodes.append(node)
         return node
 
+    def remove(self, node):
+        for child in self.nodes:
+            if child is node:
+                self.nodes.remove(child)
+                return True
+            else:
+                if child.remove(node):
+                    return True
+        return False
+
     def iter(self):
         """Iterate over this node and all descendants in depth-first order."""
         yield self

src/calibre/ebooks/oeb/transforms/structure.py

@@ -6,6 +6,8 @@ __license__   = 'GPL v3'
 __copyright__ = '2009, Kovid Goyal <kovid@kovidgoyal.net>'
 __docformat__ = 'restructuredtext en'
 
+import re
+
 from lxml import etree
 from urlparse import urlparse
 
@@ -37,6 +39,12 @@ class DetectStructure(object):
                 self.log('Auto generated TOC with %d entries.' %
                         self.oeb.toc.count())
 
+        if opts.toc_filter is not None:
+            regexp = re.compile(opts.toc_filter)
+            for node in self.oeb.toc.iter():
+                if not node.title or regexp.search(node.title) is not None:
+                    self.oeb.toc.remove(node)
+
 
     def detect_chapters(self):
         self.detected_chapters = []