Extensions Docs Server: Doc conversion script

chrome/common/extensions/docs/server2/intro_data_source.py

 # Copyright (c) 2012 The Chromium Authors. All rights reserved.
 # Use of this source code is governed by a BSD-style license that can be
 # found in the LICENSE file.
 
-import logging
-
 from HTMLParser import HTMLParser
+import re
 
 from docs_server_utils import FormatKey
 from third_party.handlebar import Handlebar
 
 class _IntroParser(HTMLParser):
   """ An HTML parser which will parse table of contents and page title info out
   of an intro.
   """
   def __init__(self):
     HTMLParser.__init__(self)
@@ skipping 37 matching lines @@
   """This class fetches the intros for a given API. From this intro, a table
   of contents dictionary is created, which contains the headings in the intro.
   """
   def __init__(self, cache_builder, base_paths):
     self._cache = cache_builder.build(self._MakeIntroDict)
     self._base_paths = base_paths
 
   def _MakeIntroDict(self, intro):
     parser = _IntroParser()
     parser.feed(intro)
+    intro = re.sub(re.compile('<h1[^>.]*?>.*?</h1>', flags=re.DOTALL),

[cduvall, 2012/08/02 00:54:06]

Used re here because there's not an easy way to remove things with HTMLParser.
I'm pretty sure my re handles all the cases though.

+                   '',
+                   intro,
+                   count=1)
     return {
       'intro': Handlebar(intro),
       'toc': parser.toc,
       'title': parser.page_title
     }
 
   def __getitem__(self, key):
     return self.get(key)
 
   def get(self, key):
     real_path = FormatKey(key)
     for base_path in self._base_paths:
       try:
         return self._cache.GetFromFile(base_path + '/' + real_path)
       except Exception:
         pass
     return None