Moved HTMLParser from parse_html_beautifulsoup.py to parse_html_util.py.

git-svn-id: file:///home/phd/archive/SVN/bookmarks_db/trunk@257 fdd5c36f-1aea-0310-aeeb-c58d7e2b6c23

diff --git a/Robots/parse_html_beautifulsoup.py b/Robots/parse_html_beautifulsoup.py
index 580831070aae1abb3526921b6c4da41ef6176541..8b26d635b763e3eb2b822cd1a871110d1fbb4824 100644 (file)
--- a/Robots/parse_html_beautifulsoup.py
+++ b/Robots/parse_html_beautifulsoup.py
@@ -6,18 +6,8 @@
 
 import re
 from sgmllib import SGMLParser, SGMLParseError
-from HTMLParser import HTMLParser
 from BeautifulSoup import BeautifulSoup, CData
-
-
-class BSoupParser(HTMLParser):
-   def __init__(self, charset, meta, title, refresh, icon):
-      object.__init__(self)
-      self.charset = charset
-      self.meta_charset = meta
-      self.title = title
-      self.refresh = refresh
-      self.icon = icon
+from parse_html_util import HTMLParser
 
 
 # http://groups.google.com/group/beautifulsoup/browse_thread/thread/69093cb0d3a3cf63
@@ -125,7 +115,7 @@ def parse_html(filename, charset=None, log=None):
    else:
       icon = None
 
-   return BSoupParser(_charset, meta_charset, title, refresh, icon)
+   return HTMLParser(_charset, meta_charset, title, refresh, icon)
 
 def _find_contenttype(Tag):
    return (Tag.name == "meta") and \

diff --git a/Robots/parse_html_util.py b/Robots/parse_html_util.py
new file mode 100644 (file)
index 0000000..79890dd
--- /dev/null
+++ b/Robots/parse_html_util.py
@@ -0,0 +1,16 @@
+"""
+   HTML parsers utilities
+
+   Written by Broytman. Copyright (C) 2010 PhiloSoft Design
+"""
+
+from HTMLParser import HTMLParser
+
+class HTMLParser(HTMLParser):
+   def __init__(self, charset, meta_charset, title, refresh, icon):
+      object.__init__(self)
+      self.charset = charset
+      self.meta_charset = meta_charset
+      self.title = title
+      self.refresh = refresh
+      self.icon = icon