Added new functions to parse html.

--HG--
extra : convert_revision : svn%3Ab85faa78-f9eb-468e-a121-7cced6da292c%40295

scrapy/trunk/scrapy/utils/markup.py

@@ -59,3 +59,42 @@ def replace_tags(text, token=''):
     Always returns a unicode string.
     """
     return _tag_re.sub(token, text.decode('utf-8'))
+
+
+def remove_comments(text):
+    """ Remove HTML Comments. """
+    return re.sub('<!--.*?-->', '', text, re.DOTALL)
+      
+def remove_tags(text, which_ones=()):
+    """ Remove HTML Tags only. 
+
+        which_ones -- is a tuple of which tags we want to remove.
+                      if is empty remove all tags.
+    """
+    if len(which_ones) > 0:
+        tags = [ '<%s>|<%s .*?>|</%s>' % (tag,tag,tag) for tag in which_ones ]
+        reg_exp_remove_tags = '|'.join(tags)
+    else:
+        reg_exp_remove_tags = '<.*?>'
+    re_tags = re.compile(reg_exp_remove_tags, re.DOTALL)
+    return re_tags.sub('', text)
+
+def remove_tags_with_content(text, which_ones=()):
+    """ Remove tags and its content.
+        
+        which_ones -- is a tuple of which tags with its content we want to remove.
+                      if is empty do nothing.
+    """
+    tags = [ '<%s.*?</%s>' % (tag,tag) for tag in which_ones ]
+    re_tags_remove = re.compile('|'.join(tags), re.DOTALL)
+    return re_tags_remove.sub('', text)
+
+def remove_escape_chars(text, which_ones=('\n','\t','\r')):
+    """ Remove escape chars. Default : \\n, \\t, \\r
+
+        which_ones -- is a tuple of which escape chars we want to remove.
+                      if is empty do nothing.
+    """
+    re_escape_chars = re.compile('[%s]' % ''.join(which_ones))
+    return re_escape_chars.sub('', text)
+