Merge branch 'develop'

Author: AlexVonB

README.rst

@@ -100,6 +100,29 @@ Options may be specified as kwargs to the ``markdownify`` function, or as a
 nested ``Options`` class in ``MarkdownConverter`` subclasses.
 
 
+Creating Custom Converters
+=========================
+
+If you have a special usecase that calls for a special conversion, you can
+always inherit from ``MarkdownConverter`` and override the method you want to
+change:
+
+.. code:: python
+
+    from markdownify import MarkdownConverter
+
+    class ImageBlockConverter(MarkdownConverter):
+        """
+        Create a custom MarkdownConverter that adds two newlines after an image
+        """
+        def convert_img(self, el, text, convert_as_inline):
+            return super().convert_img(el, text, convert_as_inline) + '\n\n'
+
+    # Create shorthand method for conversion
+    def md(html, **options):
+        return ImageBlockConverter(**options).convert(html)
+
+
 Development
 ===========
 

markdownify/__init__.py

@@ -142,22 +142,26 @@ def is_nested_node(el):
         return text
 
     def process_text(self, el):
-        text = six.text_type(el)
+        text = six.text_type(el) or ''
 
         # dont remove any whitespace when handling pre or code in pre
-        if (el.parent.name == 'pre'
-                or (el.parent.name == 'code' and el.parent.parent.name == 'pre')):
-            return escape(text or '')
+        if not (el.parent.name == 'pre'
+                or (el.parent.name == 'code'
+                    and el.parent.parent.name == 'pre')):
+            text = whitespace_re.sub(' ', text)
 
-        cleaned_text = escape(whitespace_re.sub(' ', text or ''))
+        if el.parent.name != 'code':
+            text = escape(text)
 
         # remove trailing whitespaces if any of the following condition is true:
         # - current text node is the last node in li
         # - current text node is followed by an embedded list
-        if el.parent.name == 'li' and (not el.next_sibling or el.next_sibling.name in ['ul', 'ol']):
-            return cleaned_text.rstrip()
+        if (el.parent.name == 'li'
+                and (not el.next_sibling
+                     or el.next_sibling.name in ['ul', 'ol'])):
+            text = text.rstrip()
 
-        return cleaned_text
+        return text
 
     def __getattr__(self, attr):
         # Handle headings

setup.py

@@ -10,7 +10,7 @@
 pkgmeta = {
     '__title__': 'markdownify',
     '__author__': 'Matthew Tretter',
-    '__version__': '0.9.0',
+    '__version__': '0.9.1',
 }
 
 

tests/test_conversions.py

@@ -70,6 +70,7 @@ def test_br():
 
 def test_code():
     inline_tests('code', '`')
+    assert md('<code>this_should_not_escape</code>') == '`this_should_not_escape`'
 
 
 def test_del():
@@ -131,8 +132,6 @@ def test_hn_nested_simple_tag():
 
 
 def test_hn_nested_img():
-    assert md('<img src="/path/to/img.jpg" alt="Alt text" title="Optional title" />') == '![Alt text](/path/to/img.jpg "Optional title")'
-    assert md('<img src="/path/to/img.jpg" alt="Alt text" />') == '![Alt text](/path/to/img.jpg)'
     image_attributes_to_markdown = [
         ("", ""),
         ("alt='Alt Text'", "Alt Text"),

tests/test_custom_converter.py

@@ -0,0 +1,18 @@
+from markdownify import MarkdownConverter
+
+
+class ImageBlockConverter(MarkdownConverter):
+    """
+    Create a custom MarkdownConverter that adds two newlines after an image
+    """
+    def convert_img(self, el, text, convert_as_inline):
+        return super().convert_img(el, text, convert_as_inline) + '\n\n'
+
+
+def test_img():
+    # Create shorthand method for conversion
+    def md(html, **options):
+        return ImageBlockConverter(**options).convert(html)
+
+    assert md('<img src="/path/to/img.jpg" alt="Alt text" title="Optional title" />') == '![Alt text](/path/to/img.jpg "Optional title")\n\n'
+    assert md('<img src="/path/to/img.jpg" alt="Alt text" />') == '![Alt text](/path/to/img.jpg)\n\n'