Merge branch 'tdgroot-code_language_callback' into develop

closes #64

README.rst

@@ -102,6 +102,19 @@ code_language
   should be annotated with `````python`` or similar.
   Defaults to ``''`` (empty string) and can be any string.
 
+code_language_callback
+  When the HTML code contains ``pre`` tags that in some way provide the code
+  language, for example as class, this callback can be used to extract the
+  language from the tag and prefix it to the converted ``pre`` tag.
+  The callback gets one single argument, an BeautifylSoup object, and returns
+  a string containing the code language, or ``None``.
+  An example to use the class name as code language could be::
+
+    def callback(el):
+        return el['class'][0] if el.has_attr('class') else None
+
+  Defaults to ``None``.
+
 escape_asterisks
   If set to ``False``, do not escape ``*`` to ``\*`` in text.
   Defaults to ``True``.

markdownify/__init__.py

@@ -63,6 +63,7 @@ class MarkdownConverter(object):
         autolinks = True
         bullets = '*+-'  # An iterable of bullet types.
         code_language = ''
+        code_language_callback = None
         convert = None
         default_title = False
         escape_asterisks = True
@@ -335,7 +336,12 @@ class MarkdownConverter(object):
     def convert_pre(self, el, text, convert_as_inline):
         if not text:
             return ''
-        return '\n```%s\n%s\n```\n' % (self.options['code_language'], text)
+        code_language = self.options['code_language']
+
+        if self.options['code_language_callback']:
+            code_language = self.options['code_language_callback'](el) or code_language
+
+        return '\n```%s\n%s\n```\n' % (code_language, text)
 
     convert_s = convert_del
 

tests/test_conversions.py

@@ -216,3 +216,12 @@ def test_sup():
 def test_lang():
     assert md('<pre>test\n    foo\nbar</pre>', code_language='python') == '\n```python\ntest\n    foo\nbar\n```\n'
     assert md('<pre><code>test\n    foo\nbar</code></pre>', code_language='javascript') == '\n```javascript\ntest\n    foo\nbar\n```\n'
+
+
+def test_lang_callback():
+    def callback(el):
+        return el['class'][0] if el.has_attr('class') else None
+
+    assert md('<pre class="python">test\n    foo\nbar</pre>', code_language_callback=callback) == '\n```python\ntest\n    foo\nbar\n```\n'
+    assert md('<pre class="javascript"><code>test\n    foo\nbar</code></pre>', code_language_callback=callback) == '\n```javascript\ntest\n    foo\nbar\n```\n'
+    assert md('<pre class="javascript"><code class="javascript">test\n    foo\nbar</code></pre>', code_language_callback=callback) == '\n```javascript\ntest\n    foo\nbar\n```\n'