Merge branch 'develop'

closes #59

.gitignore

@@ -8,3 +8,4 @@
 /MANIFEST
 /venv
 build/
+.vscode/settings.json

README.rst

@@ -32,14 +32,14 @@ Convert some HTML to Markdown:
     from markdownify import markdownify as md
     md('<b>Yay</b> <a href="http://github.com">GitHub</a>')  # > '**Yay** [GitHub](http://github.com)'
 
-Specify tags to exclude (blacklist):
+Specify tags to exclude:
 
 .. code:: python
 
     from markdownify import markdownify as md
     md('<b>Yay</b> <a href="http://github.com">GitHub</a>', strip=['a'])  # > '**Yay** GitHub'
 
-\...or specify the tags you want to include (whitelist):
+\...or specify the tags you want to include:
 
 .. code:: python
 
@@ -53,11 +53,11 @@ Options
 Markdownify supports the following options:
 
 strip
-  A list of tags to strip (blacklist). This option can't be used with the
+  A list of tags to strip. This option can't be used with the
   ``convert`` option.
 
 convert
-  A list of tags to convert (whitelist). This option can't be used with the
+  A list of tags to convert. This option can't be used with the
   ``strip`` option.
 
 autolinks
@@ -96,10 +96,55 @@ newline_style
   newline). While the latter convention is non-standard, it is commonly
   preferred and supported by a lot of interpreters.
 
+code_language
+  Defines the language that should be assumed for all ``<pre>`` sections.
+  Useful, if all code on a page is in the same programming language and
+  should be annotated with `````python`` or similar.
+  Defaults to ``''`` (empty string) and can be any string.
+
+escape_underscores
+  If set to ``False``, do not escape ``_`` to ``\_`` in text.
+  Defaults to ``True``.
+
 Options may be specified as kwargs to the ``markdownify`` function, or as a
 nested ``Options`` class in ``MarkdownConverter`` subclasses.
 
 
+Converting BeautifulSoup objects
+================================
+
+.. code:: python
+
+    from markdownify import MarkdownConverter
+
+    # Create shorthand method for conversion
+    def md(soup, **options):
+        return ImageBlockConverter(**options).convert_soup(soup)
+
+
+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

@@ -25,10 +25,12 @@ ASTERISK = '*'
 UNDERSCORE = '_'
 
 
-def escape(text):
+def escape(text, escape_underscores):
     if not text:
         return ''
-    return text.replace('_', r'\_')
+    if escape_underscores:
+        return text.replace('_', r'\_')
+    return text
 
 
 def chomp(text):
@@ -68,8 +70,10 @@ class MarkdownConverter(object):
     class DefaultOptions:
         autolinks = True
         bullets = '*+-'  # An iterable of bullet types.
+        code_language = ''
         convert = None
         default_title = False
+        escape_underscores = True
         heading_style = UNDERLINED
         newline_style = SPACES
         strip = None
@@ -92,15 +96,21 @@ class MarkdownConverter(object):
 
     def convert(self, html):
         soup = BeautifulSoup(html, 'html.parser')
+        return self.convert_soup(soup)
+
+    def convert_soup(self, soup):
         return self.process_tag(soup, convert_as_inline=False, children_only=True)
 
     def process_tag(self, node, convert_as_inline, children_only=False):
         text = ''
-        # markdown headings can't include block elements (elements w/newlines)
+
+        # markdown headings or cells can't include
+        # block elements (elements w/newlines)
         isHeading = html_heading_re.match(node.name) is not None
+        isCell = node.name in ['td', 'th']
         convert_children_as_inline = convert_as_inline
 
-        if not children_only and isHeading:
+        if not children_only and (isHeading or isCell):
             convert_children_as_inline = True
 
         # Remove whitespace-only textnodes in purely nested nodes
@@ -142,22 +152,26 @@ class MarkdownConverter(object):
         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'
+        if not (el.parent.name == 'pre'
-                or (el.parent.name == 'code' and el.parent.parent.name == 'pre')):
+                or (el.parent.name == 'code'
-            return escape(text or '')
+                    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, self.options['escape_underscores'])
 
         # 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']):
+        if (el.parent.name == 'li'
-            return cleaned_text.rstrip()
+                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
@@ -196,8 +210,6 @@ class MarkdownConverter(object):
         prefix, suffix, text = chomp(text)
         if not text:
             return ''
-        if convert_as_inline:
-            return text
         href = el.get('href')
         title = el.get('title')
         # For the replacement see #29: text nodes underscores are escaped
@@ -309,7 +321,7 @@ class MarkdownConverter(object):
                 el = el.parent
             bullets = self.options['bullets']
             bullet = bullets[depth % len(bullets)]
-        return '%s %s\n' % (bullet, text or '')
+        return '%s %s\n' % (bullet, (text or '').strip())
 
     def convert_p(self, el, text, convert_as_inline):
         if convert_as_inline:
@@ -319,7 +331,7 @@ class MarkdownConverter(object):
     def convert_pre(self, el, text, convert_as_inline):
         if not text:
             return ''
-        return '\n```\n%s\n```\n' % text
+        return '\n```%s\n%s\n```\n' % (self.options['code_language'], text)
 
     convert_s = convert_del
 

setup.py

@@ -10,7 +10,7 @@ read = lambda filepath: codecs.open(filepath, 'r', 'utf-8').read()
 pkgmeta = {
     '__title__': 'markdownify',
     '__author__': 'Matthew Tretter',
-    '__version__': '0.9.0',
+    '__version__': '0.10.3',
 }
 
 
@@ -70,7 +70,7 @@ setup(
     zip_safe=False,
     include_package_data=True,
     setup_requires=[
-        'flake8>=3.8,<4',
+        'flake8>=3.8,<5',
     ],
     tests_require=[
         'pytest>=6.2,<7',

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"),
@@ -211,3 +210,8 @@ def test_sub():
 def test_sup():
     assert md('<sup>foo</sup>') == 'foo'
     assert md('<sup>foo</sup>', sup_symbol='^') == '^foo^'
+
+
+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'

tests/test_custom_converter.py

@@ -0,0 +1,25 @@
+from markdownify import MarkdownConverter
+from bs4 import BeautifulSoup
+
+
+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'
+
+
+def test_soup():
+    html = '<b>test</b>'
+    soup = BeautifulSoup(html, 'html.parser')
+    assert MarkdownConverter().convert_soup(soup) == '**test**'

tests/test_escaping.py

@@ -3,6 +3,7 @@ from markdownify import markdownify as md
 
 def test_underscore():
     assert md('_hey_dude_') == r'\_hey\_dude\_'
+    assert md('_hey_dude_', escape_underscores=False) == r'_hey_dude_'
 
 
 def test_xml_entities():

tests/test_lists.py

@@ -51,6 +51,14 @@ def test_nested_ols():
 
 def test_ul():
     assert md('<ul><li>a</li><li>b</li></ul>') == '* a\n* b\n'
+    assert md("""<ul>
+     <li>
+             a
+     </li>
+     <li> b </li>
+     <li>   c
+     </li>
+ </ul>""") == '* a\n* b\n* c\n'
 
 
 def test_inline_ul():

tests/test_tables.py

@@ -39,6 +39,25 @@ table_with_html_content = """<table>
 </table>"""
 
 
+table_with_paragraphs = """<table>
+    <tr>
+        <th>Firstname</th>
+        <th><p>Lastname</p></th>
+        <th>Age</th>
+    </tr>
+    <tr>
+        <td><p>Jill</p></td>
+        <td><p>Smith</p></td>
+        <td><p>50</p></td>
+    </tr>
+    <tr>
+        <td>Eve</td>
+        <td>Jackson</td>
+        <td>94</td>
+    </tr>
+</table>"""
+
+
 table_with_header_column = """<table>
     <tr>
         <th>Firstname</th>
@@ -124,6 +143,7 @@ table_missing_head = """<table>
 def test_table():
     assert md(table) == '\n\n| Firstname | Lastname | Age |\n| --- | --- | --- |\n| Jill | Smith | 50 |\n| Eve | Jackson | 94 |\n\n'
     assert md(table_with_html_content) == '\n\n| Firstname | Lastname | Age |\n| --- | --- | --- |\n| **Jill** | *Smith* | [50](#) |\n| Eve | Jackson | 94 |\n\n'
+    assert md(table_with_paragraphs) == '\n\n| Firstname | Lastname | Age |\n| --- | --- | --- |\n| Jill | Smith | 50 |\n| Eve | Jackson | 94 |\n\n'
     assert md(table_with_header_column) == '\n\n| Firstname | Lastname | Age |\n| --- | --- | --- |\n| Jill | Smith | 50 |\n| Eve | Jackson | 94 |\n\n'
     assert md(table_head_body) == '\n\n| Firstname | Lastname | Age |\n| --- | --- | --- |\n| Jill | Smith | 50 |\n| Eve | Jackson | 94 |\n\n'
     assert md(table_missing_text) == '\n\n|  | Lastname | Age |\n| --- | --- | --- |\n| Jill |  | 50 |\n| Eve | Jackson | 94 |\n\n'