differentiated between text and code language

Fixed issue #52 - added stripping of text to list

.gitignore

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

README.rst

@@ -62,7 +62,11 @@ convert
 
 autolinks
   A boolean indicating whether the "automatic link" style should be used when
-  a ``a`` tag's contents match its href. Defaults to ``True``
+  a ``a`` tag's contents match its href. Defaults to ``True``.
+
+default_title
+  A boolean to enable setting the title of a link to its href, if no title is
+  given. Defaults to ``False``.
 
 heading_style
   Defines how headings should be converted. Accepted values are ``ATX``,
@@ -80,6 +84,11 @@ strong_em_symbol
   *emphasized* texts. Either of these symbols can be chosen by the options
   ``ASTERISK`` (default) or ``UNDERSCORE`` respectively.
 
+sub_symbol, sup_symbol
+  Define the chars that surround ``<sub>`` and ``<sup>`` text. Defaults to an
+  empty string, because this is non-standard behavior. Could be something like
+  ``~`` and ``^`` to result in ``~sub~`` and ``^sup^``.
+
 newline_style
   Defines the style of marking linebreaks (``<br>``) in markdown. The default
   value ``SPACES`` of this option will adopt the usual two spaces and a newline,
@@ -91,6 +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

@@ -1,4 +1,4 @@
-from bs4 import BeautifulSoup, NavigableString, Comment
+from bs4 import BeautifulSoup, NavigableString, Comment, Doctype
 import re
 import six
 
@@ -66,13 +66,17 @@ def _todict(obj):
 
 class MarkdownConverter(object):
     class DefaultOptions:
-        strip = None
-        convert = None
         autolinks = True
-        heading_style = UNDERLINED
         bullets = '*+-'  # An iterable of bullet types.
-        strong_em_symbol = ASTERISK
+        convert = None
+        default_title = False
+        heading_style = UNDERLINED
         newline_style = SPACES
+        strip = None
+        strong_em_symbol = ASTERISK
+        sub_symbol = ''
+        sup_symbol = ''
+        code_language = ''
 
     class Options(DefaultOptions):
         pass
@@ -93,11 +97,14 @@ class MarkdownConverter(object):
 
     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
@@ -124,7 +131,7 @@ class MarkdownConverter(object):
 
         # Convert the children first
         for el in node.children:
-            if isinstance(el, Comment):
+            if isinstance(el, Comment) or isinstance(el, Doctype):
                 continue
             elif isinstance(el, NavigableString):
                 text += self.process_text(el)
@@ -139,22 +146,26 @@ 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'
-                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
@@ -193,14 +204,17 @@ 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
-        if self.options['autolinks'] and text.replace(r'\_', '_') == href and not title:
+        if (self.options['autolinks']
+                and text.replace(r'\_', '_') == href
+                and not title
+                and not self.options['default_title']):
             # Shortcut syntax
             return '<%s>' % href
+        if self.options['default_title'] and not title:
+            title = href
         title_part = ' "%s"' % title.replace('"', r'\"') if title else ''
         return '%s[%s](%s%s)%s' % (prefix, text, href, title_part, suffix) if href else text
 
@@ -301,7 +315,7 @@ 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:
@@ -311,7 +325,7 @@ 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
 
@@ -319,6 +333,10 @@ class MarkdownConverter(object):
 
     convert_samp = convert_code
 
+    convert_sub = abstract_inline_conversion(lambda self: self.options['sub_symbol'])
+
+    convert_sup = abstract_inline_conversion(lambda self: self.options['sup_symbol'])
+
     def convert_table(self, el, text, convert_as_inline):
         return '\n\n' + text + '\n'
 

setup.py

@@ -10,7 +10,7 @@ read = lambda filepath: codecs.open(filepath, 'r', 'utf-8').read()
 pkgmeta = {
     '__title__': 'markdownify',
     '__author__': 'Matthew Tretter',
-    '__version__': '0.8.0',
+    '__version__': '0.9.4',
 }
 
 

tests/test_advanced.py

@@ -1,6 +1,17 @@
 from markdownify import markdownify as md
 
 
+def test_chomp():
+    assert md(' <b></b> ') == '  '
+    assert md(' <b> </b> ') == '  '
+    assert md(' <b>  </b> ') == '  '
+    assert md(' <b>   </b> ') == '  '
+    assert md(' <b>s </b> ') == ' **s**  '
+    assert md(' <b> s</b> ') == '  **s** '
+    assert md(' <b> s </b> ') == '  **s**  '
+    assert md(' <b>  s  </b> ') == '  **s**  '
+
+
 def test_nested():
     text = md('<p>This is an <a href="http://example.com/">example link</a>.</p>')
     assert text == 'This is an [example link](http://example.com/).\n\n'
@@ -21,3 +32,8 @@ def test_code_with_tricky_content():
     assert md('<code>/home/</code><b>username</b>') == "`/home/`**username**"
     assert md('First line <code>blah blah<br />blah blah</code> second line') \
         == "First line `blah blah  \nblah blah` second line"
+
+
+def test_special_tags():
+    assert md('<!DOCTYPE html>') == ''
+    assert md('<![CDATA[foobar]]>') == 'foobar'

tests/test_conversions.py

@@ -1,179 +1,17 @@
 from markdownify import markdownify as md, ATX, ATX_CLOSED, BACKSLASH, UNDERSCORE
 
 
-nested_uls = """
-    <ul>
-        <li>1
-            <ul>
-                <li>a
-                    <ul>
-                        <li>I</li>
-                        <li>II</li>
-                        <li>III</li>
-                    </ul>
-                </li>
-                <li>b</li>
-                <li>c</li>
-            </ul>
-        </li>
-        <li>2</li>
-        <li>3</li>
-    </ul>"""
-
-nested_ols = """
-    <ol>
-        <li>1
-            <ol>
-                <li>a
-                    <ol>
-                        <li>I</li>
-                        <li>II</li>
-                        <li>III</li>
-                    </ol>
-                </li>
-                <li>b</li>
-                <li>c</li>
-            </ol>
-        </li>
-        <li>2</li>
-        <li>3</li>
-    </ul>"""
-
-
-table = """<table>
-    <tr>
-        <th>Firstname</th>
-        <th>Lastname</th>
-        <th>Age</th>
-    </tr>
-    <tr>
-        <td>Jill</td>
-        <td>Smith</td>
-        <td>50</td>
-    </tr>
-    <tr>
-        <td>Eve</td>
-        <td>Jackson</td>
-        <td>94</td>
-    </tr>
-</table>"""
-
-
-table_with_html_content = """<table>
-    <tr>
-        <th>Firstname</th>
-        <th>Lastname</th>
-        <th>Age</th>
-    </tr>
-    <tr>
-        <td><b>Jill</b></td>
-        <td><i>Smith</i></td>
-        <td><a href="#">50</a></td>
-    </tr>
-    <tr>
-        <td>Eve</td>
-        <td>Jackson</td>
-        <td>94</td>
-    </tr>
-</table>"""
-
-
-table_with_header_column = """<table>
-    <tr>
-        <th>Firstname</th>
-        <th>Lastname</th>
-        <th>Age</th>
-    </tr>
-    <tr>
-        <th>Jill</th>
-        <td>Smith</td>
-        <td>50</td>
-    </tr>
-    <tr>
-        <th>Eve</th>
-        <td>Jackson</td>
-        <td>94</td>
-    </tr>
-</table>"""
-
-
-table_head_body = """<table>
-    <thead>
-        <tr>
-            <th>Firstname</th>
-            <th>Lastname</th>
-            <th>Age</th>
-        </tr>
-    </thead>
-    <tbody>
-        <tr>
-            <td>Jill</td>
-            <td>Smith</td>
-            <td>50</td>
-        </tr>
-        <tr>
-            <td>Eve</td>
-            <td>Jackson</td>
-            <td>94</td>
-        </tr>
-    </tbody>
-</table>"""
-
-table_missing_text = """<table>
-    <thead>
-        <tr>
-            <th></th>
-            <th>Lastname</th>
-            <th>Age</th>
-        </tr>
-    </thead>
-    <tbody>
-        <tr>
-            <td>Jill</td>
-            <td></td>
-            <td>50</td>
-        </tr>
-        <tr>
-            <td>Eve</td>
-            <td>Jackson</td>
-            <td>94</td>
-        </tr>
-    </tbody>
-</table>"""
-
-table_missing_head = """<table>
-    <tr>
-        <td>Firstname</td>
-        <td>Lastname</td>
-        <td>Age</td>
-    </tr>
-    <tr>
-        <td>Jill</td>
-        <td>Smith</td>
-        <td>50</td>
-    </tr>
-    <tr>
-        <td>Eve</td>
-        <td>Jackson</td>
-        <td>94</td>
-    </tr>
-</table>"""
-
-
-def test_chomp():
-    assert md(' <b></b> ') == '  '
-    assert md(' <b> </b> ') == '  '
-    assert md(' <b>  </b> ') == '  '
-    assert md(' <b>   </b> ') == '  '
-    assert md(' <b>s </b> ') == ' **s**  '
-    assert md(' <b> s</b> ') == '  **s** '
-    assert md(' <b> s </b> ') == '  **s**  '
-    assert md(' <b>  s  </b> ') == '  **s**  '
+def inline_tests(tag, markup):
+    # test template for different inline tags
+    assert md(f'<{tag}>Hello</{tag}>') == f'{markup}Hello{markup}'
+    assert md(f'foo <{tag}>Hello</{tag}> bar') == f'foo {markup}Hello{markup} bar'
+    assert md(f'foo<{tag}> Hello</{tag}> bar') == f'foo {markup}Hello{markup} bar'
+    assert md(f'foo <{tag}>Hello </{tag}>bar') == f'foo {markup}Hello{markup} bar'
+    assert md(f'foo <{tag}></{tag}> bar') in ['foo  bar', 'foo bar']  # Either is OK
 
 
 def test_a():
     assert md('<a href="https://google.com">Google</a>') == '[Google](https://google.com)'
-    assert md('<a href="https://google.com">https://google.com</a>', autolinks=False) == '[https://google.com](https://google.com)'
     assert md('<a href="https://google.com">https://google.com</a>') == '<https://google.com>'
     assert md('<a href="https://community.kde.org/Get_Involved">https://community.kde.org/Get_Involved</a>') == '<https://community.kde.org/Get_Involved>'
     assert md('<a href="https://community.kde.org/Get_Involved">https://community.kde.org/Get_Involved</a>', autolinks=False) == '[https://community.kde.org/Get\\_Involved](https://community.kde.org/Get_Involved)'
@@ -189,6 +27,7 @@ def test_a_spaces():
 def test_a_with_title():
     text = md('<a href="http://google.com" title="The &quot;Goog&quot;">Google</a>')
     assert text == r'[Google](http://google.com "The \"Goog\"")'
+    assert md('<a href="https://google.com">https://google.com</a>', default_title=True) == '[https://google.com](https://google.com "https://google.com")'
 
 
 def test_a_shortcut():
@@ -197,8 +36,7 @@ def test_a_shortcut():
 
 
 def test_a_no_autolinks():
-    text = md('<a href="http://google.com">http://google.com</a>', autolinks=False)
-    assert text == '[http://google.com](http://google.com)'
+    assert md('<a href="https://google.com">https://google.com</a>', autolinks=False) == '[https://google.com](https://google.com)'
 
 
 def test_b():
@@ -220,58 +58,31 @@ def test_blockquote_with_paragraph():
     assert md('<blockquote>Hello</blockquote><p>handsome</p>') == '\n> Hello\n\nhandsome\n\n'
 
 
-def test_nested_blockquote():
+def test_blockquote_nested():
     text = md('<blockquote>And she was like <blockquote>Hello</blockquote></blockquote>')
     assert text == '\n> And she was like \n> > Hello\n> \n> \n\n'
 
 
 def test_br():
     assert md('a<br />b<br />c') == 'a  \nb  \nc'
-
-
-def test_em():
-    assert md('<em>Hello</em>') == '*Hello*'
-
-
-def test_em_spaces():
-    assert md('foo <em>Hello</em> bar') == 'foo *Hello* bar'
-    assert md('foo<em> Hello</em> bar') == 'foo *Hello* bar'
-    assert md('foo <em>Hello </em>bar') == 'foo *Hello* bar'
-    assert md('foo <em></em> bar') == 'foo  bar'
-
-
-def inline_tests(tag, markup):
-    # Basically re-use test_em() and test_em_spaces(),
-    assert md(f'<{tag}>Hello</{tag}>') == f'{markup}Hello{markup}'
-    assert md(f'foo <{tag}>Hello</{tag}> bar') == f'foo {markup}Hello{markup} bar'
-    assert md(f'foo<{tag}> Hello</{tag}> bar') == f'foo {markup}Hello{markup} bar'
-    assert md(f'foo <{tag}>Hello </{tag}>bar') == f'foo {markup}Hello{markup} bar'
-    assert md(f'foo <{tag}></{tag}> bar') in ['foo  bar', 'foo bar']  # Either is OK
+    assert md('a<br />b<br />c', newline_style=BACKSLASH) == 'a\\\nb\\\nc'
 
 
 def test_code():
     inline_tests('code', '`')
-
-
-def test_samp():
-    inline_tests('samp', '`')
-
-
-def test_kbd():
-    inline_tests('kbd', '`')
-
-
-def test_pre():
-    assert md('<pre>test\n    foo\nbar</pre>') == '\n```\ntest\n    foo\nbar\n```\n'
-    assert md('<pre><code>test\n    foo\nbar</code></pre>') == '\n```\ntest\n    foo\nbar\n```\n'
+    assert md('<code>this_should_not_escape</code>') == '`this_should_not_escape`'
 
 
 def test_del():
     inline_tests('del', '~~')
 
 
-def test_s():
-    inline_tests('s', '~~')
+def test_div():
+    assert md('Hello</div> World') == 'Hello World'
+
+
+def test_em():
+    inline_tests('em', '*')
 
 
 def test_h1():
@@ -284,6 +95,8 @@ def test_h2():
 
 def test_hn():
     assert md('<h3>Hello</h3>') == '### Hello\n\n'
+    assert md('<h4>Hello</h4>') == '#### Hello\n\n'
+    assert md('<h5>Hello</h5>') == '##### Hello\n\n'
     assert md('<h6>Hello</h6>') == '###### Hello\n\n'
 
 
@@ -319,8 +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"),
@@ -330,87 +141,58 @@ def test_hn_nested_img():
         assert md('<h3>A <img src="/path/to/img.jpg " ' + image_attributes + '/> B</h3>') == '### A ' + markdown + ' B\n\n'
 
 
-def test_hr():
-    assert md('Hello<hr>World') == 'Hello\n\n---\n\nWorld'
-    assert md('Hello<hr />World') == 'Hello\n\n---\n\nWorld'
-    assert md('<p>Hello</p>\n<hr>\n<p>World</p>') == 'Hello\n\n\n\n\n---\n\n\nWorld\n\n'
+def test_hn_atx_headings():
+    assert md('<h1>Hello</h1>', heading_style=ATX) == '# Hello\n\n'
+    assert md('<h2>Hello</h2>', heading_style=ATX) == '## Hello\n\n'
+
+
+def test_hn_atx_closed_headings():
+    assert md('<h1>Hello</h1>', heading_style=ATX_CLOSED) == '# Hello #\n\n'
+    assert md('<h2>Hello</h2>', heading_style=ATX_CLOSED) == '## Hello ##\n\n'
 
 
 def test_head():
     assert md('<head>head</head>') == 'head'
 
 
-def test_atx_headings():
-    assert md('<h1>Hello</h1>', heading_style=ATX) == '# Hello\n\n'
-    assert md('<h2>Hello</h2>', heading_style=ATX) == '## Hello\n\n'
-
-
-def test_atx_closed_headings():
-    assert md('<h1>Hello</h1>', heading_style=ATX_CLOSED) == '# Hello #\n\n'
-    assert md('<h2>Hello</h2>', heading_style=ATX_CLOSED) == '## Hello ##\n\n'
+def test_hr():
+    assert md('Hello<hr>World') == 'Hello\n\n---\n\nWorld'
+    assert md('Hello<hr />World') == 'Hello\n\n---\n\nWorld'
+    assert md('<p>Hello</p>\n<hr>\n<p>World</p>') == 'Hello\n\n\n\n\n---\n\n\nWorld\n\n'
 
 
 def test_i():
     assert md('<i>Hello</i>') == '*Hello*'
 
 
-def test_ol():
-    assert md('<ol><li>a</li><li>b</li></ol>') == '1. a\n2. b\n'
-    assert md('<ol start="3"><li>a</li><li>b</li></ol>') == '3. a\n4. b\n'
-
-
-def test_p():
-    assert md('<p>hello</p>') == 'hello\n\n'
-
-
-def test_strong():
-    assert md('<strong>Hello</strong>') == '**Hello**'
-
-
-def test_ul():
-    assert md('<ul><li>a</li><li>b</li></ul>') == '* a\n* b\n'
-
-
-def test_nested_ols():
-    assert md(nested_ols) == '\n1. 1\n\t1. a\n\t\t1. I\n\t\t2. II\n\t\t3. III\n\t2. b\n\t3. c\n2. 2\n3. 3\n'
-
-
-def test_inline_ul():
-    assert md('<p>foo</p><ul><li>a</li><li>b</li></ul><p>bar</p>') == 'foo\n\n* a\n* b\n\nbar\n\n'
-
-
-def test_nested_uls():
-    """
-    Nested ULs should alternate bullet characters.
-
-    """
-    assert md(nested_uls) == '\n* 1\n\t+ a\n\t\t- I\n\t\t- II\n\t\t- III\n\t+ b\n\t+ c\n* 2\n* 3\n'
-
-
-def test_bullets():
-    assert md(nested_uls, bullets='-') == '\n- 1\n\t- a\n\t\t- I\n\t\t- II\n\t\t- III\n\t- b\n\t- c\n- 2\n- 3\n'
-
-
-def test_li_text():
-    assert md('<ul><li>foo <a href="#">bar</a></li><li>foo bar  </li><li>foo <b>bar</b>   <i>space</i>.</ul>') == '* foo [bar](#)\n* foo bar\n* foo **bar** *space*.\n'
-
-
 def test_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)'
 
 
-def test_div():
-    assert md('Hello</div> World') == 'Hello World'
+def test_kbd():
+    inline_tests('kbd', '`')
 
 
-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_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'
-    assert md(table_missing_head) == '\n\n|  |  |  |\n| --- | --- | --- |\n| Firstname | Lastname | Age |\n| Jill | Smith | 50 |\n| Eve | Jackson | 94 |\n\n'
+def test_p():
+    assert md('<p>hello</p>') == 'hello\n\n'
+
+
+def test_pre():
+    assert md('<pre>test\n    foo\nbar</pre>') == '\n```\ntest\n    foo\nbar\n```\n'
+    assert md('<pre><code>test\n    foo\nbar</code></pre>') == '\n```\ntest\n    foo\nbar\n```\n'
+
+
+def test_s():
+    inline_tests('s', '~~')
+
+
+def test_samp():
+    inline_tests('samp', '`')
+
+
+def test_strong():
+    assert md('<strong>Hello</strong>') == '**Hello**'
 
 
 def test_strong_em_symbol():
@@ -420,5 +202,16 @@ def test_strong_em_symbol():
     assert md('<i>Hello</i>', strong_em_symbol=UNDERSCORE) == '_Hello_'
 
 
-def test_newline_style():
-    assert md('a<br />b<br />c', newline_style=BACKSLASH) == 'a\\\nb\\\nc'
+def test_sub():
+    assert md('<sub>foo</sub>') == 'foo'
+    assert md('<sub>foo</sub>', sub_symbol='~') == '~foo~'
+
+
+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 +1,18 @@
+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'

tests/test_lists.py

@@ -0,0 +1,81 @@
+from markdownify import markdownify as md
+
+
+nested_uls = """
+    <ul>
+        <li>1
+            <ul>
+                <li>a
+                    <ul>
+                        <li>I</li>
+                        <li>II</li>
+                        <li>III</li>
+                    </ul>
+                </li>
+                <li>b</li>
+                <li>c</li>
+            </ul>
+        </li>
+        <li>2</li>
+        <li>3</li>
+    </ul>"""
+
+nested_ols = """
+    <ol>
+        <li>1
+            <ol>
+                <li>a
+                    <ol>
+                        <li>I</li>
+                        <li>II</li>
+                        <li>III</li>
+                    </ol>
+                </li>
+                <li>b</li>
+                <li>c</li>
+            </ol>
+        </li>
+        <li>2</li>
+        <li>3</li>
+    </ul>"""
+
+
+def test_ol():
+    assert md('<ol><li>a</li><li>b</li></ol>') == '1. a\n2. b\n'
+    assert md('<ol start="3"><li>a</li><li>b</li></ol>') == '3. a\n4. b\n'
+
+
+def test_nested_ols():
+    assert md(nested_ols) == '\n1. 1\n\t1. a\n\t\t1. I\n\t\t2. II\n\t\t3. III\n\t2. b\n\t3. c\n2. 2\n3. 3\n'
+
+
+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():
+    assert md('<p>foo</p><ul><li>a</li><li>b</li></ul><p>bar</p>') == 'foo\n\n* a\n* b\n\nbar\n\n'
+
+
+def test_nested_uls():
+    """
+    Nested ULs should alternate bullet characters.
+
+    """
+    assert md(nested_uls) == '\n* 1\n\t+ a\n\t\t- I\n\t\t- II\n\t\t- III\n\t+ b\n\t+ c\n* 2\n* 3\n'
+
+
+def test_bullets():
+    assert md(nested_uls, bullets='-') == '\n- 1\n\t- a\n\t\t- I\n\t\t- II\n\t\t- III\n\t- b\n\t- c\n- 2\n- 3\n'
+
+
+def test_li_text():
+    assert md('<ul><li>foo <a href="#">bar</a></li><li>foo bar  </li><li>foo <b>bar</b>   <i>space</i>.</ul>') == '* foo [bar](#)\n* foo bar\n* foo **bar** *space*.\n'

tests/test_tables.py

@@ -0,0 +1,150 @@
+from markdownify import markdownify as md
+
+
+table = """<table>
+    <tr>
+        <th>Firstname</th>
+        <th>Lastname</th>
+        <th>Age</th>
+    </tr>
+    <tr>
+        <td>Jill</td>
+        <td>Smith</td>
+        <td>50</td>
+    </tr>
+    <tr>
+        <td>Eve</td>
+        <td>Jackson</td>
+        <td>94</td>
+    </tr>
+</table>"""
+
+
+table_with_html_content = """<table>
+    <tr>
+        <th>Firstname</th>
+        <th>Lastname</th>
+        <th>Age</th>
+    </tr>
+    <tr>
+        <td><b>Jill</b></td>
+        <td><i>Smith</i></td>
+        <td><a href="#">50</a></td>
+    </tr>
+    <tr>
+        <td>Eve</td>
+        <td>Jackson</td>
+        <td>94</td>
+    </tr>
+</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>
+        <th>Lastname</th>
+        <th>Age</th>
+    </tr>
+    <tr>
+        <th>Jill</th>
+        <td>Smith</td>
+        <td>50</td>
+    </tr>
+    <tr>
+        <th>Eve</th>
+        <td>Jackson</td>
+        <td>94</td>
+    </tr>
+</table>"""
+
+
+table_head_body = """<table>
+    <thead>
+        <tr>
+            <th>Firstname</th>
+            <th>Lastname</th>
+            <th>Age</th>
+        </tr>
+    </thead>
+    <tbody>
+        <tr>
+            <td>Jill</td>
+            <td>Smith</td>
+            <td>50</td>
+        </tr>
+        <tr>
+            <td>Eve</td>
+            <td>Jackson</td>
+            <td>94</td>
+        </tr>
+    </tbody>
+</table>"""
+
+table_missing_text = """<table>
+    <thead>
+        <tr>
+            <th></th>
+            <th>Lastname</th>
+            <th>Age</th>
+        </tr>
+    </thead>
+    <tbody>
+        <tr>
+            <td>Jill</td>
+            <td></td>
+            <td>50</td>
+        </tr>
+        <tr>
+            <td>Eve</td>
+            <td>Jackson</td>
+            <td>94</td>
+        </tr>
+    </tbody>
+</table>"""
+
+table_missing_head = """<table>
+    <tr>
+        <td>Firstname</td>
+        <td>Lastname</td>
+        <td>Age</td>
+    </tr>
+    <tr>
+        <td>Jill</td>
+        <td>Smith</td>
+        <td>50</td>
+    </tr>
+    <tr>
+        <td>Eve</td>
+        <td>Jackson</td>
+        <td>94</td>
+    </tr>
+</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'
+    assert md(table_missing_head) == '\n\n|  |  |  |\n| --- | --- | --- |\n| Firstname | Lastname | Age |\n| Jill | Smith | 50 |\n| Eve | Jackson | 94 |\n\n'