Merge branch 'develop'

Add conversion for hr element

.github/workflows/python-app.yml

@@ -0,0 +1,33 @@
+# This workflow will install Python dependencies, run tests and lint with a single version of Python
+# For more information see: https://help.github.com/actions/language-and-framework-guides/using-python-with-github-actions
+
+name: Python application
+
+on:
+  push:
+    branches: [ develop ]
+  pull_request:
+    branches: [ develop ]
+
+jobs:
+  build:
+
+    runs-on: ubuntu-latest
+
+    steps:
+    - uses: actions/checkout@v2
+    - name: Set up Python 3.8
+      uses: actions/setup-python@v2
+      with:
+        python-version: 3.8
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install flake8==3.8.4 pytest
+        if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
+    - name: Lint with flake8
+      run: |
+        python setup.py lint
+    - name: Test with pytest
+      run: |
+        python setup.py test

.github/workflows/python-publish.yml

@@ -0,0 +1,31 @@
+# This workflow will upload a Python Package using Twine when a release is created
+# For more information see: https://help.github.com/en/actions/language-and-framework-guides/using-python-with-github-actions#publishing-to-package-registries
+
+name: Upload Python Package
+
+on:
+  release:
+    types: [created]
+
+jobs:
+  deploy:
+
+    runs-on: ubuntu-latest
+
+    steps:
+    - uses: actions/checkout@v2
+    - name: Set up Python
+      uses: actions/setup-python@v2
+      with:
+        python-version: '3.8'
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install setuptools wheel twine
+    - name: Build and publish
+      env:
+        TWINE_USERNAME: ${{ secrets.PYPI_USERNAME }}
+        TWINE_PASSWORD: ${{ secrets.PYPI_PASSWORD }}
+      run: |
+        python setup.py sdist bdist_wheel
+        twine upload dist/*

.gitignore

@@ -0,0 +1,10 @@
+*.pyc
+*.egg
+.eggs/
+*.egg-info/
+.DS_Store
+/.env
+/dist
+/MANIFEST
+/venv
+build/

LICENSE

@@ -0,0 +1,21 @@
+The MIT License (MIT)
+
+Copyright 2012-2018 Matthew Tretter
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

MANIFEST.in

@@ -0,0 +1 @@
+include README.rst

README.rst

@@ -0,0 +1,103 @@
+|build| |version| |license| |downloads|
+
+.. |build| image:: https://img.shields.io/github/workflow/status/matthewwithanm/python-markdownify/Python%20application/develop
+    :alt: GitHub Workflow Status
+    :target: https://github.com/matthewwithanm/python-markdownify/actions?query=workflow%3A%22Python+application%22
+
+.. |version| image:: https://img.shields.io/pypi/v/markdownify
+    :alt: Pypi version
+    :target: https://pypi.org/project/markdownify/
+
+.. |license| image:: https://img.shields.io/pypi/l/markdownify
+    :alt: License
+    :target: https://github.com/matthewwithanm/python-markdownify/blob/develop/LICENSE
+
+.. |downloads| image:: https://pepy.tech/badge/markdownify
+    :alt: Pypi Downloads
+    :target: https://pepy.tech/project/markdownify
+
+Installation
+============
+
+``pip install markdownify``
+
+
+Usage
+=====
+
+Convert some HTML to Markdown:
+
+.. code:: python
+
+    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):
+
+.. 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):
+
+.. code:: python
+
+    from markdownify import markdownify as md
+    md('<b>Yay</b> <a href="http://github.com">GitHub</a>', convert=['b'])  # > '**Yay** GitHub'
+
+
+Options
+=======
+
+Markdownify supports the following options:
+
+strip
+  A list of tags to strip (blacklist). 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
+  ``strip`` option.
+
+autolinks
+  A boolean indicating whether the "automatic link" style should be used when
+  a ``a`` tag's contents match its href. Defaults to ``True``
+
+heading_style
+  Defines how headings should be converted. Accepted values are ``ATX``,
+  ``ATX_CLOSED``, ``SETEXT``, and ``UNDERLINED`` (which is an alias for
+  ``SETEXT``). Defaults to ``UNDERLINED``.
+
+bullets
+  An iterable (string, list, or tuple) of bullet styles to be used. If the
+  iterable only contains one item, it will be used regardless of how deeply
+  lists are nested. Otherwise, the bullet will alternate based on nesting
+  level. Defaults to ``'*+-'``.
+
+strong_em_symbol
+  In markdown, both ``*`` and ``_`` are used to encode **strong** or
+  *emphasized* texts. Either of these symbols can be chosen by the options
+  ``ASTERISK`` (default) or ``UNDERSCORE`` respectively.
+
+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,
+  while ``BACKSLASH`` will convert a linebreak to ``\\n`` (a backslash an a
+  newline). While the latter convention is non-standard, it is commonly
+  preferred and supported by a lot of interpreters.
+
+Options may be specified as kwargs to the ``markdownify`` function, or as a
+nested ``Options`` class in ``MarkdownConverter`` subclasses.
+
+
+Development
+===========
+
+To run tests:
+
+``python setup.py test``
+
+To lint:
+
+``python setup.py lint``

markdownify/__init__.py

@@ -1,10 +1,27 @@
-from lxml.html.soupparser import fromstring
+from bs4 import BeautifulSoup, NavigableString, Comment
 import re
+import six
 
 
 convert_heading_re = re.compile(r'convert_h(\d+)')
 line_beginning_re = re.compile(r'^', re.MULTILINE)
-whitespace_re = re.compile(r'[\r\n\s\t ]+')
+whitespace_re = re.compile(r'[\t ]+')
+html_heading_re = re.compile(r'h[1-6]')
+
+
+# Heading styles
+ATX = 'atx'
+ATX_CLOSED = 'atx_closed'
+UNDERLINED = 'underlined'
+SETEXT = UNDERLINED
+
+# Newline style
+SPACES = 'spaces'
+BACKSLASH = 'backslash'
+
+# Strong and emphasis style
+ASTERISK = '*'
+UNDERSCORE = '_'
 
 
 def escape(text):
@@ -13,30 +30,72 @@ def escape(text):
     return text.replace('_', r'\_')
 
 
+def chomp(text):
+    """
+    If the text in an inline tag like b, a, or em contains a leading or trailing
+    space, strip the string and return a space as suffix of prefix, if needed.
+    This function is used to prevent conversions like
+        <b> foo</b> => ** foo**
+    """
+    prefix = ' ' if text and text[0] == ' ' else ''
+    suffix = ' ' if text and text[-1] == ' ' else ''
+    text = text.strip()
+    return (prefix, suffix, text)
+
+
+def _todict(obj):
+    return dict((k, getattr(obj, k)) for k in dir(obj) if not k.startswith('_'))
+
+
 class MarkdownConverter(object):
-    def __init__(self, tags_to_strip=None, tags_to_convert=None):
-        if tags_to_strip is not None and tags_to_convert is not None:
+    class DefaultOptions:
+        strip = None
+        convert = None
+        autolinks = True
+        heading_style = UNDERLINED
+        bullets = '*+-'  # An iterable of bullet types.
+        strong_em_symbol = ASTERISK
+        newline_style = SPACES
+
+    class Options(DefaultOptions):
+        pass
+
+    def __init__(self, **options):
+        # Create an options dictionary. Use DefaultOptions as a base so that
+        # it doesn't have to be extended.
+        self.options = _todict(self.DefaultOptions)
+        self.options.update(_todict(self.Options))
+        self.options.update(options)
+        if self.options['strip'] is not None and self.options['convert'] is not None:
             raise ValueError('You may specify either tags to strip or tags to'
-                    ' convert, but not both.')
-        self.tags_to_strip = tags_to_strip
-        self.tags_to_convert = tags_to_convert
+                             ' convert, but not both.')
 
     def convert(self, html):
-        soup = fromstring(html)
-        return self.process_tag(soup)
+        soup = BeautifulSoup(html, 'html.parser')
+        return self.process_tag(soup, convert_as_inline=False, children_only=True)
 
-    def process_tag(self, node):
-        text = self.process_text(node.text)
+    def process_tag(self, node, convert_as_inline, children_only=False):
+        text = ''
+        # markdown headings can't include block elements (elements w/newlines)
+        isHeading = html_heading_re.match(node.name) is not None
+        convert_children_as_inline = convert_as_inline
+
+        if not children_only and isHeading:
+            convert_children_as_inline = True
 
         # Convert the children first
-        for el in node.findall('*'):
-            text += self.process_tag(el)
+        for el in node.children:
+            if isinstance(el, Comment):
+                continue
+            elif isinstance(el, NavigableString):
+                text += self.process_text(six.text_type(el))
+            else:
+                text += self.process_tag(el, convert_children_as_inline)
 
-        convert_fn = getattr(self, 'convert_%s' % node.tag, None)
-        if convert_fn and self.should_convert_tag(node.tag):
-            text = convert_fn(node, text)
-
-        text += self.process_text(node.tail)
+        if not children_only:
+            convert_fn = getattr(self, 'convert_%s' % node.name, None)
+            if convert_fn and self.should_convert_tag(node.name):
+                text = convert_fn(node, text, convert_as_inline)
 
         return text
 
@@ -44,13 +103,13 @@ class MarkdownConverter(object):
         return escape(whitespace_re.sub(' ', text or ''))
 
     def __getattr__(self, attr):
-        # Handle heading levels > 2
+        # Handle headings
         m = convert_heading_re.match(attr)
         if m:
             n = int(m.group(1))
 
-            def convert_tag(el, text):
-                return self.convert_hn(n, el, text)
+            def convert_tag(el, text, convert_as_inline):
+                return self.convert_hn(n, el, text, convert_as_inline)
 
             convert_tag.__name__ = 'convert_h%s' % n
             setattr(self, convert_tag.__name__, convert_tag)
@@ -60,62 +119,159 @@ class MarkdownConverter(object):
 
     def should_convert_tag(self, tag):
         tag = tag.lower()
-        if self.tags_to_strip is not None:
-            return tag not in self.tags_to_strip
-        elif self.tags_to_convert is not None:
-            return tag in self.tags_to_convert
+        strip = self.options['strip']
+        convert = self.options['convert']
+        if strip is not None:
+            return tag not in strip
+        elif convert is not None:
+            return tag in convert
         else:
             return True
 
+    def indent(self, text, level):
+        return line_beginning_re.sub('\t' * level, text) if text else ''
+
     def underline(self, text, pad_char):
         text = (text or '').rstrip()
         return '%s\n%s\n\n' % (text, pad_char * len(text)) if text else ''
 
-    def convert_a(self, el, text):
+    def convert_a(self, el, text, convert_as_inline):
+        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:
+            # Shortcut syntax
+            return '<%s>' % href
         title_part = ' "%s"' % title.replace('"', r'\"') if title else ''
-        return '[%s](%s%s)' % (text or '', href, title_part) if href else text or ''
+        return '%s[%s](%s%s)%s' % (prefix, text, href, title_part, suffix) if href else text
 
-    def convert_b(self, el, text):
-        return self.convert_strong(el, text)
+    def convert_b(self, el, text, convert_as_inline):
+        return self.convert_strong(el, text, convert_as_inline)
 
-    def convert_blockquote(self, el, text):
-        return '\n' + line_beginning_re.sub('> ', text) if text else ''
+    def convert_blockquote(self, el, text, convert_as_inline):
 
-    def convert_br(self, el, text):
-        return '  \n'
+        if convert_as_inline:
+            return text
 
-    def convert_em(self, el, text):
-        return '*%s*' % text if text else ''
+        return '\n' + (line_beginning_re.sub('> ', text) + '\n\n') if text else ''
 
-    def convert_h1(self, el, text):
-        return self.underline(text, '=')
+    def convert_br(self, el, text, convert_as_inline):
+        if convert_as_inline:
+            return ""
 
-    def convert_h2(self, el, text):
-        return self.underline(text, '-')
-
-    def convert_hn(self, n, el, text):
-        return '%s %s\n\n' % ('#' * n, text.rstrip()) if text else ''
-
-    def convert_i(self, el, text):
-        return self.convert_em(el, text)
-
-    def convert_li(self, el, text):
-        parent = el.getparent()
-        if parent is not None and parent.tag == 'ol':
-            bullet = '%s.' % (parent.index(el) + 1)
+        if self.options['newline_style'].lower() == BACKSLASH:
+            return '\\\n'
         else:
-            bullet = '*'
+            return '  \n'
+
+    def convert_em(self, el, text, convert_as_inline):
+        em_tag = self.options['strong_em_symbol']
+        prefix, suffix, text = chomp(text)
+        if not text:
+            return ''
+        return '%s%s%s%s%s' % (prefix, em_tag, text, em_tag, suffix)
+
+    def convert_hn(self, n, el, text, convert_as_inline):
+        if convert_as_inline:
+            return text
+
+        style = self.options['heading_style'].lower()
+        text = text.rstrip()
+        if style == UNDERLINED and n <= 2:
+            line = '=' if n == 1 else '-'
+            return self.underline(text, line)
+        hashes = '#' * n
+        if style == ATX_CLOSED:
+            return '%s %s %s\n\n' % (hashes, text, hashes)
+        return '%s %s\n\n' % (hashes, text)
+
+    def convert_i(self, el, text, convert_as_inline):
+        return self.convert_em(el, text, convert_as_inline)
+
+    def convert_list(self, el, text, convert_as_inline):
+
+        # Converting a list to inline is undefined.
+        # Ignoring convert_to_inline for list.
+
+        nested = False
+        while el:
+            if el.name == 'li':
+                nested = True
+                break
+            el = el.parent
+        if nested:
+            # remove trailing newline if nested
+            return '\n' + self.indent(text, 1).rstrip()
+        return '\n' + text + '\n'
+
+    convert_ul = convert_list
+    convert_ol = convert_list
+
+    def convert_li(self, el, text, convert_as_inline):
+        parent = el.parent
+        if parent is not None and parent.name == 'ol':
+            if parent.get("start"):
+                start = int(parent.get("start"))
+            else:
+                start = 1
+            bullet = '%s.' % (start + parent.index(el))
+        else:
+            depth = -1
+            while el:
+                if el.name == 'ul':
+                    depth += 1
+                el = el.parent
+            bullets = self.options['bullets']
+            bullet = bullets[depth % len(bullets)]
         return '%s %s\n' % (bullet, text or '')
 
-    def convert_p(self, el, text):
+    def convert_p(self, el, text, convert_as_inline):
+        if convert_as_inline:
+            return text
         return '%s\n\n' % text if text else ''
 
-    def convert_strong(self, el, text):
-        return '**%s**' % text if text else ''
+    def convert_strong(self, el, text, convert_as_inline):
+        strong_tag = 2 * self.options['strong_em_symbol']
+        prefix, suffix, text = chomp(text)
+        if not text:
+            return ''
+        return '%s%s%s%s%s' % (prefix, strong_tag, text, strong_tag, suffix)
+
+    def convert_img(self, el, text, convert_as_inline):
+        alt = el.attrs.get('alt', None) or ''
+        src = el.attrs.get('src', None) or ''
+        title = el.attrs.get('title', None) or ''
+        title_part = ' "%s"' % title.replace('"', r'\"') if title else ''
+        if convert_as_inline:
+            return alt
+
+        return '![%s](%s%s)' % (alt, src, title_part)
+
+    def convert_table(self, el, text, convert_as_inline):
+        rows = el.find_all('tr')
+        text_data = []
+        for row in rows:
+            headers = row.find_all('th')
+            columns = row.find_all('td')
+            if len(headers) > 0:
+                headers = [head.text.strip() for head in headers]
+                text_data.append('| ' + ' | '.join(headers) + ' |')
+                text_data.append('| ' + ' | '.join(['---'] * len(headers)) + ' |')
+            elif len(columns) > 0:
+                columns = [colm.text.strip() for colm in columns]
+                text_data.append('| ' + ' | '.join(columns) + ' |')
+            else:
+                continue
+        return '\n'.join(text_data)
+
+    def convert_hr(self, el, text, convert_as_inline):
+        return '\n\n---\n\n'
 
 
-def markdownify(html, strip=None, convert=None):
-    converter = MarkdownConverter(strip, convert)
-    return converter.convert(html)
+def markdownify(html, **options):
+    return MarkdownConverter(**options).convert(html)

markdownify/version.py

@@ -1 +0,0 @@
-__version__ = '0.1.0'

runtests.py

@@ -1,5 +0,0 @@
-#!/usr/bin/env python
-from nose.core import run, collector
-
-if __name__ == '__main__':
-    run()

setup.cfg

@@ -0,0 +1,2 @@
+[flake8]
+ignore = E501

setup.py

@@ -2,43 +2,98 @@
 import codecs
 import os
 from setuptools import setup, find_packages
+from setuptools.command.test import test as TestCommand, Command
 
 
 read = lambda filepath: codecs.open(filepath, 'r', 'utf-8').read()
-execfile(os.path.join(os.path.dirname(__file__), 'markdownify', 'version.py'))
+
+pkgmeta = {
+    '__title__': 'markdownify',
+    '__author__': 'Matthew Tretter',
+    '__version__': '0.7.1',
+}
+
+
+class PyTest(TestCommand):
+    def finalize_options(self):
+        TestCommand.finalize_options(self)
+        self.test_args = ['tests', '-s']
+        self.test_suite = True
+
+    def run_tests(self):
+        import pytest
+        errno = pytest.main(self.test_args)
+        raise SystemExit(errno)
+
+
+class LintCommand(Command):
+    """
+    A copy of flake8's Flake8Command
+
+    """
+    description = "Run flake8 on modules registered in setuptools"
+    user_options = []
+
+    def initialize_options(self):
+        pass
+
+    def finalize_options(self):
+        pass
+
+    def distribution_files(self):
+        if self.distribution.packages:
+            for package in self.distribution.packages:
+                yield package.replace(".", os.path.sep)
+
+        if self.distribution.py_modules:
+            for filename in self.distribution.py_modules:
+                yield "%s.py" % filename
+
+    def run(self):
+        from flake8.api.legacy import get_style_guide
+        flake8_style = get_style_guide(config_file='setup.cfg')
+        paths = self.distribution_files()
+        report = flake8_style.check_files(paths)
+        raise SystemExit(report.total_errors > 0)
 
 
 setup(
-    name='python-markdownify',
+    name='markdownify',
     description='Convert HTML to markdown.',
     long_description=read(os.path.join(os.path.dirname(__file__), 'README.rst')),
-    version=__version__,
-    author='Matthew Tretter',
-    author_email='matthew@exanimo.com',
+    version=pkgmeta['__version__'],
+    author=pkgmeta['__author__'],
+    author_email='m@tthewwithanm.com',
     url='http://github.com/matthewwithanm/python-markdownify',
     download_url='http://github.com/matthewwithanm/python-markdownify/tarball/master',
     packages=find_packages(),
     zip_safe=False,
     include_package_data=True,
+    setup_requires=[
+        'flake8>=3.8,<4',
+    ],
     tests_require=[
-        'nose',
-        'unittest2',
+        'pytest>=6.2,<7',
     ],
     install_requires=[
-        'lxml',
-        'BeautifulSoup',
+        'beautifulsoup4>=4.9,<5', 'six>=1.15,<2'
     ],
     classifiers=[
         'Environment :: Web Environment',
         'Framework :: Django',
         'Intended Audience :: Developers',
-        'License :: OSI Approved :: BSD License',
+        'License :: OSI Approved :: MIT License',
         'Operating System :: OS Independent',
         'Programming Language :: Python :: 2.5',
         'Programming Language :: Python :: 2.6',
         'Programming Language :: Python :: 2.7',
+        'Programming Language :: Python :: 3.6',
+        'Programming Language :: Python :: 3.7',
+        'Programming Language :: Python :: 3.8',
         'Topic :: Utilities'
     ],
-    setup_requires=[],
-    test_suite='runtests.collector',
+    cmdclass={
+        'test': PyTest,
+        'lint': LintCommand,
+    },
 )

tests.py

@@ -1,123 +0,0 @@
-import unittest
-from markdownify import markdownify as md
-
-
-class BasicTests(unittest.TestCase):
-
-    def test_single_tag(self):
-        self.assertEqual(md('<span>Hello</span>'), 'Hello')
-
-    def test_soup(self):
-        self.assertEqual(md('<div><span>Hello</div></span>'), 'Hello')
-
-    def test_whitespace(self):
-        self.assertEqual(md(' a  b \n\n c '), ' a b c ')
-
-
-class ArgTests(unittest.TestCase):
-
-    def test_strip(self):
-        self.assertEqual(
-            md('<a href="https://github.com/matthewwithanm">Some Text</a>', strip=['a']),
-            'Some Text')
-
-    def test_do_not_strip(self):
-        self.assertEqual(
-            md('<a href="https://github.com/matthewwithanm">Some Text</a>', strip=[]),
-            '[Some Text](https://github.com/matthewwithanm)')
-
-    def test_convert(self):
-        self.assertEqual(
-            md('<a href="https://github.com/matthewwithanm">Some Text</a>', convert=['a']),
-            '[Some Text](https://github.com/matthewwithanm)')
-
-    def test_do_not_convert(self):
-        self.assertEqual(
-            md('<a href="https://github.com/matthewwithanm">Some Text</a>', convert=[]),
-            'Some Text')
-
-
-class EscapeTests(unittest.TestCase):
-
-    def test_underscore(self):
-        self.assertEqual(md('_hey_dude_'), '\_hey\_dude\_')
-
-    def test_xml_entities(self):
-        self.assertEqual(md('&amp;'), '&')
-
-    def test_named_entities(self):
-        self.assertEqual(md('&raquo;'), u'\xbb')
-
-    def test_hexadecimal_entities(self):
-        # This looks to be a bug in BeautifulSoup (fixed in bs4) that we have to work around.
-        self.assertEqual(md('&#x27;'), '\x27')
-
-    def test_single_escaping_entities(self):
-        self.assertEqual(md('&amp;amp;'), '&amp;')
-
-
-class ConversionTests(unittest.TestCase):
-
-    def test_a(self):
-        self.assertEqual(
-            md('<a href="http://google.com">Google</a>'),
-            '[Google](http://google.com)'
-        )
-
-    def test_a_with_title(self):
-        self.assertEqual(
-            md('<a href="http://google.com" title="The &quot;Goog&quot;">Google</a>'),
-            r'[Google](http://google.com "The \"Goog\"")'
-        )
-
-    def test_b(self):
-        self.assertEqual(md('<b>Hello</b>'), '**Hello**')
-
-    def test_blockquote(self):
-        self.assertEqual(md('<blockquote>Hello</blockquote>').strip(), '> Hello')
-
-    def test_nested_blockquote(self):
-        self.assertEqual(
-            md('<blockquote>And she was like <blockquote>Hello</blockquote></blockquote>').strip(),
-            '> And she was like \n> > Hello'
-        )
-
-    def test_br(self):
-        self.assertEqual(md('a<br />b<br />c'), 'a  \nb  \nc')
-
-    def test_em(self):
-        self.assertEqual(md('<em>Hello</em>'), '*Hello*')
-
-    def test_h1(self):
-        self.assertEqual(md('<h1>Hello</h1>'), 'Hello\n=====\n\n')
-
-    def test_h2(self):
-        self.assertEqual(md('<h2>Hello</h2>'), 'Hello\n-----\n\n')
-
-    def test_hn(self):
-        self.assertEqual(md('<h3>Hello</h3>'), '### Hello\n\n')
-        self.assertEqual(md('<h6>Hello</h6>'), '###### Hello\n\n')
-
-    def test_i(self):
-        self.assertEqual(md('<i>Hello</i>'), '*Hello*')
-
-    def test_ol(self):
-        self.assertEqual(md('<ol><li>a</li><li>b</li></ol>'), '1. a\n2. b\n')
-
-    def test_p(self):
-        self.assertEqual(md('<p>hello</p>'), 'hello\n\n')
-
-    def test_strong(self):
-        self.assertEqual(md('<strong>Hello</strong>'), '**Hello**')
-
-    def test_ul(self):
-        self.assertEqual(md('<ul><li>a</li><li>b</li></ul>'), '* a\n* b\n')
-
-
-class AdvancedTests(unittest.TestCase):
-
-    def test_nested(self):
-        self.assertEqual(
-            md('<p>This is an <a href="http://example.com/">example link</a>.</p>'),
-            'This is an [example link](http://example.com/).\n\n'
-        )

tests/test_advanced.py

@@ -0,0 +1,16 @@
+from markdownify import markdownify as md
+
+
+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'
+
+
+def test_ignore_comments():
+    text = md("<!-- This is a comment -->")
+    assert text == ""
+
+
+def test_ignore_comments_with_other_tags():
+    text = md("<!-- This is a comment --><a href='http://example.com/'>example link</a>")
+    assert text == "[example link](http://example.com/)"

tests/test_args.py

@@ -0,0 +1,25 @@
+"""
+Test whitelisting/blacklisting of specific tags.
+
+"""
+from markdownify import markdownify as md
+
+
+def test_strip():
+    text = md('<a href="https://github.com/matthewwithanm">Some Text</a>', strip=['a'])
+    assert text == 'Some Text'
+
+
+def test_do_not_strip():
+    text = md('<a href="https://github.com/matthewwithanm">Some Text</a>', strip=[])
+    assert text == '[Some Text](https://github.com/matthewwithanm)'
+
+
+def test_convert():
+    text = md('<a href="https://github.com/matthewwithanm">Some Text</a>', convert=['a'])
+    assert text == '[Some Text](https://github.com/matthewwithanm)'
+
+
+def test_do_not_convert():
+    text = md('<a href="https://github.com/matthewwithanm">Some Text</a>', convert=[])
+    assert text == 'Some Text'

tests/test_basic.py

@@ -0,0 +1,13 @@
+from markdownify import markdownify as md
+
+
+def test_single_tag():
+    assert md('<span>Hello</span>') == 'Hello'
+
+
+def test_soup():
+    assert md('<div><span>Hello</div></span>') == 'Hello'
+
+
+def test_whitespace():
+    assert md(' a  b \t\t c ') == ' a b c '

tests/test_conversions.py

@@ -0,0 +1,311 @@
+from markdownify import markdownify as md, ATX, ATX_CLOSED, BACKSLASH, UNDERSCORE
+import re
+
+
+nested_uls = re.sub(r'\s+', '', """
+    <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>""")
+
+
+table = re.sub(r'\s+', '', """
+<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_head_body = re.sub(r'\s+', '', """
+<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 = re.sub(r'\s+', '', """
+<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>
+""")
+
+
+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_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)'
+
+
+def test_a_spaces():
+    assert md('foo <a href="http://google.com">Google</a> bar') == 'foo [Google](http://google.com) bar'
+    assert md('foo<a href="http://google.com"> Google</a> bar') == 'foo [Google](http://google.com) bar'
+    assert md('foo <a href="http://google.com">Google </a>bar') == 'foo [Google](http://google.com) bar'
+    assert md('foo <a href="http://google.com"></a> bar') == 'foo  bar'
+
+
+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\"")'
+
+
+def test_a_shortcut():
+    text = md('<a href="http://google.com">http://google.com</a>')
+    assert text == '<http://google.com>'
+
+
+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)'
+
+
+def test_b():
+    assert md('<b>Hello</b>') == '**Hello**'
+
+
+def test_b_spaces():
+    assert md('foo <b>Hello</b> bar') == 'foo **Hello** bar'
+    assert md('foo<b> Hello</b> bar') == 'foo **Hello** bar'
+    assert md('foo <b>Hello </b>bar') == 'foo **Hello** bar'
+    assert md('foo <b></b> bar') == 'foo  bar'
+
+
+def test_blockquote():
+    assert md('<blockquote>Hello</blockquote>') == '\n> Hello\n\n'
+
+
+def test_blockquote_with_paragraph():
+    assert md('<blockquote>Hello</blockquote><p>handsome</p>') == '\n> Hello\n\nhandsome\n\n'
+
+
+def test_nested_blockquote():
+    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 test_h1():
+    assert md('<h1>Hello</h1>') == 'Hello\n=====\n\n'
+
+
+def test_h2():
+    assert md('<h2>Hello</h2>') == 'Hello\n-----\n\n'
+
+
+def test_hn():
+    assert md('<h3>Hello</h3>') == '### Hello\n\n'
+    assert md('<h6>Hello</h6>') == '###### Hello\n\n'
+
+
+def test_hn_chained():
+    assert md('<h1>First</h1>\n<h2>Second</h2>\n<h3>Third</h3>', heading_style=ATX) == '# First\n\n\n## Second\n\n\n### Third\n\n'
+    assert md('X<h1>First</h1>', heading_style=ATX) == 'X# First\n\n'
+
+
+def test_hn_nested_tag_heading_style():
+    assert md('<h1>A <p>P</p> C </h1>', heading_style=ATX_CLOSED) == '# A P C #\n\n'
+    assert md('<h1>A <p>P</p> C </h1>', heading_style=ATX) == '# A P C\n\n'
+
+
+def test_hn_nested_simple_tag():
+    tag_to_markdown = [
+        ("strong", "**strong**"),
+        ("b", "**b**"),
+        ("em", "*em*"),
+        ("i", "*i*"),
+        ("p", "p"),
+        ("a", "a"),
+        ("div", "div"),
+        ("blockquote", "blockquote"),
+    ]
+
+    for tag, markdown in tag_to_markdown:
+        assert md('<h3>A <' + tag + '>' + tag + '</' + tag + '> B</h3>') == '### A ' + markdown + ' B\n\n'
+
+    assert md('<h3>A <br>B</h3>', heading_style=ATX) == '### A B\n\n'
+
+    # Nested lists not supported
+    # assert md('<h3>A <ul><li>li1</i><li>l2</li></ul></h3>', heading_style=ATX) == '### A li1 li2 B\n\n'
+
+
+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"),
+        ("alt='Alt Text' title='Optional title'", "Alt Text"),
+    ]
+    for image_attributes, markdown in image_attributes_to_markdown:
+        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_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_i():
+    assert md('<i>Hello</i>') == '*Hello*'
+
+
+def test_ol():
+    assert md('<ol><li>a</li><li>b</li></ol>') == '\n1. a\n2. b\n\n'
+    assert md('<ol start="3"><li>a</li><li>b</li></ol>') == '\n3. a\n4. b\n\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>') == '\n* a\n* b\n\n'
+
+
+def test_inline_ul():
+    assert md('<p>foo</p><ul><li>a</li><li>b</li></ul><p>bar</p>') == 'foo\n\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\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\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_table():
+    assert md(table) == '| Firstname | Lastname | Age |\n| --- | --- | --- |\n| Jill | Smith | 50 |\n| Eve | Jackson | 94 |'
+    assert md(table_head_body) == '| Firstname | Lastname | Age |\n| --- | --- | --- |\n| Jill | Smith | 50 |\n| Eve | Jackson | 94 |'
+    assert md(table_missing_text) == '|  | Lastname | Age |\n| --- | --- | --- |\n| Jill |  | 50 |\n| Eve | Jackson | 94 |'
+
+
+def test_strong_em_symbol():
+    assert md('<strong>Hello</strong>', strong_em_symbol=UNDERSCORE) == '__Hello__'
+    assert md('<b>Hello</b>', strong_em_symbol=UNDERSCORE) == '__Hello__'
+    assert md('<em>Hello</em>', strong_em_symbol=UNDERSCORE) == '_Hello_'
+    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'

tests/test_escaping.py

@@ -0,0 +1,22 @@
+from markdownify import markdownify as md
+
+
+def test_underscore():
+    assert md('_hey_dude_') == r'\_hey\_dude\_'
+
+
+def test_xml_entities():
+    assert md('&') == '&'
+
+
+def test_named_entities():
+    assert md('»') == u'\xbb'
+
+
+def test_hexadecimal_entities():
+    # This looks to be a bug in BeautifulSoup (fixed in bs4) that we have to work around.
+    assert md(''') == '\x27'
+
+
+def test_single_escaping_entities():
+    assert md('&') == '&'