Bump version 0.5.1

Create python-publish.yml

.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.x'
+    - 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

@@ -1,7 +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.

README.rst

@@ -27,3 +27,47 @@ Specify tags to exclude (blacklist):
 
     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 ``'*+-'``.
+
+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 +1,20 @@
-from lxml.html.soupparser import fromstring
+from bs4 import BeautifulSoup, NavigableString
 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 ]+')
+FRAGMENT_ID = '__MARKDOWNIFY_WRAPPER__'
+wrapped = '<div id="%s">%%s</div>' % FRAGMENT_ID
+
+
+# Heading styles
+ATX = 'atx'
+ATX_CLOSED = 'atx_closed'
+UNDERLINED = 'underlined'
+SETEXT = UNDERLINED
 
 
 def escape(text):
@@ -13,30 +23,66 @@ 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.
+
+    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)
+        # We want to take advantage of the html5 parsing, but we don't actually
+        # want a full document. Therefore, we'll mark our fragment with an id,
+        # create the document, and extract the element with the id.
+        html = wrapped % html
+        soup = BeautifulSoup(html, 'html.parser')
+        return self.process_tag(soup.find(id=FRAGMENT_ID), children_only=True)
 
-    def process_tag(self, node):
-        text = self.process_text(node.text)
+    def process_tag(self, node, children_only=False):
+        text = ''
 
         # Convert the children first
-        for el in node.findall('*'):
-            text += self.process_tag(el)
+        for el in node.children:
+            if isinstance(el, NavigableString):
+                text += self.process_text(six.text_type(el))
+            else:
+                text += self.process_tag(el)
 
-        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)
 
         return text
 
@@ -44,7 +90,7 @@ 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))
@@ -60,22 +106,33 @@ 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):
+        prefix, suffix, text = chomp(text)
+        if not text:
+            return ''
         href = el.get('href')
         title = el.get('title')
+        if self.options['autolinks'] and text == 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)
@@ -87,35 +144,70 @@ class MarkdownConverter(object):
         return '  \n'
 
     def convert_em(self, el, text):
-        return '*%s*' % text if text else ''
-
-    def convert_h1(self, el, text):
-        return self.underline(text, '=')
-
-    def convert_h2(self, el, text):
-        return self.underline(text, '-')
+        prefix, suffix, text = chomp(text)
+        if not text:
+            return ''
+        return '%s*%s*%s' % (prefix, text, suffix)
 
     def convert_hn(self, n, el, text):
-        return '%s %s\n\n' % ('#' * n, text.rstrip()) if text else ''
+        style = self.options['heading_style']
+        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):
         return self.convert_em(el, text)
 
+    def convert_list(self, el, text):
+        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):
-        parent = el.getparent()
-        if parent is not None and parent.tag == 'ol':
+        parent = el.parent
+        if parent is not None and parent.name == 'ol':
             bullet = '%s.' % (parent.index(el) + 1)
         else:
-            bullet = '*'
+            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):
         return '%s\n\n' % text if text else ''
 
     def convert_strong(self, el, text):
-        return '**%s**' % text if text else ''
+        prefix, suffix, text = chomp(text)
+        if not text:
+            return ''
+        return '%s**%s**%s' % (prefix, text, suffix)
+
+    def convert_img(self, el, text):
+        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 ''
+        return '![%s](%s%s)' % (alt, src, title_part)
 
 
-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/pkgmeta.py

@@ -1,8 +0,0 @@
-pkgmeta = dict(
-    __title__='markdownify',
-    __author__='Matthew Tretter',
-    __version__='0.2.0',
-)
-
-globals().update(pkgmeta)
-__all__ = pkgmeta.keys()

setup.cfg

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

setup.py

@@ -2,15 +2,16 @@
 import codecs
 import os
 from setuptools import setup, find_packages
-from setuptools.command.test import test as TestCommand
+from setuptools.command.test import test as TestCommand, Command
 
 
 read = lambda filepath: codecs.open(filepath, 'r', 'utf-8').read()
 
-
-pkgmeta = {}
-execfile(os.path.join(os.path.dirname(__file__), 'markdownify', 'pkgmeta.py'),
-         pkgmeta)
+pkgmeta = {
+    '__title__': 'markdownify',
+    '__author__': 'Matthew Tretter',
+    '__version__': '0.5.1',
+}
 
 
 class PyTest(TestCommand):
@@ -25,6 +26,37 @@ class PyTest(TestCommand):
         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.engine 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='markdownify',
     description='Convert HTML to markdown.',
@@ -37,26 +69,28 @@ setup(
     packages=find_packages(),
     zip_safe=False,
     include_package_data=True,
+    setup_requires=[
+        'flake8',
+    ],
     tests_require=[
         'pytest',
     ],
     install_requires=[
-        'lxml',
-        'BeautifulSoup',
+        'beautifulsoup4', 'six'
     ],
     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',
         'Topic :: Utilities'
     ],
-    setup_requires=[],
     cmdclass={
         'test': PyTest,
+        'lint': LintCommand,
     },
 )

tests/test_conversions.py

@@ -1,19 +1,75 @@
-from markdownify import markdownify as md
+from markdownify import markdownify as md, ATX, ATX_CLOSED
+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>""")
+
+
+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="http://google.com">Google</a>') == '[Google](http://google.com)'
 
 
+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>').strip() == '> Hello'
 
@@ -31,6 +87,13 @@ 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'
 
@@ -44,12 +107,22 @@ def test_hn():
     assert md('<h6>Hello</h6>') == '###### Hello\n\n'
 
 
+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>') == '1. a\n2. b\n'
+    assert md('<ol><li>a</li><li>b</li></ol>') == '\n1. a\n2. b\n\n'
 
 
 def test_p():
@@ -61,4 +134,25 @@ def test_strong():
 
 
 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></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)'