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

@@ -17,7 +17,7 @@ jobs:
     - name: Set up Python
       uses: actions/setup-python@v2
       with:
-        python-version: '3.x'
+        python-version: '3.8'
     - name: Install dependencies
       run: |
         python -m pip install --upgrade pip

README.rst

@@ -1,3 +1,21 @@
+|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
 ============
 
@@ -57,6 +75,18 @@ bullets
   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.
 

markdownify/__init__.py

@@ -1,13 +1,12 @@
-from bs4 import BeautifulSoup, NavigableString
+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 ]+')
-FRAGMENT_ID = '__MARKDOWNIFY_WRAPPER__'
-wrapped = '<div id="%s">%%s</div>' % FRAGMENT_ID
+whitespace_re = re.compile(r'[\t ]+')
+html_heading_re = re.compile(r'h[1-6]')
 
 
 # Heading styles
@@ -16,6 +15,14 @@ ATX_CLOSED = 'atx_closed'
 UNDERLINED = 'underlined'
 SETEXT = UNDERLINED
 
+# Newline style
+SPACES = 'spaces'
+BACKSLASH = 'backslash'
+
+# Strong and emphasis style
+ASTERISK = '*'
+UNDERSCORE = '_'
+
 
 def escape(text):
     if not text:
@@ -47,6 +54,8 @@ class MarkdownConverter(object):
         autolinks = True
         heading_style = UNDERLINED
         bullets = '*+-'  # An iterable of bullet types.
+        strong_em_symbol = ASTERISK
+        newline_style = SPACES
 
     class Options(DefaultOptions):
         pass
@@ -62,27 +71,31 @@ class MarkdownConverter(object):
                              ' convert, but not both.')
 
     def convert(self, html):
-        # 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)
+        return self.process_tag(soup, convert_as_inline=False, children_only=True)
 
-    def process_tag(self, node, children_only=False):
+    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.children:
-            if isinstance(el, NavigableString):
+            if isinstance(el, Comment):
+                continue
+            elif isinstance(el, NavigableString):
                 text += self.process_text(six.text_type(el))
             else:
-                text += self.process_tag(el)
+                text += self.process_tag(el, convert_children_as_inline)
 
         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)
+                text = convert_fn(node, text, convert_as_inline)
 
         return text
 
@@ -95,8 +108,8 @@ class MarkdownConverter(object):
         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)
@@ -122,35 +135,52 @@ class MarkdownConverter(object):
         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')
-        if self.options['autolinks'] and text == href and not 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%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 '\n' + (line_beginning_re.sub('> ', text) + '\n\n') if text else ''
+
+    def convert_br(self, el, text, convert_as_inline):
+        if convert_as_inline:
+            return ""
+
+        if self.options['newline_style'].lower() == BACKSLASH:
+            return '\\\n'
+        else:
+            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' % (prefix, text, suffix)
+        return '%s%s%s%s%s' % (prefix, em_tag, text, em_tag, suffix)
 
-    def convert_hn(self, n, el, text):
-        style = self.options['heading_style']
+    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 '-'
@@ -160,10 +190,14 @@ class MarkdownConverter(object):
             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_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.
 
-    def convert_list(self, el, text):
         nested = False
         while el:
             if el.name == 'li':
@@ -178,10 +212,14 @@ class MarkdownConverter(object):
     convert_ul = convert_list
     convert_ol = convert_list
 
-    def convert_li(self, el, text):
+    def convert_li(self, el, text, convert_as_inline):
         parent = el.parent
         if parent is not None and parent.name == 'ol':
-            bullet = '%s.' % (parent.index(el) + 1)
+            if parent.get("start"):
+                start = int(parent.get("start"))
+            else:
+                start = 1
+            bullet = '%s.' % (start + parent.index(el))
         else:
             depth = -1
             while el:
@@ -192,22 +230,48 @@ class MarkdownConverter(object):
             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):
+    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' % (prefix, text, suffix)
+        return '%s%s%s%s%s' % (prefix, strong_tag, text, strong_tag, suffix)
 
-    def convert_img(self, el, text):
+    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, **options):
     return MarkdownConverter(**options).convert(html)

setup.py

@@ -10,7 +10,7 @@ read = lambda filepath: codecs.open(filepath, 'r', 'utf-8').read()
 pkgmeta = {
     '__title__': 'markdownify',
     '__author__': 'Matthew Tretter',
-    '__version__': '0.5.1',
+    '__version__': '0.7.1',
 }
 
 
@@ -50,7 +50,7 @@ class LintCommand(Command):
                 yield "%s.py" % filename
 
     def run(self):
-        from flake8.engine import get_style_guide
+        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)
@@ -70,13 +70,13 @@ setup(
     zip_safe=False,
     include_package_data=True,
     setup_requires=[
-        'flake8',
+        'flake8>=3.8,<4',
     ],
     tests_require=[
-        'pytest',
+        'pytest>=6.2,<7',
     ],
     install_requires=[
-        'beautifulsoup4', 'six'
+        'beautifulsoup4>=4.9,<5', 'six>=1.15,<2'
     ],
     classifiers=[
         'Environment :: Web Environment',
@@ -87,6 +87,9 @@ setup(
         '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'
     ],
     cmdclass={

tests/test_advanced.py

@@ -4,3 +4,13 @@ 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_basic.py

@@ -10,4 +10,4 @@ def test_soup():
 
 
 def test_whitespace():
-    assert md(' a  b \n\n c ') == ' a b c '
+    assert md(' a  b \t\t c ') == ' a b c '

tests/test_conversions.py

@@ -1,4 +1,4 @@
-from markdownify import markdownify as md, ATX, ATX_CLOSED
+from markdownify import markdownify as md, ATX, ATX_CLOSED, BACKSLASH, UNDERSCORE
 import re
 
 
@@ -22,6 +22,76 @@ nested_uls = re.sub(r'\s+', '', """
     </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> ') == '  '
@@ -34,7 +104,11 @@ def test_chomp():
 
 
 def test_a():
-    assert md('<a href="http://google.com">Google</a>') == '[Google](http://google.com)'
+    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():
@@ -71,12 +145,16 @@ def test_b_spaces():
 
 
 def test_blockquote():
-    assert md('<blockquote>Hello</blockquote>').strip() == '> Hello'
+    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>').strip()
-    assert text == '> And she was like \n> > Hello'
+    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():
@@ -107,6 +185,59 @@ def test_hn():
     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'
@@ -123,6 +254,7 @@ def test_i():
 
 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():
@@ -156,3 +288,24 @@ def test_bullets():
 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

@@ -2,7 +2,7 @@ from markdownify import markdownify as md
 
 
 def test_underscore():
-    assert md('_hey_dude_') == '\_hey\_dude\_'
+    assert md('_hey_dude_') == r'\_hey\_dude\_'
 
 
 def test_xml_entities():