Merge branch 'develop'

Add conversion for hr element

.github/workflows/python-app.yml

@@ -16,14 +16,14 @@ jobs:
 
     steps:
     - uses: actions/checkout@v2
-    - name: Set up Python 3.6
+    - name: Set up Python 3.8
       uses: actions/setup-python@v2
       with:
-        python-version: 3.6
+        python-version: 3.8
     - name: Install dependencies
       run: |
         python -m pip install --upgrade pip
-        pip install flake8==2.5.4 pytest
+        pip install flake8==3.8.4 pytest
         if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
     - name: Lint with flake8
       run: |

.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

@@ -75,6 +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

@@ -1,11 +1,11 @@
-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 ]+')
+whitespace_re = re.compile(r'[\t ]+')
 html_heading_re = re.compile(r'h[1-6]')
 
 
@@ -15,6 +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:
@@ -46,6 +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
@@ -75,7 +85,9 @@ class MarkdownConverter(object):
 
         # 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, convert_children_as_inline)
@@ -146,25 +158,29 @@ class MarkdownConverter(object):
         if convert_as_inline:
             return text
 
-        return '\n' + line_beginning_re.sub('> ', text) if text else ''
+        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 ""
 
-        return '  \n'
+        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, convert_as_inline):
         if convert_as_inline:
             return text
 
-        style = self.options['heading_style']
+        style = self.options['heading_style'].lower()
         text = text.rstrip()
         if style == UNDERLINED and n <= 2:
             line = '=' if n == 1 else '-'
@@ -220,10 +236,11 @@ class MarkdownConverter(object):
         return '%s\n\n' % 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' % (prefix, text, suffix)
+        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 ''
@@ -235,6 +252,26 @@ class MarkdownConverter(object):
 
         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__': '0.6.1',
+    '__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> ') == '  '
@@ -75,12 +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():
@@ -111,6 +185,11 @@ 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'
@@ -150,7 +229,9 @@ def test_hn_nested_img():
 
 
 def test_hr():
-    assert md('<hr>hr</hr>') == '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():
@@ -211,3 +292,20 @@ def test_img():
 
 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():