Merge branch 'develop'

When checking a links href and text for
equality, first un-escape the underscores
in the text -- because six escapes them.
This should fix #29.

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
 ============
 

markdownify/__init__.py

@@ -6,8 +6,7 @@ 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
+html_heading_re = re.compile(r'h[1-6]')
 
 
 # Heading styles
@@ -62,27 +61,29 @@ 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):
                 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 +96,8 @@ 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)
@@ -122,34 +123,47 @@ 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, convert_as_inline):
+
+        if convert_as_inline:
+            return text
 
-    def convert_blockquote(self, el, text):
         return '\n' + line_beginning_re.sub('> ', text) if text else ''
 
-    def convert_br(self, el, text):
+    def convert_br(self, el, text, convert_as_inline):
+        if convert_as_inline:
+            return ""
+
         return '  \n'
 
-    def convert_em(self, el, text):
+    def convert_em(self, el, text, convert_as_inline):
         prefix, suffix, text = chomp(text)
         if not text:
             return ''
         return '%s*%s*%s' % (prefix, text, suffix)
 
-    def convert_hn(self, n, el, text):
+    def convert_hn(self, n, el, text, convert_as_inline):
+        if convert_as_inline:
+            return text
+
         style = self.options['heading_style']
         text = text.rstrip()
         if style == UNDERLINED and n <= 2:
@@ -160,10 +174,14 @@ 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':
@@ -178,7 +196,7 @@ 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':
             if parent.get("start"):
@@ -196,20 +214,25 @@ 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):
         prefix, suffix, text = chomp(text)
         if not text:
             return ''
         return '%s**%s**%s' % (prefix, text, 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)
 
 

setup.py

@@ -10,7 +10,7 @@ read = lambda filepath: codecs.open(filepath, 'r', 'utf-8').read()
 pkgmeta = {
     '__title__': 'markdownify',
     '__author__': 'Matthew Tretter',
-    '__version__': '0.5.2',
+    '__version__': '0.6.1',
 }
 
 

tests/test_conversions.py

@@ -34,7 +34,11 @@ 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():
@@ -107,6 +111,52 @@ def test_hn():
     assert md('<h6>Hello</h6>') == '###### Hello\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('<hr>hr</hr>') == 'hr'
+
+
+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'
@@ -157,3 +207,7 @@ 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'