Merge branch 'develop'

Author: chrispy-snps

markdownify/__init__.py

@@ -106,6 +106,7 @@ def should_remove_whitespace_inside(el):
     return el.name in ('p', 'blockquote',
                        'article', 'div', 'section',
                        'ol', 'ul', 'li',
+                       'dl', 'dt', 'dd',
                        'table', 'thead', 'tbody', 'tfoot',
                        'tr', 'td', 'th')
 
@@ -442,7 +443,7 @@ def _indent_for_blockquote(match):
 
     def convert_br(self, el, text, parent_tags):
         if '_inline' in parent_tags:
-            return ""
+            return ' '
 
         if self.options['newline_style'].lower() == BACKSLASH:
             return '\\\n'
@@ -489,6 +490,11 @@ def _indent_for_dd(match):
 
         return '%s\n' % text
 
+    # definition lists are formatted as follows:
+    #   https://pandoc.org/MANUAL.html#definition-lists
+    #   https://michelf.ca/projects/php-markdown/extra/#def-list
+    convert_dl = convert_div
+
     def convert_dt(self, el, text, parent_tags):
         # remove newlines from term text
         text = (text or '').strip()
@@ -501,7 +507,7 @@ def convert_dt(self, el, text, parent_tags):
         # TODO - format consecutive <dt> elements as directly adjacent lines):
         #   https://michelf.ca/projects/php-markdown/extra/#def-list
 
-        return '\n%s\n' % text
+        return '\n\n%s\n' % text
 
     def _convert_hn(self, n, el, text, parent_tags):
         """ Method name prefixed with _ to prevent <hn> to call this """
@@ -538,6 +544,24 @@ def convert_img(self, el, text, parent_tags):
 
         return '![%s](%s%s)' % (alt, src, title_part)
 
+    def convert_video(self, el, text, parent_tags):
+        if ('_inline' in parent_tags
+                and el.parent.name not in self.options['keep_inline_images_in']):
+            return text
+        src = el.attrs.get('src', None) or ''
+        if not src:
+            sources = el.find_all('source', attrs={'src': True})
+            if sources:
+                src = sources[0].attrs.get('src', None) or ''
+        poster = el.attrs.get('poster', None) or ''
+        if src and poster:
+            return '[![%s](%s)](%s)' % (text, poster, src)
+        if src:
+            return '[%s](%s)' % (text, src)
+        if poster:
+            return '![%s](%s)' % (text, poster)
+        return text
+
     def convert_list(self, el, text, parent_tags):
 
         # Converting a list to inline is undefined.
@@ -677,6 +701,12 @@ def convert_tr(self, el, text, parent_tags):
         )
         overline = ''
         underline = ''
+        full_colspan = 0
+        for cell in cells:
+            if 'colspan' in cell.attrs and cell['colspan'].isdigit():
+                full_colspan += int(cell["colspan"])
+            else:
+                full_colspan += 1
         if ((is_headrow
              or (is_head_row_missing
                  and self.options['table_infer_header']))
@@ -685,12 +715,6 @@ def convert_tr(self, el, text, parent_tags):
             # - is headline or
             # - headline is missing and header inference is enabled
             # print headline underline
-            full_colspan = 0
-            for cell in cells:
-                if 'colspan' in cell.attrs and cell['colspan'].isdigit():
-                    full_colspan += int(cell["colspan"])
-                else:
-                    full_colspan += 1
             underline += '| ' + ' | '.join(['---'] * full_colspan) + ' |' + '\n'
         elif ((is_head_row_missing
                and not self.options['table_infer_header'])
@@ -703,8 +727,8 @@ def convert_tr(self, el, text, parent_tags):
             #  - the parent is table or
             #  - the parent is tbody at the beginning of a table.
             # print empty headline above this row
-            overline += '| ' + ' | '.join([''] * len(cells)) + ' |' + '\n'
-            overline += '| ' + ' | '.join(['---'] * len(cells)) + ' |' + '\n'
+            overline += '| ' + ' | '.join([''] * full_colspan) + ' |' + '\n'
+            overline += '| ' + ' | '.join(['---'] * full_colspan) + ' |' + '\n'
         return overline + '|' + text + '\n' + underline
 
 

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "markdownify"
-version = "1.0.0"
+version = "1.1.0"
 authors = [{name = "Matthew Tretter", email = "[email protected]"}]
 description = "Convert HTML to markdown."
 readme = "README.rst"

tests/test_conversions.py

@@ -79,6 +79,8 @@ def test_blockquote_nested():
 def test_br():
     assert md('a<br />b<br />c') == 'a  \nb  \nc'
     assert md('a<br />b<br />c', newline_style=BACKSLASH) == 'a\\\nb\\\nc'
+    assert md('<h1>foo<br />bar</h1>', heading_style=ATX) == '\n\n# foo bar\n\n'
+    assert md('<td>foo<br />bar</td>', heading_style=ATX) == ' foo bar |'
 
 
 def test_code():
@@ -102,13 +104,13 @@ def test_code():
 
 
 def test_dl():
-    assert md('<dl><dt>term</dt><dd>definition</dd></dl>') == '\nterm\n:   definition\n'
-    assert md('<dl><dt><p>te</p><p>rm</p></dt><dd>definition</dd></dl>') == '\nte rm\n:   definition\n'
-    assert md('<dl><dt>term</dt><dd><p>definition-p1</p><p>definition-p2</p></dd></dl>') == '\nterm\n:   definition-p1\n\n    definition-p2\n'
-    assert md('<dl><dt>term</dt><dd><p>definition 1</p></dd><dd><p>definition 2</p></dd></dl>') == '\nterm\n:   definition 1\n:   definition 2\n'
-    assert md('<dl><dt>term 1</dt><dd>definition 1</dd><dt>term 2</dt><dd>definition 2</dd></dl>') == '\nterm 1\n:   definition 1\nterm 2\n:   definition 2\n'
-    assert md('<dl><dt>term</dt><dd><blockquote><p>line 1</p><p>line 2</p></blockquote></dd></dl>') == '\nterm\n:   > line 1\n    >\n    > line 2\n'
-    assert md('<dl><dt>term</dt><dd><ol><li><p>1</p><ul><li>2a</li><li>2b</li></ul></li><li><p>3</p></li></ol></dd></dl>') == '\nterm\n:   1. 1\n\n       * 2a\n       * 2b\n    2. 3\n'
+    assert md('<dl><dt>term</dt><dd>definition</dd></dl>') == '\n\nterm\n:   definition\n\n'
+    assert md('<dl><dt><p>te</p><p>rm</p></dt><dd>definition</dd></dl>') == '\n\nte rm\n:   definition\n\n'
+    assert md('<dl><dt>term</dt><dd><p>definition-p1</p><p>definition-p2</p></dd></dl>') == '\n\nterm\n:   definition-p1\n\n    definition-p2\n\n'
+    assert md('<dl><dt>term</dt><dd><p>definition 1</p></dd><dd><p>definition 2</p></dd></dl>') == '\n\nterm\n:   definition 1\n:   definition 2\n\n'
+    assert md('<dl><dt>term 1</dt><dd>definition 1</dd><dt>term 2</dt><dd>definition 2</dd></dl>') == '\n\nterm 1\n:   definition 1\n\nterm 2\n:   definition 2\n\n'
+    assert md('<dl><dt>term</dt><dd><blockquote><p>line 1</p><p>line 2</p></blockquote></dd></dl>') == '\n\nterm\n:   > line 1\n    >\n    > line 2\n\n'
+    assert md('<dl><dt>term</dt><dd><ol><li><p>1</p><ul><li>2a</li><li>2b</li></ul></li><li><p>3</p></li></ol></dd></dl>') == '\n\nterm\n:   1. 1\n\n       * 2a\n       * 2b\n    2. 3\n\n'
 
 
 def test_del():
@@ -243,6 +245,14 @@ def test_img():
     assert md('<img src="/path/to/img.jpg" alt="Alt text" />') == '![Alt text](/path/to/img.jpg)'
 
 
+def test_video():
+    assert md('<video src="/path/to/video.mp4" poster="/path/to/img.jpg">text</video>') == '[![text](/path/to/img.jpg)](/path/to/video.mp4)'
+    assert md('<video src="/path/to/video.mp4">text</video>') == '[text](/path/to/video.mp4)'
+    assert md('<video><source src="/path/to/video.mp4"/>text</video>') == '[text](/path/to/video.mp4)'
+    assert md('<video poster="/path/to/img.jpg">text</video>') == '![text](/path/to/img.jpg)'
+    assert md('<video>text</video>') == 'text'
+
+
 def test_kbd():
     inline_tests('kbd', '`')
 

tests/test_tables.py

@@ -267,6 +267,23 @@
     </tr>
 </table>"""
 
+table_with_colspan_missing_head = """<table>
+    <tr>
+        <td colspan="2">Name</td>
+        <td>Age</td>
+    </tr>
+    <tr>
+        <td>Jill</td>
+        <td>Smith</td>
+        <td>50</td>
+    </tr>
+    <tr>
+        <td>Eve</td>
+        <td>Jackson</td>
+        <td>94</td>
+    </tr>
+</table>"""
+
 
 def test_table():
     assert md(table) == '\n\n| Firstname | Lastname | Age |\n| --- | --- | --- |\n| Jill | Smith | 50 |\n| Eve | Jackson | 94 |\n\n'
@@ -283,6 +300,7 @@ def test_table():
     assert md(table_with_caption) == 'TEXT\n\nCaption\n\n|  |  |  |\n| --- | --- | --- |\n| Firstname | Lastname | Age |\n\n'
     assert md(table_with_colspan) == '\n\n| Name | | Age |\n| --- | --- | --- |\n| Jill | Smith | 50 |\n| Eve | Jackson | 94 |\n\n'
     assert md(table_with_undefined_colspan) == '\n\n| Name | Age |\n| --- | --- |\n| Jill | Smith |\n\n'
+    assert md(table_with_colspan_missing_head) == '\n\n|  |  |  |\n| --- | --- | --- |\n| Name | | Age |\n| Jill | Smith | 50 |\n| Eve | Jackson | 94 |\n\n'
 
 
 def test_table_infer_header():
@@ -300,3 +318,4 @@ def test_table_infer_header():
     assert md(table_with_caption, table_infer_header=True) == 'TEXT\n\nCaption\n\n| Firstname | Lastname | Age |\n| --- | --- | --- |\n\n'
     assert md(table_with_colspan, table_infer_header=True) == '\n\n| Name | | Age |\n| --- | --- | --- |\n| Jill | Smith | 50 |\n| Eve | Jackson | 94 |\n\n'
     assert md(table_with_undefined_colspan, table_infer_header=True) == '\n\n| Name | Age |\n| --- | --- |\n| Jill | Smith |\n\n'
+    assert md(table_with_colspan_missing_head, table_infer_header=True) == '\n\n| Name | | Age |\n| --- | --- | --- |\n| Jill | Smith | 50 |\n| Eve | Jackson | 94 |\n\n'