Merge branch 'develop'

don't escape text in pre tag (Fenced Code Blocks)

.github/workflows/python-app.yml

@@ -23,11 +23,7 @@ jobs:
     - 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
+        pip install tox
+    - name: Lint and test
       run: |
-        python setup.py lint
-    - name: Test with pytest
-      run: |
-        python setup.py test
+        tox

.gitignore

@@ -9,3 +9,4 @@
 /venv
 build/
 .vscode/settings.json
+.tox/

README.rst

@@ -32,14 +32,14 @@ Convert some HTML to Markdown:
     from markdownify import markdownify as md
     md('<b>Yay</b> <a href="http://github.com">GitHub</a>')  # > '**Yay** [GitHub](http://github.com)'
 
-Specify tags to exclude (blacklist):
+Specify tags to exclude:
 
 .. code:: python
 
     from markdownify import markdownify as md
     md('<b>Yay</b> <a href="http://github.com">GitHub</a>', strip=['a'])  # > '**Yay** GitHub'
 
-\...or specify the tags you want to include (whitelist):
+\...or specify the tags you want to include:
 
 .. code:: python
 
@@ -53,11 +53,11 @@ Options
 Markdownify supports the following options:
 
 strip
-  A list of tags to strip (blacklist). This option can't be used with the
+  A list of tags to strip. 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
+  A list of tags to convert. This option can't be used with the
   ``strip`` option.
 
 autolinks
@@ -92,14 +92,65 @@ sub_symbol, sup_symbol
 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
+  while ``BACKSLASH`` will convert a linebreak to ``\\n`` (a backslash and a
   newline). While the latter convention is non-standard, it is commonly
   preferred and supported by a lot of interpreters.
 
+code_language
+  Defines the language that should be assumed for all ``<pre>`` sections.
+  Useful, if all code on a page is in the same programming language and
+  should be annotated with `````python`` or similar.
+  Defaults to ``''`` (empty string) and can be any string.
+
+code_language_callback
+  When the HTML code contains ``pre`` tags that in some way provide the code
+  language, for example as class, this callback can be used to extract the
+  language from the tag and prefix it to the converted ``pre`` tag.
+  The callback gets one single argument, an BeautifylSoup object, and returns
+  a string containing the code language, or ``None``.
+  An example to use the class name as code language could be::
+
+    def callback(el):
+        return el['class'][0] if el.has_attr('class') else None
+
+  Defaults to ``None``.
+
+escape_asterisks
+  If set to ``False``, do not escape ``*`` to ``\*`` in text.
+  Defaults to ``True``.
+
+escape_underscores
+  If set to ``False``, do not escape ``_`` to ``\_`` in text.
+  Defaults to ``True``.
+
+keep_inline_images_in
+  Images are converted to their alt-text when the images are located inside
+  headlines or table cells. If some inline images should be converted to
+  markdown images instead, this option can be set to a list of parent tags
+  that should be allowed to contain inline images, for example ``['td']``.
+  Defaults to an empty list.
+
+wrap, wrap_width
+  If ``wrap`` is set to ``True``, all text paragraphs are wrapped at
+  ``wrap_width`` characters. Defaults to ``False`` and ``80``.
+  Use with ``newline_style=BACKSLASH`` to keep line breaks in paragraphs.
+
 Options may be specified as kwargs to the ``markdownify`` function, or as a
 nested ``Options`` class in ``MarkdownConverter`` subclasses.
 
 
+Converting BeautifulSoup objects
+================================
+
+.. code:: python
+
+    from markdownify import MarkdownConverter
+
+    # Create shorthand method for conversion
+    def md(soup, **options):
+        return MarkdownConverter(**options).convert_soup(soup)
+
+
 Creating Custom Converters
 ==========================
 
@@ -123,13 +174,16 @@ change:
         return ImageBlockConverter(**options).convert(html)
 
 
+Command Line Interface
+======================
+
+Use ``markdownify example.html > example.md`` or pipe input from stdin
+(``cat example.html | markdownify > example.md``).
+Call ``markdownify -h`` to see all available options.
+They are the same as listed above and take the same arguments.
+
+
 Development
 ===========
 
-To run tests:
-
-``python setup.py test``
-
-To lint:
-
-``python setup.py lint``
+To run tests and the linter run ``pip install tox`` once, then ``tox``.

markdownify/__init__.py

@@ -1,4 +1,5 @@
 from bs4 import BeautifulSoup, NavigableString, Comment, Doctype
+from textwrap import fill
 import re
 import six
 
@@ -25,12 +26,6 @@ ASTERISK = '*'
 UNDERSCORE = '_'
 
 
-def escape(text):
-    if not text:
-        return ''
-    return text.replace('_', r'\_')
-
-
 def chomp(text):
     """
     If the text in an inline tag like b, a, or em contains a leading or trailing
@@ -68,15 +63,21 @@ class MarkdownConverter(object):
     class DefaultOptions:
         autolinks = True
         bullets = '*+-'  # An iterable of bullet types.
+        code_language = ''
+        code_language_callback = None
         convert = None
         default_title = False
+        escape_asterisks = True
+        escape_underscores = True
         heading_style = UNDERLINED
+        keep_inline_images_in = []
         newline_style = SPACES
         strip = None
         strong_em_symbol = ASTERISK
         sub_symbol = ''
         sup_symbol = ''
-        code_language = ''
+        wrap = False
+        wrap_width = 80
 
     class Options(DefaultOptions):
         pass
@@ -93,6 +94,9 @@ class MarkdownConverter(object):
 
     def convert(self, html):
         soup = BeautifulSoup(html, 'html.parser')
+        return self.convert_soup(soup)
+
+    def convert_soup(self, soup):
         return self.process_tag(soup, convert_as_inline=False, children_only=True)
 
     def process_tag(self, node, convert_as_inline, children_only=False):
@@ -154,8 +158,8 @@ class MarkdownConverter(object):
                     and el.parent.parent.name == 'pre')):
             text = whitespace_re.sub(' ', text)
 
-        if el.parent.name != 'code':
-            text = escape(text)
+        if el.parent.name != 'code' and el.parent.name != 'pre':
+            text = self.escape(text)
 
         # remove trailing whitespaces if any of the following condition is true:
         # - current text node is the last node in li
@@ -193,6 +197,15 @@ class MarkdownConverter(object):
         else:
             return True
 
+    def escape(self, text):
+        if not text:
+            return ''
+        if self.options['escape_asterisks']:
+            text = text.replace('*', r'\*')
+        if self.options['escape_underscores']:
+            text = text.replace('_', r'\_')
+        return text
+
     def indent(self, text, level):
         return line_beginning_re.sub('\t' * level, text) if text else ''
 
@@ -272,7 +285,8 @@ class MarkdownConverter(object):
         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:
+        if (convert_as_inline
+                and el.parent.name not in self.options['keep_inline_images_in']):
             return alt
 
         return '![%s](%s%s)' % (alt, src, title_part)
@@ -320,12 +334,22 @@ class MarkdownConverter(object):
     def convert_p(self, el, text, convert_as_inline):
         if convert_as_inline:
             return text
+        if self.options['wrap']:
+            text = fill(text,
+                        width=self.options['wrap_width'],
+                        break_long_words=False,
+                        break_on_hyphens=False)
         return '%s\n\n' % text if text else ''
 
     def convert_pre(self, el, text, convert_as_inline):
         if not text:
             return ''
-        return '\n```%s\n%s\n```\n' % (self.options['code_language'], text)
+        code_language = self.options['code_language']
+
+        if self.options['code_language_callback']:
+            code_language = self.options['code_language_callback'](el) or code_language
+
+        return '\n```%s\n%s\n```\n' % (code_language, text)
 
     convert_s = convert_del
 
@@ -354,8 +378,13 @@ class MarkdownConverter(object):
         if is_headrow and not el.previous_sibling:
             # first row and is headline: print headline underline
             underline += '| ' + ' | '.join(['---'] * len(cells)) + ' |' + '\n'
-        elif not el.previous_sibling and not el.parent.name != 'table':
-            # first row, not headline, and the parent is sth. like tbody:
+        elif (not el.previous_sibling
+              and (el.parent.name == 'table'
+                   or (el.parent.name == 'tbody'
+                       and not el.parent.previous_sibling))):
+            # first row, not headline, and:
+            # - 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'

markdownify/main.py

@@ -0,0 +1,68 @@
+#!/usr/bin/env python
+
+import argparse
+import sys
+
+from markdownify import markdownify
+
+
+def main(argv=sys.argv[1:]):
+    parser = argparse.ArgumentParser(
+        prog='markdownify',
+        description='Converts html to markdown.',
+    )
+
+    parser.add_argument('html', nargs='?', type=argparse.FileType('r'),
+                        default=sys.stdin,
+                        help="The html file to convert. Defaults to STDIN if not "
+                        "provided.")
+    parser.add_argument('-s', '--strip', nargs='*',
+                        help="A list of tags to strip. This option can't be used with "
+                        "the --convert option.")
+    parser.add_argument('-c', '--convert', nargs='*',
+                        help="A list of tags to convert. This option can't be used with "
+                        "the --strip option.")
+    parser.add_argument('-a', '--autolinks', action='store_true',
+                        help="A boolean indicating whether the 'automatic link' style "
+                        "should be used when a 'a' tag's contents match its href.")
+    parser.add_argument('--default-title', action='store_false',
+                        help="A boolean to enable setting the title of a link to its "
+                        "href, if no title is given.")
+    parser.add_argument('--heading-style', default='UNDERLINED',
+                        choices=('ATX', 'ATX_CLOSED', 'SETEXT', 'UNDERLINED'),
+                        help="Defines how headings should be converted.")
+    parser.add_argument('-b', '--bullets', default='*+-',
+                        help="A string of bullet styles to use; the bullet will "
+                        "alternate based on nesting level.")
+    parser.add_argument('--strong-em-symbol', default='ASTERISK',
+                        choices=('ASTERISK', 'UNDERSCORE'),
+                        help="Use * or _ to convert strong and italics text"),
+    parser.add_argument('--sub-symbol', default='',
+                        help="Define the chars that surround '<sub>'.")
+    parser.add_argument('--sup-symbol', default='',
+                        help="Define the chars that surround '<sup>'.")
+    parser.add_argument('--code-language', default='',
+                        help="Defines the language that should be assumed for all "
+                        "'<pre>' sections.")
+    parser.add_argument('--no-escape-asterisks', dest='escape_asterisks',
+                        action='store_false',
+                        help="Do not escape '*' to '\\*' in text.")
+    parser.add_argument('--no-escape-underscores', dest='escape_underscores',
+                        action='store_false',
+                        help="Do not escape '_' to '\\_' in text.")
+    parser.add_argument('-i', '--keep-inline-images-in', nargs='*',
+                        help="Images are converted to their alt-text when the images are "
+                        "located inside headlines or table cells. If some inline images "
+                        "should be converted to markdown images instead, this option can "
+                        "be set to a list of parent tags that should be allowed to "
+                        "contain inline images.")
+    parser.add_argument('-w', '--wrap', action='store_true',
+                        help="Wrap all text paragraphs at --wrap-width characters.")
+    parser.add_argument('--wrap-width', type=int, default=80)
+
+    args = parser.parse_args(argv)
+    print(markdownify(**vars(args)))
+
+
+if __name__ == '__main__':
+    main()

setup.cfg

@@ -1,2 +0,0 @@
-[flake8]
-ignore = E501 W503

setup.py

@@ -2,7 +2,6 @@
 import codecs
 import os
 from setuptools import setup, find_packages
-from setuptools.command.test import test as TestCommand, Command
 
 
 read = lambda filepath: codecs.open(filepath, 'r', 'utf-8').read()
@@ -10,52 +9,10 @@ read = lambda filepath: codecs.open(filepath, 'r', 'utf-8').read()
 pkgmeta = {
     '__title__': 'markdownify',
     '__author__': 'Matthew Tretter',
-    '__version__': '0.9.4',
+    '__version__': '0.11.5',
 }
 
-
-class PyTest(TestCommand):
-    def finalize_options(self):
-        TestCommand.finalize_options(self)
-        self.test_args = ['tests', '-s']
-        self.test_suite = True
-
-    def run_tests(self):
-        import pytest
-        errno = pytest.main(self.test_args)
-        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.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)
-        raise SystemExit(report.total_errors > 0)
-
+read = lambda filepath: codecs.open(filepath, 'r', 'utf-8').read()
 
 setup(
     name='markdownify',
@@ -69,14 +26,9 @@ setup(
     packages=find_packages(),
     zip_safe=False,
     include_package_data=True,
-    setup_requires=[
-        'flake8>=3.8,<4',
-    ],
-    tests_require=[
-        'pytest>=6.2,<7',
-    ],
     install_requires=[
-        'beautifulsoup4>=4.9,<5', 'six>=1.15,<2'
+        'beautifulsoup4>=4.9,<5',
+        'six>=1.15,<2',
     ],
     classifiers=[
         'Environment :: Web Environment',
@@ -92,8 +44,9 @@ setup(
         'Programming Language :: Python :: 3.8',
         'Topic :: Utilities'
     ],
-    cmdclass={
-        'test': PyTest,
-        'lint': LintCommand,
-    },
+    entry_points={
+        'console_scripts': [
+            'markdownify = markdownify.main:main'
+        ]
+    }
 )

tests/test_conversions.py

@@ -133,12 +133,13 @@ def test_hn_nested_simple_tag():
 
 def test_hn_nested_img():
     image_attributes_to_markdown = [
-        ("", ""),
-        ("alt='Alt Text'", "Alt Text"),
-        ("alt='Alt Text' title='Optional title'", "Alt Text"),
+        ("", "", ""),
+        ("alt='Alt Text'", "Alt Text", ""),
+        ("alt='Alt Text' title='Optional title'", "Alt Text", " \"Optional title\""),
     ]
-    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'
+    for image_attributes, markdown, title in image_attributes_to_markdown:
+        assert md('<h3>A <img src="/path/to/img.jpg" ' + image_attributes + '/> B</h3>') == '### A ' + markdown + ' B\n\n'
+        assert md('<h3>A <img src="/path/to/img.jpg" ' + image_attributes + '/> B</h3>', keep_inline_images_in=['h3']) == '### A ![' + markdown + '](/path/to/img.jpg' + title + ') B\n\n'
 
 
 def test_hn_atx_headings():
@@ -176,11 +177,17 @@ def test_kbd():
 
 def test_p():
     assert md('<p>hello</p>') == 'hello\n\n'
+    assert md('<p>123456789 123456789</p>') == '123456789 123456789\n\n'
+    assert md('<p>123456789 123456789</p>', wrap=True, wrap_width=10) == '123456789\n123456789\n\n'
+    assert md('<p><a href="https://example.com">Some long link</a></p>', wrap=True, wrap_width=10) == '[Some long\nlink](https://example.com)\n\n'
+    assert md('<p>12345<br />67890</p>', wrap=True, wrap_width=10, newline_style=BACKSLASH) == '12345\\\n67890\n\n'
+    assert md('<p>12345678901<br />12345</p>', wrap=True, wrap_width=10, newline_style=BACKSLASH) == '12345678901\\\n12345\n\n'
 
 
 def test_pre():
     assert md('<pre>test\n    foo\nbar</pre>') == '\n```\ntest\n    foo\nbar\n```\n'
     assert md('<pre><code>test\n    foo\nbar</code></pre>') == '\n```\ntest\n    foo\nbar\n```\n'
+    assert md('<pre>this_should_not_escape</pre>') == '\n```\nthis_should_not_escape\n```\n'
 
 
 def test_s():
@@ -215,3 +222,12 @@ def test_sup():
 def test_lang():
     assert md('<pre>test\n    foo\nbar</pre>', code_language='python') == '\n```python\ntest\n    foo\nbar\n```\n'
     assert md('<pre><code>test\n    foo\nbar</code></pre>', code_language='javascript') == '\n```javascript\ntest\n    foo\nbar\n```\n'
+
+
+def test_lang_callback():
+    def callback(el):
+        return el['class'][0] if el.has_attr('class') else None
+
+    assert md('<pre class="python">test\n    foo\nbar</pre>', code_language_callback=callback) == '\n```python\ntest\n    foo\nbar\n```\n'
+    assert md('<pre class="javascript"><code>test\n    foo\nbar</code></pre>', code_language_callback=callback) == '\n```javascript\ntest\n    foo\nbar\n```\n'
+    assert md('<pre class="javascript"><code class="javascript">test\n    foo\nbar</code></pre>', code_language_callback=callback) == '\n```javascript\ntest\n    foo\nbar\n```\n'

tests/test_custom_converter.py

@@ -1,4 +1,5 @@
 from markdownify import MarkdownConverter
+from bs4 import BeautifulSoup
 
 
 class ImageBlockConverter(MarkdownConverter):
@@ -16,3 +17,9 @@ 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")\n\n'
     assert md('<img src="/path/to/img.jpg" alt="Alt text" />') == '![Alt text](/path/to/img.jpg)\n\n'
+
+
+def test_soup():
+    html = '<b>test</b>'
+    soup = BeautifulSoup(html, 'html.parser')
+    assert MarkdownConverter().convert_soup(soup) == '**test**'

tests/test_escaping.py

@@ -1,8 +1,14 @@
 from markdownify import markdownify as md
 
 
+def test_asterisks():
+    assert md('*hey*dude*') == r'\*hey\*dude\*'
+    assert md('*hey*dude*', escape_asterisks=False) == r'*hey*dude*'
+
+
 def test_underscore():
     assert md('_hey_dude_') == r'\_hey\_dude\_'
+    assert md('_hey_dude_', escape_underscores=False) == r'_hey_dude_'
 
 
 def test_xml_entities():

tests/test_tables.py

@@ -139,6 +139,26 @@ table_missing_head = """<table>
     </tr>
 </table>"""
 
+table_body = """<table>
+    <tbody>
+        <tr>
+            <td>Firstname</td>
+            <td>Lastname</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>
+    </tbody>
+</table>"""
+
 
 def test_table():
     assert md(table) == '\n\n| Firstname | Lastname | Age |\n| --- | --- | --- |\n| Jill | Smith | 50 |\n| Eve | Jackson | 94 |\n\n'
@@ -148,3 +168,4 @@ def test_table():
     assert md(table_head_body) == '\n\n| Firstname | Lastname | Age |\n| --- | --- | --- |\n| Jill | Smith | 50 |\n| Eve | Jackson | 94 |\n\n'
     assert md(table_missing_text) == '\n\n|  | Lastname | Age |\n| --- | --- | --- |\n| Jill |  | 50 |\n| Eve | Jackson | 94 |\n\n'
     assert md(table_missing_head) == '\n\n|  |  |  |\n| --- | --- | --- |\n| Firstname | Lastname | Age |\n| Jill | Smith | 50 |\n| Eve | Jackson | 94 |\n\n'
+    assert md(table_body) == '\n\n|  |  |  |\n| --- | --- | --- |\n| Firstname | Lastname | Age |\n| Jill | Smith | 50 |\n| Eve | Jackson | 94 |\n\n'

tox.ini

@@ -0,0 +1,14 @@
+[tox]
+envlist = py38
+
+[testenv]
+deps =
+	pytest
+	flake8
+	restructuredtext_lint
+	Pygments
+commands =
+	pytest
+	flake8 --ignore=E501,W503 markdownify tests
+	restructuredtext-lint README.rst
+