Compare commits
2 Commits
0.14.0
...
feature/to
| Author | SHA1 | Date | |
|---|---|---|---|
|
e249e58818 | ||
|
|
2840653e29 |
5
.github/workflows/python-app.yml
vendored
5
.github/workflows/python-app.yml
vendored
@@ -23,10 +23,7 @@ jobs:
|
||||
- name: Install dependencies
|
||||
run: |
|
||||
python -m pip install --upgrade pip
|
||||
pip install --upgrade setuptools setuptools_scm wheel build tox
|
||||
pip install tox
|
||||
- name: Lint and test
|
||||
run: |
|
||||
tox
|
||||
- name: Build
|
||||
run: |
|
||||
python -m build -nwsx .
|
||||
|
||||
4
.github/workflows/python-publish.yml
vendored
4
.github/workflows/python-publish.yml
vendored
@@ -21,11 +21,11 @@ jobs:
|
||||
- name: Install dependencies
|
||||
run: |
|
||||
python -m pip install --upgrade pip
|
||||
pip install --upgrade setuptools setuptools_scm wheel build twine
|
||||
pip install setuptools wheel twine
|
||||
- name: Build and publish
|
||||
env:
|
||||
TWINE_USERNAME: ${{ secrets.PYPI_USERNAME }}
|
||||
TWINE_PASSWORD: ${{ secrets.PYPI_PASSWORD }}
|
||||
run: |
|
||||
python -m build -nwsx .
|
||||
python setup.py sdist bdist_wheel
|
||||
twine upload dist/*
|
||||
|
||||
@@ -1,2 +1 @@
|
||||
include README.rst
|
||||
prune tests
|
||||
|
||||
39
README.rst
39
README.rst
@@ -1,8 +1,8 @@
|
||||
|build| |version| |license| |downloads|
|
||||
|
||||
.. |build| image:: https://img.shields.io/github/actions/workflow/status/matthewwithanm/python-markdownify/python-app.yml?branch=develop
|
||||
.. |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/workflows/python-app.yml?query=workflow%3A%22Python+application%22
|
||||
: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
|
||||
@@ -87,11 +87,7 @@ strong_em_symbol
|
||||
sub_symbol, sup_symbol
|
||||
Define the chars that surround ``<sub>`` and ``<sup>`` text. Defaults to an
|
||||
empty string, because this is non-standard behavior. Could be something like
|
||||
``~`` and ``^`` to result in ``~sub~`` and ``^sup^``. If the value starts
|
||||
with ``<`` and ends with ``>``, it is treated as an HTML tag and a ``/`` is
|
||||
inserted after the ``<`` in the string used after the text; this allows
|
||||
specifying ``<sub>`` to use raw HTML in the output for subscripts, for
|
||||
example.
|
||||
``~`` and ``^`` to result in ``~sub~`` and ``^sup^``.
|
||||
|
||||
newline_style
|
||||
Defines the style of marking linebreaks (``<br>``) in markdown. The default
|
||||
@@ -127,11 +123,6 @@ escape_underscores
|
||||
If set to ``False``, do not escape ``_`` to ``\_`` in text.
|
||||
Defaults to ``True``.
|
||||
|
||||
escape_misc
|
||||
If set to ``True``, escape miscellaneous punctuation characters
|
||||
that sometimes have Markdown significance in text.
|
||||
Defaults to ``False``.
|
||||
|
||||
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
|
||||
@@ -165,12 +156,7 @@ Creating Custom Converters
|
||||
|
||||
If you have a special usecase that calls for a special conversion, you can
|
||||
always inherit from ``MarkdownConverter`` and override the method you want to
|
||||
change.
|
||||
The function that handles a HTML tag named ``abc`` is called
|
||||
``convert_abc(self, el, text, convert_as_inline)`` and returns a string
|
||||
containing the converted HTML tag.
|
||||
The ``MarkdownConverter`` object will handle the conversion based on the
|
||||
function names:
|
||||
change:
|
||||
|
||||
.. code:: python
|
||||
|
||||
@@ -187,24 +173,9 @@ function names:
|
||||
def md(html, **options):
|
||||
return ImageBlockConverter(**options).convert(html)
|
||||
|
||||
.. code:: python
|
||||
|
||||
from markdownify import MarkdownConverter
|
||||
|
||||
class IgnoreParagraphsConverter(MarkdownConverter):
|
||||
"""
|
||||
Create a custom MarkdownConverter that ignores paragraphs
|
||||
"""
|
||||
def convert_p(self, el, text, convert_as_inline):
|
||||
return ''
|
||||
|
||||
# Create shorthand method for conversion
|
||||
def md(html, **options):
|
||||
return IgnoreParagraphsConverter(**options).convert(html)
|
||||
|
||||
|
||||
Command Line Interface
|
||||
======================
|
||||
=====================
|
||||
|
||||
Use ``markdownify example.html > example.md`` or pipe input from stdin
|
||||
(``cat example.html | markdownify > example.md``).
|
||||
|
||||
@@ -7,8 +7,7 @@ import six
|
||||
convert_heading_re = re.compile(r'convert_h(\d+)')
|
||||
line_beginning_re = re.compile(r'^', re.MULTILINE)
|
||||
whitespace_re = re.compile(r'[\t ]+')
|
||||
all_whitespace_re = re.compile(r'[\t \r\n]+')
|
||||
newline_whitespace_re = re.compile(r'[\t \r\n]*[\r\n][\t \r\n]*')
|
||||
all_whitespace_re = re.compile(r'[\s]+')
|
||||
html_heading_re = re.compile(r'h[1-6]')
|
||||
|
||||
|
||||
@@ -44,22 +43,15 @@ def abstract_inline_conversion(markup_fn):
|
||||
"""
|
||||
This abstracts all simple inline tags like b, em, del, ...
|
||||
Returns a function that wraps the chomped text in a pair of the string
|
||||
that is returned by markup_fn, with '/' inserted in the string used after
|
||||
the text if it looks like an HTML tag. markup_fn is necessary to allow for
|
||||
that is returned by markup_fn. markup_fn is necessary to allow for
|
||||
references to self.strong_em_symbol etc.
|
||||
"""
|
||||
def implementation(self, el, text, convert_as_inline):
|
||||
markup_prefix = markup_fn(self)
|
||||
if markup_prefix.startswith('<') and markup_prefix.endswith('>'):
|
||||
markup_suffix = '</' + markup_prefix[1:]
|
||||
else:
|
||||
markup_suffix = markup_prefix
|
||||
if el.find_parent(['pre', 'code', 'kbd', 'samp']):
|
||||
return text
|
||||
markup = markup_fn(self)
|
||||
prefix, suffix, text = chomp(text)
|
||||
if not text:
|
||||
return ''
|
||||
return '%s%s%s%s%s' % (prefix, markup_prefix, text, markup_suffix, suffix)
|
||||
return '%s%s%s%s%s' % (prefix, markup, text, markup, suffix)
|
||||
return implementation
|
||||
|
||||
|
||||
@@ -67,23 +59,6 @@ def _todict(obj):
|
||||
return dict((k, getattr(obj, k)) for k in dir(obj) if not k.startswith('_'))
|
||||
|
||||
|
||||
def should_remove_whitespace_inside(el):
|
||||
"""Return to remove whitespace immediately inside a block-level element."""
|
||||
if not el or not el.name:
|
||||
return False
|
||||
if html_heading_re.match(el.name) is not None:
|
||||
return True
|
||||
return el.name in ('p', 'blockquote',
|
||||
'ol', 'ul', 'li',
|
||||
'table', 'thead', 'tbody', 'tfoot',
|
||||
'tr', 'td', 'th')
|
||||
|
||||
|
||||
def should_remove_whitespace_outside(el):
|
||||
"""Return to remove whitespace immediately outside a block-level element."""
|
||||
return should_remove_whitespace_inside(el) or (el and el.name == 'pre')
|
||||
|
||||
|
||||
class MarkdownConverter(object):
|
||||
class DefaultOptions:
|
||||
autolinks = True
|
||||
@@ -94,7 +69,6 @@ class MarkdownConverter(object):
|
||||
default_title = False
|
||||
escape_asterisks = True
|
||||
escape_underscores = True
|
||||
escape_misc = False
|
||||
heading_style = UNDERLINED
|
||||
keep_inline_images_in = []
|
||||
newline_style = SPACES
|
||||
@@ -137,23 +111,27 @@ class MarkdownConverter(object):
|
||||
if not children_only and (isHeading or isCell):
|
||||
convert_children_as_inline = True
|
||||
|
||||
# Remove whitespace-only textnodes just before, after or
|
||||
# inside block-level elements.
|
||||
should_remove_inside = should_remove_whitespace_inside(node)
|
||||
for el in node.children:
|
||||
# Only extract (remove) whitespace-only text node if any of the
|
||||
# conditions is true:
|
||||
# - el is the first element in its parent (block-level)
|
||||
# - el is the last element in its parent (block-level)
|
||||
# - el is adjacent to a block-level node
|
||||
can_extract = (should_remove_inside and (not el.previous_sibling
|
||||
or not el.next_sibling)
|
||||
or should_remove_whitespace_outside(el.previous_sibling)
|
||||
or should_remove_whitespace_outside(el.next_sibling))
|
||||
if (isinstance(el, NavigableString)
|
||||
and six.text_type(el).strip() == ''
|
||||
and can_extract):
|
||||
el.extract()
|
||||
# Remove whitespace-only textnodes in purely nested nodes
|
||||
def is_nested_node(el):
|
||||
return el and el.name in ['ol', 'ul', 'li',
|
||||
'table', 'thead', 'tbody', 'tfoot',
|
||||
'tr', 'td', 'th']
|
||||
|
||||
if is_nested_node(node):
|
||||
for el in node.children:
|
||||
# Only extract (remove) whitespace-only text node if any of the
|
||||
# conditions is true:
|
||||
# - el is the first element in its parent
|
||||
# - el is the last element in its parent
|
||||
# - el is adjacent to an nested node
|
||||
can_extract = (not el.previous_sibling
|
||||
or not el.next_sibling
|
||||
or is_nested_node(el.previous_sibling)
|
||||
or is_nested_node(el.next_sibling))
|
||||
if (isinstance(el, NavigableString)
|
||||
and six.text_type(el).strip() == ''
|
||||
and can_extract):
|
||||
el.extract()
|
||||
|
||||
# Convert the children first
|
||||
for el in node.children:
|
||||
@@ -162,13 +140,7 @@ class MarkdownConverter(object):
|
||||
elif isinstance(el, NavigableString):
|
||||
text += self.process_text(el)
|
||||
else:
|
||||
text_strip = text.rstrip('\n')
|
||||
newlines_left = len(text) - len(text_strip)
|
||||
next_text = self.process_tag(el, convert_children_as_inline)
|
||||
next_text_strip = next_text.lstrip('\n')
|
||||
newlines_right = len(next_text) - len(next_text_strip)
|
||||
newlines = '\n' * max(newlines_left, newlines_right)
|
||||
text = text_strip + newlines + next_text_strip
|
||||
text += self.process_tag(el, convert_children_as_inline)
|
||||
|
||||
if not children_only:
|
||||
convert_fn = getattr(self, 'convert_%s' % node.name, None)
|
||||
@@ -180,28 +152,21 @@ class MarkdownConverter(object):
|
||||
def process_text(self, el):
|
||||
text = six.text_type(el) or ''
|
||||
|
||||
# normalize whitespace if we're not inside a preformatted element
|
||||
if not el.find_parent('pre'):
|
||||
if self.options['wrap']:
|
||||
text = all_whitespace_re.sub(' ', text)
|
||||
else:
|
||||
text = newline_whitespace_re.sub('\n', text)
|
||||
text = whitespace_re.sub(' ', text)
|
||||
# dont remove any whitespace when handling pre or code in pre
|
||||
if not (el.parent.name == 'pre'
|
||||
or (el.parent.name == 'code'
|
||||
and el.parent.parent.name == 'pre')):
|
||||
text = whitespace_re.sub(' ', text)
|
||||
|
||||
# escape special characters if we're not inside a preformatted or code element
|
||||
if not el.find_parent(['pre', 'code', 'kbd', 'samp']):
|
||||
if el.parent.name != 'code' and el.parent.name != 'pre':
|
||||
text = self.escape(text)
|
||||
|
||||
# remove leading whitespace at the start or just after a
|
||||
# block-level element; remove traliing whitespace at the end
|
||||
# or just before a block-level element.
|
||||
if (should_remove_whitespace_outside(el.previous_sibling)
|
||||
or (should_remove_whitespace_inside(el.parent)
|
||||
and not el.previous_sibling)):
|
||||
text = text.lstrip()
|
||||
if (should_remove_whitespace_outside(el.next_sibling)
|
||||
or (should_remove_whitespace_inside(el.parent)
|
||||
and not el.next_sibling)):
|
||||
# remove trailing whitespaces if any of the following condition is true:
|
||||
# - current text node is the last node in li
|
||||
# - current text node is followed by an embedded list
|
||||
if (el.parent.name == 'li'
|
||||
and (not el.next_sibling
|
||||
or el.next_sibling.name in ['ul', 'ol'])):
|
||||
text = text.rstrip()
|
||||
|
||||
return text
|
||||
@@ -235,33 +200,18 @@ class MarkdownConverter(object):
|
||||
def escape(self, text):
|
||||
if not text:
|
||||
return ''
|
||||
if self.options['escape_misc']:
|
||||
text = re.sub(r'([\\&<`[>~=+|])', r'\\\1', text)
|
||||
# A sequence of one or more consecutive '-', preceded and
|
||||
# followed by whitespace or start/end of fragment, might
|
||||
# be confused with an underline of a header, or with a
|
||||
# list marker.
|
||||
text = re.sub(r'(\s|^)(-+(?:\s|$))', r'\1\\\2', text)
|
||||
# A sequence of up to six consecutive '#', preceded and
|
||||
# followed by whitespace or start/end of fragment, might
|
||||
# be confused with an ATX heading.
|
||||
text = re.sub(r'(\s|^)(#{1,6}(?:\s|$))', r'\1\\\2', text)
|
||||
# '.' or ')' preceded by up to nine digits might be
|
||||
# confused with a list item.
|
||||
text = re.sub(r'((?:\s|^)[0-9]{1,9})([.)](?:\s|$))', r'\1\\\2',
|
||||
text)
|
||||
if self.options['escape_asterisks']:
|
||||
text = text.replace('*', r'\*')
|
||||
if self.options['escape_underscores']:
|
||||
text = text.replace('_', r'\_')
|
||||
return text
|
||||
|
||||
def indent(self, text, columns):
|
||||
return line_beginning_re.sub(' ' * columns, text) if text else ''
|
||||
def indent(self, text, level):
|
||||
return line_beginning_re.sub('\t' * level, text) if text else ''
|
||||
|
||||
def underline(self, text, pad_char):
|
||||
text = (text or '').rstrip()
|
||||
return '\n\n%s\n%s\n\n' % (text, pad_char * len(text)) if text else ''
|
||||
return '%s\n%s\n\n' % (text, pad_char * len(text)) if text else ''
|
||||
|
||||
def convert_a(self, el, text, convert_as_inline):
|
||||
prefix, suffix, text = chomp(text)
|
||||
@@ -286,9 +236,9 @@ class MarkdownConverter(object):
|
||||
def convert_blockquote(self, el, text, convert_as_inline):
|
||||
|
||||
if convert_as_inline:
|
||||
return ' ' + text.strip() + ' '
|
||||
return text
|
||||
|
||||
return '\n' + (line_beginning_re.sub('> ', text.strip()) + '\n\n') 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:
|
||||
@@ -316,15 +266,14 @@ class MarkdownConverter(object):
|
||||
return text
|
||||
|
||||
style = self.options['heading_style'].lower()
|
||||
text = text.strip()
|
||||
text = text.rstrip()
|
||||
if style == UNDERLINED and n <= 2:
|
||||
line = '=' if n == 1 else '-'
|
||||
return self.underline(text, line)
|
||||
text = all_whitespace_re.sub(' ', text)
|
||||
hashes = '#' * n
|
||||
if style == ATX_CLOSED:
|
||||
return '\n%s %s %s\n\n' % (hashes, text, hashes)
|
||||
return '\n%s %s\n\n' % (hashes, text)
|
||||
return '%s %s %s\n\n' % (hashes, text, hashes)
|
||||
return '%s %s\n\n' % (hashes, text)
|
||||
|
||||
def convert_hr(self, el, text, convert_as_inline):
|
||||
return '\n\n---\n\n'
|
||||
@@ -358,8 +307,8 @@ class MarkdownConverter(object):
|
||||
el = el.parent
|
||||
if nested:
|
||||
# remove trailing newline if nested
|
||||
return '\n' + text.rstrip()
|
||||
return '\n\n' + text + ('\n' if before_paragraph else '')
|
||||
return '\n' + self.indent(text, 1).rstrip()
|
||||
return text + ('\n' if before_paragraph else '')
|
||||
|
||||
convert_ul = convert_list
|
||||
convert_ol = convert_list
|
||||
@@ -367,7 +316,7 @@ class MarkdownConverter(object):
|
||||
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") and str(parent.get("start")).isnumeric():
|
||||
if parent.get("start"):
|
||||
start = int(parent.get("start"))
|
||||
else:
|
||||
start = 1
|
||||
@@ -380,33 +329,17 @@ class MarkdownConverter(object):
|
||||
el = el.parent
|
||||
bullets = self.options['bullets']
|
||||
bullet = bullets[depth % len(bullets)]
|
||||
bullet = bullet + ' '
|
||||
text = (text or '').strip()
|
||||
text = self.indent(text, len(bullet))
|
||||
if text:
|
||||
text = bullet + text[len(bullet):]
|
||||
return '%s\n' % text
|
||||
return '%s %s\n' % (bullet, (text or '').strip())
|
||||
|
||||
def convert_p(self, el, text, convert_as_inline):
|
||||
if convert_as_inline:
|
||||
return ' ' + text.strip() + ' '
|
||||
return text
|
||||
if self.options['wrap']:
|
||||
# Preserve newlines (and preceding whitespace) resulting
|
||||
# from <br> tags. Newlines in the input have already been
|
||||
# replaced by spaces.
|
||||
lines = text.split('\n')
|
||||
new_lines = []
|
||||
for line in lines:
|
||||
line = line.lstrip()
|
||||
line_no_trailing = line.rstrip()
|
||||
trailing = line[len(line_no_trailing):]
|
||||
line = fill(line,
|
||||
width=self.options['wrap_width'],
|
||||
break_long_words=False,
|
||||
break_on_hyphens=False)
|
||||
new_lines.append(line + trailing)
|
||||
text = '\n'.join(new_lines)
|
||||
return '\n\n%s\n\n' % text if text else ''
|
||||
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:
|
||||
@@ -418,12 +351,6 @@ class MarkdownConverter(object):
|
||||
|
||||
return '\n```%s\n%s\n```\n' % (code_language, text)
|
||||
|
||||
def convert_script(self, el, text, convert_as_inline):
|
||||
return ''
|
||||
|
||||
def convert_style(self, el, text, convert_as_inline):
|
||||
return ''
|
||||
|
||||
convert_s = convert_del
|
||||
|
||||
convert_strong = convert_b
|
||||
@@ -437,42 +364,20 @@ class MarkdownConverter(object):
|
||||
def convert_table(self, el, text, convert_as_inline):
|
||||
return '\n\n' + text + '\n'
|
||||
|
||||
def convert_caption(self, el, text, convert_as_inline):
|
||||
return text + '\n'
|
||||
|
||||
def convert_figcaption(self, el, text, convert_as_inline):
|
||||
return '\n\n' + text + '\n\n'
|
||||
|
||||
def convert_td(self, el, text, convert_as_inline):
|
||||
colspan = 1
|
||||
if 'colspan' in el.attrs and el['colspan'].isdigit():
|
||||
colspan = int(el['colspan'])
|
||||
return ' ' + text.strip().replace("\n", " ") + ' |' * colspan
|
||||
return ' ' + text + ' |'
|
||||
|
||||
def convert_th(self, el, text, convert_as_inline):
|
||||
colspan = 1
|
||||
if 'colspan' in el.attrs and el['colspan'].isdigit():
|
||||
colspan = int(el['colspan'])
|
||||
return ' ' + text.strip().replace("\n", " ") + ' |' * colspan
|
||||
return ' ' + text + ' |'
|
||||
|
||||
def convert_tr(self, el, text, convert_as_inline):
|
||||
cells = el.find_all(['td', 'th'])
|
||||
is_headrow = (
|
||||
all([cell.name == 'th' for cell in cells])
|
||||
or (not el.previous_sibling and not el.parent.name == 'tbody')
|
||||
or (not el.previous_sibling and el.parent.name == 'tbody' and len(el.parent.parent.find_all(['thead'])) < 1)
|
||||
)
|
||||
is_headrow = all([cell.name == 'th' for cell in cells])
|
||||
overline = ''
|
||||
underline = ''
|
||||
if is_headrow and not el.previous_sibling:
|
||||
# first row and is headline: 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'
|
||||
underline += '| ' + ' | '.join(['---'] * len(cells)) + ' |' + '\n'
|
||||
elif (not el.previous_sibling
|
||||
and (el.parent.name == 'table'
|
||||
or (el.parent.name == 'tbody'
|
||||
|
||||
@@ -3,8 +3,7 @@
|
||||
import argparse
|
||||
import sys
|
||||
|
||||
from markdownify import markdownify, ATX, ATX_CLOSED, UNDERLINED, \
|
||||
SPACES, BACKSLASH, ASTERISK, UNDERSCORE
|
||||
from markdownify import markdownify
|
||||
|
||||
|
||||
def main(argv=sys.argv[1:]):
|
||||
@@ -29,23 +28,16 @@ def main(argv=sys.argv[1:]):
|
||||
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, UNDERLINED),
|
||||
parser.add_argument('--heading-style',
|
||||
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('--newline-style', default=SPACES,
|
||||
choices=(SPACES, BACKSLASH),
|
||||
help="Defines the style of <br> conversions: two spaces "
|
||||
"or backslash at the and of the line thet should break.")
|
||||
parser.add_argument('--code-language', default='',
|
||||
help="Defines the language that should be assumed for all "
|
||||
"'<pre>' sections.")
|
||||
|
||||
@@ -1,45 +0,0 @@
|
||||
[build-system]
|
||||
requires = ["setuptools>=61.2", "setuptools_scm[toml]>=3.4.3"]
|
||||
build-backend = "setuptools.build_meta"
|
||||
|
||||
[project]
|
||||
name = "markdownify"
|
||||
version = "0.14.0"
|
||||
authors = [{name = "Matthew Tretter", email = "m@tthewwithanm.com"}]
|
||||
description = "Convert HTML to markdown."
|
||||
readme = "README.rst"
|
||||
classifiers = [
|
||||
"Environment :: Web Environment",
|
||||
"Framework :: Django",
|
||||
"Intended Audience :: Developers",
|
||||
"License :: OSI Approved :: MIT License",
|
||||
"Operating System :: OS Independent",
|
||||
"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",
|
||||
]
|
||||
dependencies = [
|
||||
"beautifulsoup4>=4.9,<5",
|
||||
"six>=1.15,<2"
|
||||
]
|
||||
|
||||
[project.urls]
|
||||
Homepage = "http://github.com/matthewwithanm/python-markdownify"
|
||||
Download = "http://github.com/matthewwithanm/python-markdownify/tarball/master"
|
||||
|
||||
[project.scripts]
|
||||
markdownify = "markdownify.main:main"
|
||||
|
||||
[tool.setuptools]
|
||||
zip-safe = false
|
||||
include-package-data = true
|
||||
|
||||
[tool.setuptools.packages.find]
|
||||
include = ["markdownify", "markdownify.*"]
|
||||
namespaces = false
|
||||
|
||||
[tool.setuptools_scm]
|
||||
52
setup.py
Normal file
52
setup.py
Normal file
@@ -0,0 +1,52 @@
|
||||
#/usr/bin/env python
|
||||
import codecs
|
||||
import os
|
||||
from setuptools import setup, find_packages
|
||||
|
||||
|
||||
read = lambda filepath: codecs.open(filepath, 'r', 'utf-8').read()
|
||||
|
||||
pkgmeta = {
|
||||
'__title__': 'markdownify',
|
||||
'__author__': 'Matthew Tretter',
|
||||
'__version__': '0.11.2',
|
||||
}
|
||||
|
||||
read = lambda filepath: codecs.open(filepath, 'r', 'utf-8').read()
|
||||
|
||||
setup(
|
||||
name='markdownify',
|
||||
description='Convert HTML to markdown.',
|
||||
long_description=read(os.path.join(os.path.dirname(__file__), 'README.rst')),
|
||||
version=pkgmeta['__version__'],
|
||||
author=pkgmeta['__author__'],
|
||||
author_email='m@tthewwithanm.com',
|
||||
url='http://github.com/matthewwithanm/python-markdownify',
|
||||
download_url='http://github.com/matthewwithanm/python-markdownify/tarball/master',
|
||||
packages=find_packages(),
|
||||
zip_safe=False,
|
||||
include_package_data=True,
|
||||
install_requires=[
|
||||
'beautifulsoup4>=4.9,<5',
|
||||
'six>=1.15,<2',
|
||||
],
|
||||
classifiers=[
|
||||
'Environment :: Web Environment',
|
||||
'Framework :: Django',
|
||||
'Intended Audience :: Developers',
|
||||
'License :: OSI Approved :: MIT License',
|
||||
'Operating System :: OS Independent',
|
||||
'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'
|
||||
],
|
||||
entry_points={
|
||||
'console_scripts': [
|
||||
'markdownify = markdownify.main:main'
|
||||
]
|
||||
}
|
||||
)
|
||||
10
shell.nix
10
shell.nix
@@ -1,10 +0,0 @@
|
||||
{ pkgs ? import <nixpkgs> {} }:
|
||||
pkgs.mkShell {
|
||||
name = "python-shell";
|
||||
buildInputs = with pkgs; [
|
||||
python38
|
||||
python38Packages.tox
|
||||
python38Packages.setuptools
|
||||
python38Packages.virtualenv
|
||||
];
|
||||
}
|
||||
@@ -14,7 +14,7 @@ def test_chomp():
|
||||
|
||||
def test_nested():
|
||||
text = md('<p>This is an <a href="http://example.com/">example link</a>.</p>')
|
||||
assert text == '\n\nThis is an [example link](http://example.com/).\n\n'
|
||||
assert text == 'This is an [example link](http://example.com/).\n\n'
|
||||
|
||||
|
||||
def test_ignore_comments():
|
||||
|
||||
@@ -11,4 +11,3 @@ def test_soup():
|
||||
|
||||
def test_whitespace():
|
||||
assert md(' a b \t\t c ') == ' a b c '
|
||||
assert md(' a b \n\n c ') == ' a b\nc '
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
from markdownify import markdownify as md, ATX, ATX_CLOSED, BACKSLASH, SPACES, UNDERSCORE
|
||||
from markdownify import markdownify as md, ATX, ATX_CLOSED, BACKSLASH, UNDERSCORE
|
||||
|
||||
|
||||
def inline_tests(tag, markup):
|
||||
@@ -52,12 +52,6 @@ def test_b_spaces():
|
||||
|
||||
def test_blockquote():
|
||||
assert md('<blockquote>Hello</blockquote>') == '\n> Hello\n\n'
|
||||
assert md('<blockquote>\nHello\n</blockquote>') == '\n> Hello\n\n'
|
||||
|
||||
|
||||
def test_blockquote_with_nested_paragraph():
|
||||
assert md('<blockquote><p>Hello</p></blockquote>') == '\n> Hello\n\n'
|
||||
assert md('<blockquote><p>Hello</p><p>Hello again</p></blockquote>') == '\n> Hello\n> \n> Hello again\n\n'
|
||||
|
||||
|
||||
def test_blockquote_with_paragraph():
|
||||
@@ -66,7 +60,7 @@ def test_blockquote_with_paragraph():
|
||||
|
||||
def test_blockquote_nested():
|
||||
text = md('<blockquote>And she was like <blockquote>Hello</blockquote></blockquote>')
|
||||
assert text == '\n> And she was like\n> > Hello\n\n'
|
||||
assert text == '\n> And she was like \n> > Hello\n> \n> \n\n'
|
||||
|
||||
|
||||
def test_br():
|
||||
@@ -74,29 +68,9 @@ def test_br():
|
||||
assert md('a<br />b<br />c', newline_style=BACKSLASH) == 'a\\\nb\\\nc'
|
||||
|
||||
|
||||
def test_caption():
|
||||
assert md('TEXT<figure><figcaption>Caption</figcaption><span>SPAN</span></figure>') == 'TEXT\n\nCaption\n\nSPAN'
|
||||
assert md('<figure><span>SPAN</span><figcaption>Caption</figcaption></figure>TEXT') == 'SPAN\n\nCaption\n\nTEXT'
|
||||
|
||||
|
||||
def test_code():
|
||||
inline_tests('code', '`')
|
||||
assert md('<code>*this_should_not_escape*</code>') == '`*this_should_not_escape*`'
|
||||
assert md('<kbd>*this_should_not_escape*</kbd>') == '`*this_should_not_escape*`'
|
||||
assert md('<samp>*this_should_not_escape*</samp>') == '`*this_should_not_escape*`'
|
||||
assert md('<code><span>*this_should_not_escape*</span></code>') == '`*this_should_not_escape*`'
|
||||
assert md('<code>this should\t\tnormalize</code>') == '`this should normalize`'
|
||||
assert md('<code><span>this should\t\tnormalize</span></code>') == '`this should normalize`'
|
||||
assert md('<code>foo<b>bar</b>baz</code>') == '`foobarbaz`'
|
||||
assert md('<kbd>foo<i>bar</i>baz</kbd>') == '`foobarbaz`'
|
||||
assert md('<samp>foo<del> bar </del>baz</samp>') == '`foo bar baz`'
|
||||
assert md('<samp>foo <del>bar</del> baz</samp>') == '`foo bar baz`'
|
||||
assert md('<code>foo<em> bar </em>baz</code>') == '`foo bar baz`'
|
||||
assert md('<code>foo<code> bar </code>baz</code>') == '`foo bar baz`'
|
||||
assert md('<code>foo<strong> bar </strong>baz</code>') == '`foo bar baz`'
|
||||
assert md('<code>foo<s> bar </s>baz</code>') == '`foo bar baz`'
|
||||
assert md('<code>foo<sup>bar</sup>baz</code>', sup_symbol='^') == '`foobarbaz`'
|
||||
assert md('<code>foo<sub>bar</sub>baz</code>', sub_symbol='^') == '`foobarbaz`'
|
||||
assert md('<code>this_should_not_escape</code>') == '`this_should_not_escape`'
|
||||
|
||||
|
||||
def test_del():
|
||||
@@ -111,40 +85,29 @@ def test_em():
|
||||
inline_tests('em', '*')
|
||||
|
||||
|
||||
def test_header_with_space():
|
||||
assert md('<h3>\n\nHello</h3>') == '\n### Hello\n\n'
|
||||
assert md('<h3>Hello\n\n\nWorld</h3>') == '\n### Hello World\n\n'
|
||||
assert md('<h4>\n\nHello</h4>') == '\n#### Hello\n\n'
|
||||
assert md('<h5>\n\nHello</h5>') == '\n##### Hello\n\n'
|
||||
assert md('<h5>\n\nHello\n\n</h5>') == '\n##### Hello\n\n'
|
||||
assert md('<h5>\n\nHello \n\n</h5>') == '\n##### Hello\n\n'
|
||||
|
||||
|
||||
def test_h1():
|
||||
assert md('<h1>Hello</h1>') == '\n\nHello\n=====\n\n'
|
||||
assert md('<h1>Hello</h1>') == 'Hello\n=====\n\n'
|
||||
|
||||
|
||||
def test_h2():
|
||||
assert md('<h2>Hello</h2>') == '\n\nHello\n-----\n\n'
|
||||
assert md('<h2>Hello</h2>') == 'Hello\n-----\n\n'
|
||||
|
||||
|
||||
def test_hn():
|
||||
assert md('<h3>Hello</h3>') == '\n### Hello\n\n'
|
||||
assert md('<h4>Hello</h4>') == '\n#### Hello\n\n'
|
||||
assert md('<h5>Hello</h5>') == '\n##### Hello\n\n'
|
||||
assert md('<h6>Hello</h6>') == '\n###### Hello\n\n'
|
||||
assert md('<h3>Hello</h3>') == '### Hello\n\n'
|
||||
assert md('<h4>Hello</h4>') == '#### Hello\n\n'
|
||||
assert md('<h5>Hello</h5>') == '##### Hello\n\n'
|
||||
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) == '\n# First\n\n## Second\n\n### Third\n\n'
|
||||
assert md('X<h1>First</h1>', heading_style=ATX) == 'X\n# First\n\n'
|
||||
assert md('X<h1>First</h1>', heading_style=ATX_CLOSED) == 'X\n# First #\n\n'
|
||||
assert md('X<h1>First</h1>') == 'X\n\nFirst\n=====\n\n'
|
||||
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) == '\n# A P C #\n\n'
|
||||
assert md('<h1>A <p>P</p> C </h1>', heading_style=ATX) == '\n# A P C\n\n'
|
||||
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():
|
||||
@@ -160,12 +123,12 @@ def test_hn_nested_simple_tag():
|
||||
]
|
||||
|
||||
for tag, markdown in tag_to_markdown:
|
||||
assert md('<h3>A <' + tag + '>' + tag + '</' + tag + '> B</h3>') == '\n### A ' + markdown + ' B\n\n'
|
||||
assert md('<h3>A <' + tag + '>' + tag + '</' + tag + '> B</h3>') == '### A ' + markdown + ' B\n\n'
|
||||
|
||||
assert md('<h3>A <br>B</h3>', heading_style=ATX) == '\n### A 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) == '\n### A li1 li2 B\n\n'
|
||||
# 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():
|
||||
@@ -175,18 +138,18 @@ def test_hn_nested_img():
|
||||
("alt='Alt Text' title='Optional title'", "Alt Text", " \"Optional title\""),
|
||||
]
|
||||
for image_attributes, markdown, title in image_attributes_to_markdown:
|
||||
assert md('<h3>A <img src="/path/to/img.jpg" ' + image_attributes + '/> B</h3>') == '\n### A' + (' ' + markdown + ' ' if markdown else ' ') + 'B\n\n'
|
||||
assert md('<h3>A <img src="/path/to/img.jpg" ' + image_attributes + '/> B</h3>', keep_inline_images_in=['h3']) == '\n### A  B\n\n'
|
||||
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  B\n\n'
|
||||
|
||||
|
||||
def test_hn_atx_headings():
|
||||
assert md('<h1>Hello</h1>', heading_style=ATX) == '\n# Hello\n\n'
|
||||
assert md('<h2>Hello</h2>', heading_style=ATX) == '\n## Hello\n\n'
|
||||
assert md('<h1>Hello</h1>', heading_style=ATX) == '# Hello\n\n'
|
||||
assert md('<h2>Hello</h2>', heading_style=ATX) == '## Hello\n\n'
|
||||
|
||||
|
||||
def test_hn_atx_closed_headings():
|
||||
assert md('<h1>Hello</h1>', heading_style=ATX_CLOSED) == '\n# Hello #\n\n'
|
||||
assert md('<h2>Hello</h2>', heading_style=ATX_CLOSED) == '\n## Hello ##\n\n'
|
||||
assert md('<h1>Hello</h1>', heading_style=ATX_CLOSED) == '# Hello #\n\n'
|
||||
assert md('<h2>Hello</h2>', heading_style=ATX_CLOSED) == '## Hello ##\n\n'
|
||||
|
||||
|
||||
def test_head():
|
||||
@@ -196,7 +159,7 @@ def test_head():
|
||||
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>') == '\n\nHello\n\n---\n\nWorld\n\n'
|
||||
assert md('<p>Hello</p>\n<hr>\n<p>World</p>') == 'Hello\n\n\n\n\n---\n\n\nWorld\n\n'
|
||||
|
||||
|
||||
def test_i():
|
||||
@@ -213,51 +176,18 @@ def test_kbd():
|
||||
|
||||
|
||||
def test_p():
|
||||
assert md('<p>hello</p>') == '\n\nhello\n\n'
|
||||
assert md('<p>123456789 123456789</p>') == '\n\n123456789 123456789\n\n'
|
||||
assert md('<p>123456789\n\n\n123456789</p>') == '\n\n123456789\n123456789\n\n'
|
||||
assert md('<p>123456789\n\n\n123456789</p>', wrap=True, wrap_width=80) == '\n\n123456789 123456789\n\n'
|
||||
assert md('<p>123456789 123456789</p>', wrap=True, wrap_width=10) == '\n\n123456789\n123456789\n\n'
|
||||
assert md('<p><a href="https://example.com">Some long link</a></p>', wrap=True, wrap_width=10) == '\n\n[Some long\nlink](https://example.com)\n\n'
|
||||
assert md('<p>12345<br />67890</p>', wrap=True, wrap_width=10, newline_style=BACKSLASH) == '\n\n12345\\\n67890\n\n'
|
||||
assert md('<p>12345<br />67890</p>', wrap=True, wrap_width=50, newline_style=BACKSLASH) == '\n\n12345\\\n67890\n\n'
|
||||
assert md('<p>12345<br />67890</p>', wrap=True, wrap_width=10, newline_style=SPACES) == '\n\n12345 \n67890\n\n'
|
||||
assert md('<p>12345<br />67890</p>', wrap=True, wrap_width=50, newline_style=SPACES) == '\n\n12345 \n67890\n\n'
|
||||
assert md('<p>12345678901<br />12345</p>', wrap=True, wrap_width=10, newline_style=BACKSLASH) == '\n\n12345678901\\\n12345\n\n'
|
||||
assert md('<p>12345678901<br />12345</p>', wrap=True, wrap_width=50, newline_style=BACKSLASH) == '\n\n12345678901\\\n12345\n\n'
|
||||
assert md('<p>12345678901<br />12345</p>', wrap=True, wrap_width=10, newline_style=SPACES) == '\n\n12345678901 \n12345\n\n'
|
||||
assert md('<p>12345678901<br />12345</p>', wrap=True, wrap_width=50, newline_style=SPACES) == '\n\n12345678901 \n12345\n\n'
|
||||
assert md('<p>1234 5678 9012<br />67890</p>', wrap=True, wrap_width=10, newline_style=BACKSLASH) == '\n\n1234 5678\n9012\\\n67890\n\n'
|
||||
assert md('<p>1234 5678 9012<br />67890</p>', wrap=True, wrap_width=10, newline_style=SPACES) == '\n\n1234 5678\n9012 \n67890\n\n'
|
||||
assert md('First<p>Second</p><p>Third</p>Fourth') == 'First\n\nSecond\n\nThird\n\nFourth'
|
||||
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```\n*this_should_not_escape*\n```\n'
|
||||
assert md('<pre><span>*this_should_not_escape*</span></pre>') == '\n```\n*this_should_not_escape*\n```\n'
|
||||
assert md('<pre>\t\tthis should\t\tnot normalize</pre>') == '\n```\n\t\tthis should\t\tnot normalize\n```\n'
|
||||
assert md('<pre><span>\t\tthis should\t\tnot normalize</span></pre>') == '\n```\n\t\tthis should\t\tnot normalize\n```\n'
|
||||
assert md('<pre>foo<b>\nbar\n</b>baz</pre>') == '\n```\nfoo\nbar\nbaz\n```\n'
|
||||
assert md('<pre>foo<i>\nbar\n</i>baz</pre>') == '\n```\nfoo\nbar\nbaz\n```\n'
|
||||
assert md('<pre>foo\n<i>bar</i>\nbaz</pre>') == '\n```\nfoo\nbar\nbaz\n```\n'
|
||||
assert md('<pre>foo<i>\n</i>baz</pre>') == '\n```\nfoo\nbaz\n```\n'
|
||||
assert md('<pre>foo<del>\nbar\n</del>baz</pre>') == '\n```\nfoo\nbar\nbaz\n```\n'
|
||||
assert md('<pre>foo<em>\nbar\n</em>baz</pre>') == '\n```\nfoo\nbar\nbaz\n```\n'
|
||||
assert md('<pre>foo<code>\nbar\n</code>baz</pre>') == '\n```\nfoo\nbar\nbaz\n```\n'
|
||||
assert md('<pre>foo<strong>\nbar\n</strong>baz</pre>') == '\n```\nfoo\nbar\nbaz\n```\n'
|
||||
assert md('<pre>foo<s>\nbar\n</s>baz</pre>') == '\n```\nfoo\nbar\nbaz\n```\n'
|
||||
assert md('<pre>foo<sup>\nbar\n</sup>baz</pre>', sup_symbol='^') == '\n```\nfoo\nbar\nbaz\n```\n'
|
||||
assert md('<pre>foo<sub>\nbar\n</sub>baz</pre>', sub_symbol='^') == '\n```\nfoo\nbar\nbaz\n```\n'
|
||||
|
||||
|
||||
def test_script():
|
||||
assert md('foo <script>var foo=42;</script> bar') == 'foo bar'
|
||||
|
||||
|
||||
def test_style():
|
||||
assert md('foo <style>h1 { font-size: larger }</style> bar') == 'foo bar'
|
||||
assert md('<pre>this_should_not_escape</pre>') == '\n```\nthis_should_not_escape\n```\n'
|
||||
|
||||
|
||||
def test_s():
|
||||
@@ -282,13 +212,11 @@ def test_strong_em_symbol():
|
||||
def test_sub():
|
||||
assert md('<sub>foo</sub>') == 'foo'
|
||||
assert md('<sub>foo</sub>', sub_symbol='~') == '~foo~'
|
||||
assert md('<sub>foo</sub>', sub_symbol='<sub>') == '<sub>foo</sub>'
|
||||
|
||||
|
||||
def test_sup():
|
||||
assert md('<sup>foo</sup>') == 'foo'
|
||||
assert md('<sup>foo</sup>', sup_symbol='^') == '^foo^'
|
||||
assert md('<sup>foo</sup>', sup_symbol='<sup>') == '<sup>foo</sup>'
|
||||
|
||||
|
||||
def test_lang():
|
||||
@@ -303,13 +231,3 @@ def test_lang_callback():
|
||||
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'
|
||||
|
||||
|
||||
def test_spaces():
|
||||
assert md('<p> a b </p> <p> c d </p>') == '\n\na b\n\nc d\n\n'
|
||||
assert md('<p> <i>a</i> </p>') == '\n\n*a*\n\n'
|
||||
assert md('test <p> again </p>') == 'test\n\nagain\n\n'
|
||||
assert md('test <blockquote> text </blockquote> after') == 'test\n> text\n\nafter'
|
||||
assert md(' <ol> <li> x </li> <li> y </li> </ol> ') == '\n\n1. x\n2. y\n'
|
||||
assert md(' <ul> <li> x </li> <li> y </li> </ol> ') == '\n\n* x\n* y\n'
|
||||
assert md('test <pre> foo </pre> bar') == 'test\n```\n foo \n```\nbar'
|
||||
|
||||
@@ -1,5 +1,3 @@
|
||||
import warnings
|
||||
from bs4 import MarkupResemblesLocatorWarning
|
||||
from markdownify import markdownify as md
|
||||
|
||||
|
||||
@@ -14,7 +12,7 @@ def test_underscore():
|
||||
|
||||
|
||||
def test_xml_entities():
|
||||
assert md('&', escape_misc=True) == r'\&'
|
||||
assert md('&') == '&'
|
||||
|
||||
|
||||
def test_named_entities():
|
||||
@@ -27,49 +25,4 @@ def test_hexadecimal_entities():
|
||||
|
||||
|
||||
def test_single_escaping_entities():
|
||||
assert md('&amp;', escape_misc=True) == r'\&'
|
||||
|
||||
|
||||
def test_misc():
|
||||
# ignore the bs4 warning that "1.2" or "*" looks like a filename
|
||||
warnings.filterwarnings("ignore", category=MarkupResemblesLocatorWarning)
|
||||
|
||||
assert md('\\*', escape_misc=True) == r'\\\*'
|
||||
assert md('<foo>', escape_misc=True) == r'\<foo\>'
|
||||
assert md('# foo', escape_misc=True) == r'\# foo'
|
||||
assert md('#5', escape_misc=True) == r'#5'
|
||||
assert md('5#', escape_misc=True) == '5#'
|
||||
assert md('####### foo', escape_misc=True) == r'####### foo'
|
||||
assert md('> foo', escape_misc=True) == r'\> foo'
|
||||
assert md('~~foo~~', escape_misc=True) == r'\~\~foo\~\~'
|
||||
assert md('foo\n===\n', escape_misc=True) == 'foo\n\\=\\=\\=\n'
|
||||
assert md('---\n', escape_misc=True) == '\\---\n'
|
||||
assert md('- test', escape_misc=True) == r'\- test'
|
||||
assert md('x - y', escape_misc=True) == r'x \- y'
|
||||
assert md('test-case', escape_misc=True) == 'test-case'
|
||||
assert md('x-', escape_misc=True) == 'x-'
|
||||
assert md('-y', escape_misc=True) == '-y'
|
||||
assert md('+ x\n+ y\n', escape_misc=True) == '\\+ x\n\\+ y\n'
|
||||
assert md('`x`', escape_misc=True) == r'\`x\`'
|
||||
assert md('[text](link)', escape_misc=True) == r'\[text](link)'
|
||||
assert md('1. x', escape_misc=True) == r'1\. x'
|
||||
# assert md('1<span>.</span> x', escape_misc=True) == r'1\. x'
|
||||
assert md('<span>1.</span> x', escape_misc=True) == r'1\. x'
|
||||
assert md(' 1. x', escape_misc=True) == r' 1\. x'
|
||||
assert md('123456789. x', escape_misc=True) == r'123456789\. x'
|
||||
assert md('1234567890. x', escape_misc=True) == r'1234567890. x'
|
||||
assert md('A1. x', escape_misc=True) == r'A1. x'
|
||||
assert md('1.2', escape_misc=True) == r'1.2'
|
||||
assert md('not a number. x', escape_misc=True) == r'not a number. x'
|
||||
assert md('1) x', escape_misc=True) == r'1\) x'
|
||||
# assert md('1<span>)</span> x', escape_misc=True) == r'1\) x'
|
||||
assert md('<span>1)</span> x', escape_misc=True) == r'1\) x'
|
||||
assert md(' 1) x', escape_misc=True) == r' 1\) x'
|
||||
assert md('123456789) x', escape_misc=True) == r'123456789\) x'
|
||||
assert md('1234567890) x', escape_misc=True) == r'1234567890) x'
|
||||
assert md('(1) x', escape_misc=True) == r'(1) x'
|
||||
assert md('A1) x', escape_misc=True) == r'A1) x'
|
||||
assert md('1)x', escape_misc=True) == r'1)x'
|
||||
assert md('not a number) x', escape_misc=True) == r'not a number) x'
|
||||
assert md('|not table|', escape_misc=True) == r'\|not table\|'
|
||||
assert md(r'\ <foo> &amp; | ` `', escape_misc=False) == r'\ <foo> & | ` `'
|
||||
assert md('&amp;') == '&'
|
||||
|
||||
@@ -41,21 +41,16 @@ nested_ols = """
|
||||
|
||||
|
||||
def test_ol():
|
||||
assert md('<ol><li>a</li><li>b</li></ol>') == '\n\n1. a\n2. b\n'
|
||||
assert md('<ol start="3"><li>a</li><li>b</li></ol>') == '\n\n3. a\n4. b\n'
|
||||
assert md('foo<ol start="3"><li>a</li><li>b</li></ol>bar') == 'foo\n\n3. a\n4. b\n\nbar'
|
||||
assert md('<ol start="-1"><li>a</li><li>b</li></ol>') == '\n\n1. a\n2. b\n'
|
||||
assert md('<ol start="foo"><li>a</li><li>b</li></ol>') == '\n\n1. a\n2. b\n'
|
||||
assert md('<ol start="1.5"><li>a</li><li>b</li></ol>') == '\n\n1. a\n2. b\n'
|
||||
assert md('<ol start="1234"><li><p>first para</p><p>second para</p></li><li><p>third para</p><p>fourth para</p></li></ol>') == '\n\n1234. first para\n \n second para\n1235. third para\n \n fourth para\n'
|
||||
assert md('<ol><li>a</li><li>b</li></ol>') == '1. a\n2. b\n'
|
||||
assert md('<ol start="3"><li>a</li><li>b</li></ol>') == '3. a\n4. b\n'
|
||||
|
||||
|
||||
def test_nested_ols():
|
||||
assert md(nested_ols) == '\n\n1. 1\n 1. a\n 1. I\n 2. II\n 3. III\n 2. b\n 3. c\n2. 2\n3. 3\n'
|
||||
assert md(nested_ols) == '\n1. 1\n\t1. a\n\t\t1. I\n\t\t2. II\n\t\t3. III\n\t2. b\n\t3. c\n2. 2\n3. 3\n'
|
||||
|
||||
|
||||
def test_ul():
|
||||
assert md('<ul><li>a</li><li>b</li></ul>') == '\n\n* a\n* b\n'
|
||||
assert md('<ul><li>a</li><li>b</li></ul>') == '* a\n* b\n'
|
||||
assert md("""<ul>
|
||||
<li>
|
||||
a
|
||||
@@ -63,13 +58,11 @@ def test_ul():
|
||||
<li> b </li>
|
||||
<li> c
|
||||
</li>
|
||||
</ul>""") == '\n\n* a\n* b\n* c\n'
|
||||
assert md('<ul><li><p>first para</p><p>second para</p></li><li><p>third para</p><p>fourth para</p></li></ul>') == '\n\n* first para\n \n second para\n* third para\n \n fourth para\n'
|
||||
</ul>""") == '* a\n* b\n* c\n'
|
||||
|
||||
|
||||
def test_inline_ul():
|
||||
assert md('<p>foo</p><ul><li>a</li><li>b</li></ul><p>bar</p>') == '\n\nfoo\n\n* a\n* b\n\nbar\n\n'
|
||||
assert md('foo<ul><li>bar</li></ul>baz') == 'foo\n\n* bar\n\nbaz'
|
||||
assert md('<p>foo</p><ul><li>a</li><li>b</li></ul><p>bar</p>') == 'foo\n\n* a\n* b\n\nbar\n\n'
|
||||
|
||||
|
||||
def test_nested_uls():
|
||||
@@ -77,12 +70,12 @@ def test_nested_uls():
|
||||
Nested ULs should alternate bullet characters.
|
||||
|
||||
"""
|
||||
assert md(nested_uls) == '\n\n* 1\n + a\n - I\n - II\n - III\n + b\n + c\n* 2\n* 3\n'
|
||||
assert md(nested_uls) == '\n* 1\n\t+ a\n\t\t- I\n\t\t- II\n\t\t- III\n\t+ b\n\t+ c\n* 2\n* 3\n'
|
||||
|
||||
|
||||
def test_bullets():
|
||||
assert md(nested_uls, bullets='-') == '\n\n- 1\n - a\n - I\n - II\n - III\n - b\n - c\n- 2\n- 3\n'
|
||||
assert md(nested_uls, bullets='-') == '\n- 1\n\t- a\n\t\t- I\n\t\t- II\n\t\t- III\n\t- b\n\t- c\n- 2\n- 3\n'
|
||||
|
||||
|
||||
def test_li_text():
|
||||
assert md('<ul><li>foo <a href="#">bar</a></li><li>foo bar </li><li>foo <b>bar</b> <i>space</i>.</ul>') == '\n\n* foo [bar](#)\n* foo bar\n* foo **bar** *space*.\n'
|
||||
assert md('<ul><li>foo <a href="#">bar</a></li><li>foo bar </li><li>foo <b>bar</b> <i>space</i>.</ul>') == '* foo [bar](#)\n* foo bar\n* foo **bar** *space*.\n'
|
||||
|
||||
@@ -57,26 +57,6 @@ table_with_paragraphs = """<table>
|
||||
</tr>
|
||||
</table>"""
|
||||
|
||||
table_with_linebreaks = """<table>
|
||||
<tr>
|
||||
<th>Firstname</th>
|
||||
<th>Lastname</th>
|
||||
<th>Age</th>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>Jill</td>
|
||||
<td>Smith
|
||||
Jackson</td>
|
||||
<td>50</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>Eve</td>
|
||||
<td>Jackson
|
||||
Smith</td>
|
||||
<td>94</td>
|
||||
</tr>
|
||||
</table>"""
|
||||
|
||||
|
||||
table_with_header_column = """<table>
|
||||
<tr>
|
||||
@@ -119,28 +99,6 @@ table_head_body = """<table>
|
||||
</tbody>
|
||||
</table>"""
|
||||
|
||||
table_head_body_missing_head = """<table>
|
||||
<thead>
|
||||
<tr>
|
||||
<td>Firstname</td>
|
||||
<td>Lastname</td>
|
||||
<td>Age</td>
|
||||
</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 = """<table>
|
||||
<thead>
|
||||
<tr>
|
||||
@@ -201,54 +159,13 @@ table_body = """<table>
|
||||
</tbody>
|
||||
</table>"""
|
||||
|
||||
table_with_caption = """TEXT<table><caption>Caption</caption>
|
||||
<tbody><tr><td>Firstname</td>
|
||||
<td>Lastname</td>
|
||||
<td>Age</td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>"""
|
||||
|
||||
table_with_colspan = """<table>
|
||||
<tr>
|
||||
<th colspan="2">Name</th>
|
||||
<th>Age</th>
|
||||
</tr>
|
||||
<tr>
|
||||
<td colspan="1">Jill</td>
|
||||
<td>Smith</td>
|
||||
<td>50</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>Eve</td>
|
||||
<td>Jackson</td>
|
||||
<td>94</td>
|
||||
</tr>
|
||||
</table>"""
|
||||
|
||||
table_with_undefined_colspan = """<table>
|
||||
<tr>
|
||||
<th colspan="undefined">Name</th>
|
||||
<th>Age</th>
|
||||
</tr>
|
||||
<tr>
|
||||
<td colspan="-1">Jill</td>
|
||||
<td>Smith</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'
|
||||
assert md(table_with_html_content) == '\n\n| Firstname | Lastname | Age |\n| --- | --- | --- |\n| **Jill** | *Smith* | [50](#) |\n| Eve | Jackson | 94 |\n\n'
|
||||
assert md(table_with_paragraphs) == '\n\n| Firstname | Lastname | Age |\n| --- | --- | --- |\n| Jill | Smith | 50 |\n| Eve | Jackson | 94 |\n\n'
|
||||
assert md(table_with_linebreaks) == '\n\n| Firstname | Lastname | Age |\n| --- | --- | --- |\n| Jill | Smith Jackson | 50 |\n| Eve | Jackson Smith | 94 |\n\n'
|
||||
assert md(table_with_header_column) == '\n\n| Firstname | Lastname | Age |\n| --- | --- | --- |\n| Jill | Smith | 50 |\n| Eve | Jackson | 94 |\n\n'
|
||||
assert md(table_head_body) == '\n\n| Firstname | Lastname | Age |\n| --- | --- | --- |\n| Jill | Smith | 50 |\n| Eve | Jackson | 94 |\n\n'
|
||||
assert md(table_head_body_missing_head) == '\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| Firstname | Lastname | Age |\n| --- | --- | --- |\n| Jill | Smith | 50 |\n| Eve | Jackson | 94 |\n\n'
|
||||
assert md(table_body) == '\n\n| Firstname | Lastname | Age |\n| --- | --- | --- |\n| Jill | Smith | 50 |\n| Eve | Jackson | 94 |\n\n'
|
||||
assert md(table_with_caption) == 'TEXT\n\nCaption\n| Firstname | Lastname | Age |\n| --- | --- | --- |\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_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'
|
||||
|
||||
Reference in New Issue
Block a user