Cyclic0007/python-markdownify
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge branch 'develop'

Browse Source
This commit is contained in:
AlexVonB
2020-08-09 21:20:44 +02:00
parent 53ba0daa77 aceced68eb
commit e9cc01938a
6 changed files with 102 additions and 26 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
.gitignore vendored
View File

@@ -1,5 +1,7 @@
*.pyc
*.egg
.eggs/
*.egg-info/
.DS_Store
/.env
/dist

21
LICENSE Normal file
View File

@@ -0,0 +1,21 @@
The MIT License (MIT)
Copyright 2012-2018 Matthew Tretter
Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal
in the Software without restriction, including without limitation the rights
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:
The above copyright notice and this permission notice shall be included in all
copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
SOFTWARE.

38
markdownify/__init__.py
View File

@@ -1,5 +1,6 @@
from bs4 import BeautifulSoup, NavigableString
import re
import six
convert_heading_re = re.compile(r'convert_h(\d+)')
@@ -22,6 +23,19 @@ def escape(text):
return text.replace('_', r'\_')
def chomp(text):
"""
If the text in an inline tag like b, a, or em contains a leading or trailing
space, strip the string and return a space as suffix of prefix, if needed.
This function is used to prevent conversions like
<b> foo</b> => ** foo**
"""
prefix = ' ' if text and text[0] == ' ' else ''
suffix = ' ' if text and text[-1] == ' ' else ''
text = text.strip()
return (prefix, suffix, text)
def _todict(obj):
return dict((k, getattr(obj, k)) for k in dir(obj) if not k.startswith('_'))
@@ -52,7 +66,7 @@ class MarkdownConverter(object):
# 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)
soup = BeautifulSoup(html, 'html.parser')
return self.process_tag(soup.find(id=FRAGMENT_ID), children_only=True)
def process_tag(self, node, children_only=False):
@@ -61,7 +75,7 @@ class MarkdownConverter(object):
# Convert the children first
for el in node.children:
if isinstance(el, NavigableString):
text += self.process_text(unicode(el))
text += self.process_text(six.text_type(el))
else:
text += self.process_tag(el)
@@ -109,13 +123,16 @@ class MarkdownConverter(object):
return '%s\n%s\n\n' % (text, pad_char * len(text)) if text else ''
def convert_a(self, el, text):
prefix, suffix, text = chomp(text)
if not text:
return ''
href = el.get('href')
title = el.get('title')
if self.options['autolinks'] and text == href and not title:
# Shortcut syntax
return '<%s>' % href
title_part = ' "%s"' % title.replace('"', r'\"') if title else ''
return '[%s](%s%s)' % (text or '', href, title_part) if href else text or ''
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)
@@ -127,7 +144,10 @@ class MarkdownConverter(object):
return ' \n'
def convert_em(self, el, text):
return '*%s*' % text if text else ''
prefix, suffix, text = chomp(text)
if not text:
return ''
return '%s*%s*%s' % (prefix, text, suffix)
def convert_hn(self, n, el, text):
style = self.options['heading_style']
@@ -151,8 +171,9 @@ class MarkdownConverter(object):
break
el = el.parent
if nested:
text = '\n' + self.indent(text, 1)
return text
# remove trailing newline if nested
return '\n' + self.indent(text, 1).rstrip()
return '\n' + text + '\n'
convert_ul = convert_list
convert_ol = convert_list
@@ -175,7 +196,10 @@ class MarkdownConverter(object):
return '%s\n\n' % text if text else ''
def convert_strong(self, el, text):
return '**%s**' % text if text else ''
prefix, suffix, text = chomp(text)
if not text:
return ''
return '%s**%s**%s' % (prefix, text, suffix)
def convert_img(self, el, text):
alt = el.attrs.get('alt', None) or ''

8
markdownify/pkgmeta.py
View File

@@ -1,8 +0,0 @@
pkgmeta = dict(
__title__='markdownify',
__author__='Matthew Tretter',
__version__='0.4.0',
)
globals().update(pkgmeta)
__all__ = pkgmeta.keys()

13
setup.py
View File

@@ -7,10 +7,11 @@ from setuptools.command.test import test as TestCommand, Command
read = lambda filepath: codecs.open(filepath, 'r', 'utf-8').read()
pkgmeta = {}
execfile(os.path.join(os.path.dirname(__file__), 'markdownify', 'pkgmeta.py'),
pkgmeta)
pkgmeta = {
'__title__': 'markdownify',
'__author__': 'Matthew Tretter',
'__version__': '0.4.1',
}
class PyTest(TestCommand):
@@ -75,13 +76,13 @@ setup(
'pytest',
],
install_requires=[
'beautifulsoup4',
'beautifulsoup4', 'six'
],
classifiers=[
'Environment :: Web Environment',
'Framework :: Django',
'Intended Audience :: Developers',
'License :: OSI Approved :: BSD License',
'License :: OSI Approved :: MIT License',
'Operating System :: OS Independent',
'Programming Language :: Python :: 2.5',
'Programming Language :: Python :: 2.6',

46
tests/test_conversions.py
View File

@@ -2,7 +2,7 @@ from markdownify import markdownify as md, ATX, ATX_CLOSED
import re
nested_uls = re.sub('\s+', '', """
nested_uls = re.sub(r'\s+', '', """
<ul>
<li>1
<ul>
@@ -22,10 +22,28 @@ nested_uls = re.sub('\s+', '', """
</ul>""")
def test_chomp():
assert md(' <b></b> ') == ' '
assert md(' <b> </b> ') == ' '
assert md(' <b> </b> ') == ' '
assert md(' <b> </b> ') == ' '
assert md(' <b>s </b> ') == ' **s** '
assert md(' <b> s</b> ') == ' **s** '
assert md(' <b> s </b> ') == ' **s** '
assert md(' <b> s </b> ') == ' **s** '
def test_a():
assert md('<a href="http://google.com">Google</a>') == '[Google](http://google.com)'
def test_a_spaces():
assert md('foo <a href="http://google.com">Google</a> bar') == 'foo [Google](http://google.com) bar'
assert md('foo<a href="http://google.com"> Google</a> bar') == 'foo [Google](http://google.com) bar'
assert md('foo <a href="http://google.com">Google </a>bar') == 'foo [Google](http://google.com) bar'
assert md('foo <a href="http://google.com"></a> bar') == 'foo bar'
def test_a_with_title():
text = md('<a href="http://google.com" title="The &quot;Goog&quot;">Google</a>')
assert text == r'[Google](http://google.com "The \"Goog\"")'
@@ -45,6 +63,13 @@ def test_b():
assert md('<b>Hello</b>') == '**Hello**'
def test_b_spaces():
assert md('foo <b>Hello</b> bar') == 'foo **Hello** bar'
assert md('foo<b> Hello</b> bar') == 'foo **Hello** bar'
assert md('foo <b>Hello </b>bar') == 'foo **Hello** bar'
assert md('foo <b></b> bar') == 'foo bar'
def test_blockquote():
assert md('<blockquote>Hello</blockquote>').strip() == '> Hello'
@@ -62,6 +87,13 @@ def test_em():
assert md('<em>Hello</em>') == '*Hello*'
def test_em_spaces():
assert md('foo <em>Hello</em> bar') == 'foo *Hello* bar'
assert md('foo<em> Hello</em> bar') == 'foo *Hello* bar'
assert md('foo <em>Hello </em>bar') == 'foo *Hello* bar'
assert md('foo <em></em> bar') == 'foo bar'
def test_h1():
assert md('<h1>Hello</h1>') == 'Hello\n=====\n\n'
@@ -90,7 +122,7 @@ def test_i():
def test_ol():
assert md('<ol><li>a</li><li>b</li></ol>') == '1. a\n2. b\n'
assert md('<ol><li>a</li><li>b</li></ol>') == '\n1. a\n2. b\n\n'
def test_p():
@@ -102,7 +134,11 @@ def test_strong():
def test_ul():
assert md('<ul><li>a</li><li>b</li></ul>') == '* a\n* b\n'
assert md('<ul><li>a</li><li>b</li></ul>') == '\n* a\n* b\n\n'
def test_inline_ul():
assert md('<p>foo</p><ul><li>a</li><li>b</li></ul><p>bar</p>') == 'foo\n\n\n* a\n* b\n\nbar\n\n'
def test_nested_uls():
@@ -110,11 +146,11 @@ def test_nested_uls():
Nested ULs should alternate bullet characters.
"""
assert md(nested_uls) == '* 1\n\t+ a\n\t\t- I\n\t\t- II\n\t\t- III\n\t\t\n\t+ b\n\t+ c\n\t\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\n'
def test_bullets():
assert md(nested_uls, bullets='-') == '- 1\n\t- a\n\t\t- I\n\t\t- II\n\t\t- III\n\t\t\n\t- b\n\t- c\n\t\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\n'
def test_img():