85ef82e083
* feat: add basic type stubs * feat: add types for constants * feat: add type for `MarkdownConverter` class * ci: add basic job for checking types * feat: add new constant * ci: install types as required * ci: install types package manually * test: add strict coverage for types * fix: allow `strip_document` to be `None` * feat: expand types for MarkdownConverter * fix: do not use `Unpack` as it requires Python 3.12 * feat: define `MarkdownConverter#convert_soup` * feat: improve type for `code_language_callback` * chore: add end-of-file newline * refactor: use `Union` for now
71 lines
2.1 KiB
Python
71 lines
2.1 KiB
Python
from markdownify import markdownify, ASTERISK, BACKSLASH, LSTRIP, RSTRIP, SPACES, STRIP, UNDERLINED, UNDERSCORE, MarkdownConverter
|
|
from bs4 import BeautifulSoup
|
|
from typing import Union
|
|
|
|
markdownify("<p>Hello</p>") == "Hello" # test default of STRIP
|
|
markdownify("<p>Hello</p>", strip_document=LSTRIP) == "Hello\n\n"
|
|
markdownify("<p>Hello</p>", strip_document=RSTRIP) == "\n\nHello"
|
|
markdownify("<p>Hello</p>", strip_document=STRIP) == "Hello"
|
|
markdownify("<p>Hello</p>", strip_document=None) == "\n\nHello\n\n"
|
|
|
|
# default options
|
|
MarkdownConverter(
|
|
autolinks=True,
|
|
bs4_options='html.parser',
|
|
bullets='*+-',
|
|
code_language='',
|
|
code_language_callback=None,
|
|
convert=None,
|
|
default_title=False,
|
|
escape_asterisks=True,
|
|
escape_underscores=True,
|
|
escape_misc=False,
|
|
heading_style=UNDERLINED,
|
|
keep_inline_images_in=[],
|
|
newline_style=SPACES,
|
|
strip=None,
|
|
strip_document=STRIP,
|
|
strip_pre=STRIP,
|
|
strong_em_symbol=ASTERISK,
|
|
sub_symbol='',
|
|
sup_symbol='',
|
|
table_infer_header=False,
|
|
wrap=False,
|
|
wrap_width=80,
|
|
).convert("")
|
|
|
|
# custom options
|
|
MarkdownConverter(
|
|
strip_document=None,
|
|
bullets="-",
|
|
escape_asterisks=True,
|
|
escape_underscores=True,
|
|
escape_misc=True,
|
|
autolinks=True,
|
|
default_title=True,
|
|
newline_style=BACKSLASH,
|
|
sup_symbol='^',
|
|
sub_symbol='^',
|
|
keep_inline_images_in=['h3'],
|
|
wrap=True,
|
|
wrap_width=80,
|
|
strong_em_symbol=UNDERSCORE,
|
|
code_language='python',
|
|
code_language_callback=None
|
|
).convert("")
|
|
|
|
html = '<b>test</b>'
|
|
soup = BeautifulSoup(html, 'html.parser')
|
|
MarkdownConverter().convert_soup(soup) == '**test**'
|
|
|
|
|
|
def callback(el: BeautifulSoup) -> Union[str, None]:
|
|
return el['class'][0] if el.has_attr('class') else None
|
|
|
|
|
|
MarkdownConverter(code_language_callback=callback).convert("")
|
|
MarkdownConverter(code_language_callback=lambda el: None).convert("")
|
|
|
|
markdownify('<pre class="python">test\n foo\nbar</pre>', code_language_callback=callback)
|
|
markdownify('<pre class="python">test\n foo\nbar</pre>', code_language_callback=lambda el: None)
|