Basic conversion skeleton

markdownify/__init__.py

@@ -0,0 +1,42 @@
+from lxml.etree import tostring
+from lxml.html.soupparser import fromstring
+
+
+class MarkdownConverter(object):
+    def __init__(self, strip=None, keep=None):
+        if strip is not None and keep is not None:
+            raise ValueError('You may specify either tags to strip or tags to'
+                    ' keep, but not both.')
+        self.strip = strip
+        self.keep = keep
+
+    def convert(self, html):
+        soup = fromstring(html)
+        self.convert_tag(soup)
+        return soup.text
+
+    def convert_tag(self, node):
+        text = node.text or ''
+
+        # Convert the children first
+        for el in node.findall('*'):
+            self.convert_tag(el)
+
+            convert_fn = getattr(self, 'convert_%s' % el.tag, None)
+            tail = el.tail or ''
+            el.tail = ''
+
+            if convert_fn:
+                text += convert_fn(el)
+            else:
+                text += el.text or ''
+
+            text += tail
+
+        node.clear()
+        node.text = text
+
+
+def markdownify(html, strip=None, keep=None):
+    converter = MarkdownConverter(strip, keep)
+    return converter.convert(html)

markdownify/version.py

@@ -0,0 +1 @@
+__version__ = '0.1.0'

runtests.py

@@ -0,0 +1,5 @@
+#!/usr/bin/env python
+from nose.core import run, collector
+
+if __name__ == '__main__':
+    run()

setup.py

@@ -0,0 +1,44 @@
+#/usr/bin/env python
+import codecs
+import os
+from setuptools import setup, find_packages
+
+
+read = lambda filepath: codecs.open(filepath, 'r', 'utf-8').read()
+execfile(os.path.join(os.path.dirname(__file__), 'markdownify', 'version.py'))
+
+
+setup(
+    name='markdownify',
+    description='Convert HTML to markdown.',
+    long_description=read(os.path.join(os.path.dirname(__file__), 'README.rst')),
+    version=__version__,
+    author='Matthew Tretter',
+    author_email='matthew@exanimo.com',
+    url='http://github.com/matthewwithanm/markdownify',
+    download_url='http://github.com/matthewwithanm/markdownify/tarball/master',
+    packages=find_packages(),
+    zip_safe=False,
+    include_package_data=True,
+    tests_require=[
+        'nose',
+        'unittest2',
+    ],
+    install_requires=[
+        'lxml',
+        'BeautifulSoup',
+    ],
+    classifiers=[
+        'Environment :: Web Environment',
+        'Framework :: Django',
+        'Intended Audience :: Developers',
+        'License :: OSI Approved :: BSD License',
+        'Operating System :: OS Independent',
+        'Programming Language :: Python :: 2.5',
+        'Programming Language :: Python :: 2.6',
+        'Programming Language :: Python :: 2.7',
+        'Topic :: Utilities'
+    ],
+    setup_requires=[],
+    test_suite='runtests.collector',
+)

tests.py

@@ -0,0 +1,11 @@
+import unittest
+from markdownify import markdownify as md
+
+
+class BasicTests(unittest.TestCase):
+
+    def test_single_tag(self):
+        self.assertEqual(md('<span>Hello</span>'), 'Hello')
+
+    def test_soup(self):
+        self.assertEqual(md('<div><span>Hello</div></span>'), 'Hello')