Merge branch 'develop'

Fix parsing corrupt html

.github/workflows/python-app.yml

@@ -0,0 +1,33 @@
+# This workflow will install Python dependencies, run tests and lint with a single version of Python
+# For more information see: https://help.github.com/actions/language-and-framework-guides/using-python-with-github-actions
+
+name: Python application
+
+on:
+  push:
+    branches: [ develop ]
+  pull_request:
+    branches: [ develop ]
+
+jobs:
+  build:
+
+    runs-on: ubuntu-latest
+
+    steps:
+    - uses: actions/checkout@v2
+    - name: Set up Python 3.6
+      uses: actions/setup-python@v2
+      with:
+        python-version: 3.6
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install flake8==2.5.4 pytest
+        if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
+    - name: Lint with flake8
+      run: |
+        python setup.py lint
+    - name: Test with pytest
+      run: |
+        python setup.py test

README.rst

@@ -1,3 +1,21 @@
+|build| |version| |license| |downloads|
+
+.. |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?query=workflow%3A%22Python+application%22
+
+.. |version| image:: https://img.shields.io/pypi/v/markdownify
+    :alt: Pypi version
+    :target: https://pypi.org/project/markdownify/
+
+.. |license| image:: https://img.shields.io/pypi/l/markdownify
+    :alt: License
+    :target: https://github.com/matthewwithanm/python-markdownify/blob/develop/LICENSE
+
+.. |downloads| image:: https://pepy.tech/badge/markdownify
+    :alt: Pypi Downloads
+    :target: https://pepy.tech/project/markdownify
+
 Installation
 ============
 

markdownify/__init__.py

@@ -6,8 +6,6 @@ import six
 convert_heading_re = re.compile(r'convert_h(\d+)')
 line_beginning_re = re.compile(r'^', re.MULTILINE)
 whitespace_re = re.compile(r'[\r\n\s\t ]+')
-FRAGMENT_ID = '__MARKDOWNIFY_WRAPPER__'
-wrapped = '<div id="%s">%%s</div>' % FRAGMENT_ID
 
 
 # Heading styles
@@ -62,12 +60,8 @@ class MarkdownConverter(object):
                              ' convert, but not both.')
 
     def convert(self, html):
-        # We want to take advantage of the html5 parsing, but we don't actually
-        # 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, 'html.parser')
-        return self.process_tag(soup.find(id=FRAGMENT_ID), children_only=True)
+        return self.process_tag(soup, children_only=True)
 
     def process_tag(self, node, children_only=False):
         text = ''
@@ -181,7 +175,11 @@ class MarkdownConverter(object):
     def convert_li(self, el, text):
         parent = el.parent
         if parent is not None and parent.name == 'ol':
-            bullet = '%s.' % (parent.index(el) + 1)
+            if parent.get("start"):
+                start = int(parent.get("start"))
+            else:
+                start = 1
+            bullet = '%s.' % (start + parent.index(el))
         else:
             depth = -1
             while el:

setup.py

@@ -10,7 +10,7 @@ read = lambda filepath: codecs.open(filepath, 'r', 'utf-8').read()
 pkgmeta = {
     '__title__': 'markdownify',
     '__author__': 'Matthew Tretter',
-    '__version__': '0.5.1',
+    '__version__': '0.5.3',
 }
 
 

tests/test_conversions.py

@@ -123,6 +123,7 @@ def test_i():
 
 def test_ol():
     assert md('<ol><li>a</li><li>b</li></ol>') == '\n1. a\n2. b\n\n'
+    assert md('<ol start="3"><li>a</li><li>b</li></ol>') == '\n3. a\n4. b\n\n'
 
 
 def test_p():
@@ -156,3 +157,7 @@ def test_bullets():
 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")'
     assert md('<img src="/path/to/img.jpg" alt="Alt text" />') == '![Alt text](/path/to/img.jpg)'
+
+
+def test_div():
+    assert md('Hello</div> World') == 'Hello World'