From 2b22d239ad594ff6fbe0d49ad5ba27a6e97115fb Mon Sep 17 00:00:00 2001
From: chrispy <chrispy@synopsys.com>
Date: Mon, 15 Jan 2024 07:59:39 -0500
Subject: [PATCH 01/13] avoid text normalization/escaping in any
 preformatted/code context

Signed-off-by: chrispy <chrispy@synopsys.com>
---
 markdownify/__init__.py   |  9 ++++-----
 tests/test_conversions.py | 12 ++++++++++--
 2 files changed, 14 insertions(+), 7 deletions(-)

diff --git a/markdownify/__init__.py b/markdownify/__init__.py
index e15ecd4..bf765ec 100644
--- a/markdownify/__init__.py
+++ b/markdownify/__init__.py
@@ -152,13 +152,12 @@ def is_nested_node(el):
     def process_text(self, el):
         text = six.text_type(el) or ''
 
-        # 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')):
+        # normalize whitespace if we're not inside a preformatted element
+        if not el.find_parent('pre'):
             text = whitespace_re.sub(' ', text)
 
-        if el.parent.name != 'code' and el.parent.name != 'pre':
+        # escape special characters if we're not inside a preformatted or code element
+        if not el.find_parent(['pre', 'code', 'kbd', 'samp']):
             text = self.escape(text)
 
         # remove trailing whitespaces if any of the following condition is true:
diff --git a/tests/test_conversions.py b/tests/test_conversions.py
index da78649..1ecaf3c 100644
--- a/tests/test_conversions.py
+++ b/tests/test_conversions.py
@@ -70,7 +70,12 @@ def test_br():
 
 def test_code():
     inline_tests('code', '`')
-    assert md('<code>this_should_not_escape</code>') == '`this_should_not_escape`'
+    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`'
 
 
 def test_del():
@@ -187,7 +192,10 @@ def test_p():
 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```\nthis_should_not_escape\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'
 
 
 def test_s():

From 60967c1c9563405a06ebae2735a049e37258b689 Mon Sep 17 00:00:00 2001
From: "Thomas L. Kjeldsen" <tlk@users.noreply.github.com>
Date: Mon, 11 Mar 2024 21:07:24 +0100
Subject: [PATCH 02/13] ignore script and style content (such as css and
 javascript) (#112)

---
 markdownify/__init__.py   | 6 ++++++
 tests/test_conversions.py | 8 ++++++++
 2 files changed, 14 insertions(+)

diff --git a/markdownify/__init__.py b/markdownify/__init__.py
index bf765ec..151a222 100644
--- a/markdownify/__init__.py
+++ b/markdownify/__init__.py
@@ -350,6 +350,12 @@ def convert_pre(self, el, text, convert_as_inline):
 
         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
diff --git a/tests/test_conversions.py b/tests/test_conversions.py
index 1ecaf3c..5c6ec06 100644
--- a/tests/test_conversions.py
+++ b/tests/test_conversions.py
@@ -198,6 +198,14 @@ def test_pre():
     assert md('<pre><span>\t\tthis  should\t\tnot  normalize</span></pre>') == '\n```\n\t\tthis  should\t\tnot  normalize\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'
+
+
 def test_s():
     inline_tests('s', '~~')
 

From a2f82678f762061527473692b6a0ac7287152959 Mon Sep 17 00:00:00 2001
From: G <17325189+GeeCastro@users.noreply.github.com>
Date: Mon, 11 Mar 2024 20:10:08 +0000
Subject: [PATCH 03/13] Add no css example to readme (#111)

* Add no css example

---------

Co-authored-by: G <17325189+Chichilele@users.noreply.github.com>
---
 README.rst | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/README.rst b/README.rst
index 06f319b..21a5972 100644
--- a/README.rst
+++ b/README.rst
@@ -173,6 +173,22 @@ change:
     def md(html, **options):
         return ImageBlockConverter(**options).convert(html)
 
+.. code:: python
+
+    from markdownify import MarkdownConverter
+
+    class NoCssConverter(MarkdownConverter):
+        """
+        Create a custom MarkdownConverter that removes the CSS code by ignoring the `style` tag
+        """
+        def convert_style(self, el, text, convert_as_inline):
+            return ''
+
+    # Create shorthand method for conversion
+    def md(html, **options):
+        return NoCssConverter(**options).convert(html)
+
+
 
 Command Line Interface
 ======================

From f33ccd7c1aef77dcfc4751715f1008fa8d519b46 Mon Sep 17 00:00:00 2001
From: Veronika Butkevich <13301101+5yato4ok@users.noreply.github.com>
Date: Tue, 26 Mar 2024 20:46:30 +0100
Subject: [PATCH 04/13] Fix newline start in header tags (#89)

* Fix newline start in header tags
---
 markdownify/__init__.py   | 2 +-
 tests/test_conversions.py | 8 ++++++++
 2 files changed, 9 insertions(+), 1 deletion(-)

diff --git a/markdownify/__init__.py b/markdownify/__init__.py
index 151a222..a60400c 100644
--- a/markdownify/__init__.py
+++ b/markdownify/__init__.py
@@ -265,7 +265,7 @@ def convert_hn(self, n, el, text, convert_as_inline):
             return text
 
         style = self.options['heading_style'].lower()
-        text = text.rstrip()
+        text = text.strip()
         if style == UNDERLINED and n <= 2:
             line = '=' if n == 1 else '-'
             return self.underline(text, line)
diff --git a/tests/test_conversions.py b/tests/test_conversions.py
index 5c6ec06..b03c874 100644
--- a/tests/test_conversions.py
+++ b/tests/test_conversions.py
@@ -90,6 +90,14 @@ def test_em():
     inline_tests('em', '*')
 
 
+def test_header_with_space():
+    assert md('<h3>\n\nHello</h3>') == '### Hello\n\n'
+    assert md('<h4>\n\nHello</h4>') == '#### Hello\n\n'
+    assert md('<h5>\n\nHello</h5>') == '##### Hello\n\n'
+    assert md('<h5>\n\nHello\n\n</h5>') == '##### Hello\n\n'
+    assert md('<h5>\n\nHello   \n\n</h5>') == '##### Hello\n\n'
+
+
 def test_h1():
     assert md('<h1>Hello</h1>') == 'Hello\n=====\n\n'
 

From 0477a0c8a08b0f9b0ada8d22090a8bb6915085f7 Mon Sep 17 00:00:00 2001
From: Carina de Oliveira Antunes <carinadeoliveiraantunes@gmail.com>
Date: Tue, 26 Mar 2024 20:49:50 +0100
Subject: [PATCH 05/13] convert_td: strip text (#91)

---
 markdownify/__init__.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/markdownify/__init__.py b/markdownify/__init__.py
index a60400c..eaa58c1 100644
--- a/markdownify/__init__.py
+++ b/markdownify/__init__.py
@@ -370,7 +370,7 @@ def convert_table(self, el, text, convert_as_inline):
         return '\n\n' + text + '\n'
 
     def convert_td(self, el, text, convert_as_inline):
-        return ' ' + text + ' |'
+        return ' ' + text.strip() + ' |'
 
     def convert_th(self, el, text, convert_as_inline):
         return ' ' + text + ' |'

From 96a25cfbf3c4b00d226d20ee97d9d7f39c2c60e0 Mon Sep 17 00:00:00 2001
From: AlexVonB <AlexVonB@users.noreply.github.com>
Date: Tue, 26 Mar 2024 21:05:31 +0100
Subject: [PATCH 06/13] added tests for linebreaks in table cells

---
 markdownify/__init__.py |  2 +-
 tests/test_tables.py    | 21 +++++++++++++++++++++
 2 files changed, 22 insertions(+), 1 deletion(-)

diff --git a/markdownify/__init__.py b/markdownify/__init__.py
index eaa58c1..f9b5f9b 100644
--- a/markdownify/__init__.py
+++ b/markdownify/__init__.py
@@ -370,7 +370,7 @@ def convert_table(self, el, text, convert_as_inline):
         return '\n\n' + text + '\n'
 
     def convert_td(self, el, text, convert_as_inline):
-        return ' ' + text.strip() + ' |'
+        return ' ' + text.strip().replace("\n", " ") + ' |'
 
     def convert_th(self, el, text, convert_as_inline):
         return ' ' + text + ' |'
diff --git a/tests/test_tables.py b/tests/test_tables.py
index e0c07ea..334bfb7 100644
--- a/tests/test_tables.py
+++ b/tests/test_tables.py
@@ -57,6 +57,26 @@
     </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>
@@ -164,6 +184,7 @@ 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_missing_text) == '\n\n|  | Lastname | Age |\n| --- | --- | --- |\n| Jill |  | 50 |\n| Eve | Jackson | 94 |\n\n'

From 2f9a42d3b8873e9ac4ce91379c8f36fc610e7ee7 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Andr=C3=A9=20van=20Delft?= <andrevandelft@outlook.com>
Date: Tue, 26 Mar 2024 21:07:28 +0100
Subject: [PATCH 07/13] Strip text before adding blockquote markers (#76)

---
 markdownify/__init__.py   | 2 +-
 tests/test_conversions.py | 8 +++++++-
 2 files changed, 8 insertions(+), 2 deletions(-)

diff --git a/markdownify/__init__.py b/markdownify/__init__.py
index f9b5f9b..1e7b787 100644
--- a/markdownify/__init__.py
+++ b/markdownify/__init__.py
@@ -237,7 +237,7 @@ def convert_blockquote(self, el, text, convert_as_inline):
         if convert_as_inline:
             return text
 
-        return '\n' + (line_beginning_re.sub('> ', text) + '\n\n') if text else ''
+        return '\n' + (line_beginning_re.sub('> ', text.strip()) + '\n\n') if text else ''
 
     def convert_br(self, el, text, convert_as_inline):
         if convert_as_inline:
diff --git a/tests/test_conversions.py b/tests/test_conversions.py
index b03c874..ae56837 100644
--- a/tests/test_conversions.py
+++ b/tests/test_conversions.py
@@ -52,6 +52,12 @@ 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():
@@ -60,7 +66,7 @@ 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> \n\n'
+    assert text == '\n> And she was like \n> > Hello\n\n'
 
 
 def test_br():

From 7d0bf46057558508bd122b2fcfe5419276d59e71 Mon Sep 17 00:00:00 2001
From: Chris Papademetrious <chrispy@synopsys.com>
Date: Tue, 26 Mar 2024 16:15:22 -0400
Subject: [PATCH 08/13] revert workaround example in README.rst for <script>
 and <style> now that it is properly fixed (#115)

Signed-off-by: chrispy <chrispy@synopsys.com>
---
 README.rst | 16 ----------------
 1 file changed, 16 deletions(-)

diff --git a/README.rst b/README.rst
index 21a5972..06f319b 100644
--- a/README.rst
+++ b/README.rst
@@ -173,22 +173,6 @@ change:
     def md(html, **options):
         return ImageBlockConverter(**options).convert(html)
 
-.. code:: python
-
-    from markdownify import MarkdownConverter
-
-    class NoCssConverter(MarkdownConverter):
-        """
-        Create a custom MarkdownConverter that removes the CSS code by ignoring the `style` tag
-        """
-        def convert_style(self, el, text, convert_as_inline):
-            return ''
-
-    # Create shorthand method for conversion
-    def md(html, **options):
-        return NoCssConverter(**options).convert(html)
-
-
 
 Command Line Interface
 ======================

From 804a3f8f079e1f9018030d80414d9981b531fccb Mon Sep 17 00:00:00 2001
From: AlexVonB <AlexVonB@users.noreply.github.com>
Date: Tue, 26 Mar 2024 21:21:45 +0100
Subject: [PATCH 09/13] added further readme for custom converters

---
 README.rst | 22 +++++++++++++++++++++-
 1 file changed, 21 insertions(+), 1 deletion(-)

diff --git a/README.rst b/README.rst
index 06f319b..51888ea 100644
--- a/README.rst
+++ b/README.rst
@@ -156,7 +156,12 @@ 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:
+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:
 
 .. code:: python
 
@@ -173,6 +178,21 @@ change:
     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
 ======================

From e4df41225da327aeb1ca5acd87be02518f8f8865 Mon Sep 17 00:00:00 2001
From: huuya <32855384+huuyafwww@users.noreply.github.com>
Date: Wed, 27 Mar 2024 05:32:36 +0900
Subject: [PATCH 10/13] Support conversion of header rows in tables without th
 tag (#83)

* Fixed support for header row conversion for tables without th tag
---
 markdownify/__init__.py |  6 +++++-
 tests/test_tables.py    | 27 +++++++++++++++++++++++++--
 2 files changed, 30 insertions(+), 3 deletions(-)

diff --git a/markdownify/__init__.py b/markdownify/__init__.py
index 1e7b787..b67c32b 100644
--- a/markdownify/__init__.py
+++ b/markdownify/__init__.py
@@ -377,7 +377,11 @@ def convert_th(self, el, text, convert_as_inline):
 
     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])
+        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)
+        )
         overline = ''
         underline = ''
         if is_headrow and not el.previous_sibling:
diff --git a/tests/test_tables.py b/tests/test_tables.py
index 334bfb7..ebbb146 100644
--- a/tests/test_tables.py
+++ b/tests/test_tables.py
@@ -119,6 +119,28 @@
     </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>
@@ -187,6 +209,7 @@ def test_table():
     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|  |  |  |\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'
+    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'

From d5fb0fbb859f7c9881d04894d75129d4e17fe83f Mon Sep 17 00:00:00 2001
From: Chris Papademetrious <chrispy@synopsys.com>
Date: Tue, 26 Mar 2024 16:41:56 -0400
Subject: [PATCH 11/13] make sure there are blank lines around table/figure
 captions (#114)

Signed-off-by: chrispy <chrispy@synopsys.com>
Co-authored-by: AlexVonB <AlexVonB@users.noreply.github.com>
---
 markdownify/__init__.py   | 6 ++++++
 tests/test_conversions.py | 5 +++++
 tests/test_tables.py      | 9 +++++++++
 3 files changed, 20 insertions(+)

diff --git a/markdownify/__init__.py b/markdownify/__init__.py
index b67c32b..cab4f36 100644
--- a/markdownify/__init__.py
+++ b/markdownify/__init__.py
@@ -369,6 +369,12 @@ def convert_style(self, el, text, convert_as_inline):
     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):
         return ' ' + text.strip().replace("\n", " ") + ' |'
 
diff --git a/tests/test_conversions.py b/tests/test_conversions.py
index ae56837..1e685f3 100644
--- a/tests/test_conversions.py
+++ b/tests/test_conversions.py
@@ -74,6 +74,11 @@ 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*`'
diff --git a/tests/test_tables.py b/tests/test_tables.py
index ebbb146..9be876d 100644
--- a/tests/test_tables.py
+++ b/tests/test_tables.py
@@ -201,6 +201,14 @@
     </tbody>
 </table>"""
 
+table_with_caption = """TEXT<table><caption>Caption</caption>
+    <tbody><tr><td>Firstname</td>
+            <td>Lastname</td>
+            <td>Age</td>
+        </tr>
+    </tbody>
+</table>"""
+
 
 def test_table():
     assert md(table) == '\n\n| Firstname | Lastname | Age |\n| --- | --- | --- |\n| Jill | Smith | 50 |\n| Eve | Jackson | 94 |\n\n'
@@ -213,3 +221,4 @@ def test_table():
     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'

From 57d4f379236fdda75c7359d664ecf4aea8bcb157 Mon Sep 17 00:00:00 2001
From: AlexVonB <AlexVonB@users.noreply.github.com>
Date: Tue, 26 Mar 2024 21:43:25 +0100
Subject: [PATCH 12/13] fixed tests for table caption

---
 tests/test_tables.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tests/test_tables.py b/tests/test_tables.py
index 9be876d..42f3a25 100644
--- a/tests/test_tables.py
+++ b/tests/test_tables.py
@@ -221,4 +221,4 @@ def test_table():
     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'
+    assert md(table_with_caption) == 'TEXT\n\nCaption\n| Firstname | Lastname | Age |\n| --- | --- | --- |\n\n'

From 3b4a014f25e8fef9434a41b17698210d920001fb Mon Sep 17 00:00:00 2001
From: Eric Xu <70456761+xydxydxyd1@users.noreply.github.com>
Date: Tue, 26 Mar 2024 13:50:54 -0700
Subject: [PATCH 13/13] Table merge cell horizontally (#110)

* Fix #109 Table merge cell horizontally

* Add test case for colspan

---------

Co-authored-by: AlexVonB <AlexVonB@users.noreply.github.com>
---
 markdownify/__init__.py | 18 +++++++++++++++---
 tests/test_tables.py    | 18 ++++++++++++++++++
 2 files changed, 33 insertions(+), 3 deletions(-)

diff --git a/markdownify/__init__.py b/markdownify/__init__.py
index cab4f36..86226d2 100644
--- a/markdownify/__init__.py
+++ b/markdownify/__init__.py
@@ -376,10 +376,16 @@ def convert_figcaption(self, el, text, convert_as_inline):
         return '\n\n' + text + '\n\n'
 
     def convert_td(self, el, text, convert_as_inline):
-        return ' ' + text.strip().replace("\n", " ") + ' |'
+        colspan = 1
+        if 'colspan' in el.attrs:
+            colspan = int(el['colspan'])
+        return ' ' + text.strip().replace("\n", " ") + ' |' * colspan
 
     def convert_th(self, el, text, convert_as_inline):
-        return ' ' + text + ' |'
+        colspan = 1
+        if 'colspan' in el.attrs:
+            colspan = int(el['colspan'])
+        return ' ' + text.strip().replace("\n", " ") + ' |' * colspan
 
     def convert_tr(self, el, text, convert_as_inline):
         cells = el.find_all(['td', 'th'])
@@ -392,7 +398,13 @@ def convert_tr(self, el, text, convert_as_inline):
         underline = ''
         if is_headrow and not el.previous_sibling:
             # first row and is headline: print headline underline
-            underline += '| ' + ' | '.join(['---'] * len(cells)) + ' |' + '\n'
+            full_colspan = 0
+            for cell in cells:
+                if "colspan" in cell.attrs:
+                    full_colspan += int(cell["colspan"])
+                else:
+                    full_colspan += 1
+            underline += '| ' + ' | '.join(['---'] * full_colspan) + ' |' + '\n'
         elif (not el.previous_sibling
               and (el.parent.name == 'table'
                    or (el.parent.name == 'tbody'
diff --git a/tests/test_tables.py b/tests/test_tables.py
index 42f3a25..9120c29 100644
--- a/tests/test_tables.py
+++ b/tests/test_tables.py
@@ -209,6 +209,23 @@
     </tbody>
 </table>"""
 
+table_with_colspan = """<table>
+    <tr>
+        <th colspan="2">Name</th>
+        <th>Age</th>
+    </tr>
+    <tr>
+        <td>Jill</td>
+        <td>Smith</td>
+        <td>50</td>
+    </tr>
+    <tr>
+        <td>Eve</td>
+        <td>Jackson</td>
+        <td>94</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'
@@ -222,3 +239,4 @@ def test_table():
     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'