Ignore <p> tags in table rows

Alir3z4 · Apr 19, 2021 · 855c1a0 · 855c1a0
1 parent 4592133
commit 855c1a0
Show file tree

Hide file tree

Showing 4 changed files with 30 additions and 0 deletions.
diff --git a/ChangeLog.rst b/ChangeLog.rst
@@ -6,6 +6,7 @@ UNRELEASED
 * Add support for Python 3.9.
 * Fix extra line breaks inside html link text (between '[' and ']')
 * Fix #344: indent ``<ul>`` inside ``<ol>`` three spaces instead of two to comply with CommonMark, GFM, etc.
+* Feature #198: Ignore ``<p>`` tags inside table rows
 
 2020.1.16
 =========

diff --git a/html2text/__init__.py b/html2text/__init__.py
@@ -365,6 +365,8 @@ def handle_tag(
                     self.soft_br()
             elif self.astack:
                 pass
+            elif self.split_next_td:
+                pass
             else:
                 self.p()
 

diff --git a/test/no_p_in_table.html b/test/no_p_in_table.html
@@ -0,0 +1,12 @@
+<!DOCTYPE html> <html>
+    <head lang="en"> <meta charset="UTF-8"> <title></title> </head>
+    <body> <h1>This is a test document</h1> With some text, <code>code</code>, <b>bolds</b> and <i>italics</i>.  <h2>This is second header</h2> <p style="display: none">Displaynone text</p> 
+    <table>
+        <tr> <th>Header 1</th> <th>Header 2</th> <th>Header 3</th> </tr>
+        <tr> <td><p>Content 1</p></td> <td><p>2</p></td> <td><img src="http://lorempixel.com/200/200" alt="200"/> Image!</td> </tr>
+        <tr> <td><p>Content 1 longer</p></td> <td><p>Content 2</p></td> <td><p>blah</p></td> </tr>
+        <tr> <td><p>Content </p></td> <td><p>Content 2</p></td> <td><p>blah</p></td> </tr>
+        <tr> <td><p>t </p></td> <td><p>Content 2</p></td> <td><p>blah blah blah</p></td> </tr>
+    </table>
+
+  </body> </html>
diff --git a/test/no_p_in_table.md b/test/no_p_in_table.md
@@ -0,0 +1,15 @@
+# This is a test document
+
+With some text, `code`, **bolds** and _italics_.
+
+## This is second header
+
+Displaynone text
+
+Header 1 | Header 2 | Header 3  
+---|---|---  
+Content 1 | 2 | ![200](http://lorempixel.com/200/200) Image!  
+Content 1 longer | Content 2 | blah  
+Content  | Content 2 | blah  
+t  | Content 2 | blah blah blah
+