Convert Wordpress caption to figure

In Wordpress, inserting image with a caption can look like:

[caption id="attachment_42" caption="Image Description"]<a ...><img ... /></a>[/caption]
[caption id="attachment_42"]<a ...><img ... /></a> Image Description[/caption]
[caption id="attachment_42"]<img ... > Image Description[/caption]

Replace by an HTML figure tag

pelican/tests/content/wordpressexport.xml

@@ -685,7 +685,52 @@ proident, sunt in culpa qui officia deserunt mollit anim id est laborum.]]></con
             <wp:meta_key>_edit_last</wp:meta_key>
             <wp:meta_value><![CDATA[3]]></wp:meta_value>
         </wp:postmeta>
-    </item>   
+    </item>
+    <item>
+        <title>Caption on image</title>
+        <link>http://thisisa.test/?p=176</link>
+        <pubDate>Thu, 01 Jan 1970 00:00:00 +0000</pubDate>
+        <dc:creator>bob</dc:creator>
+        <guid isPermaLink="false">http://thisisa.test/?p=176</guid>
+        <description></description>
+        <content:encoded><![CDATA[Lorem ipsum dolor sit amet, consectetur adipisicing elit, sed do eiusmod
+tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam,
+quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo
+consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse
+cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non
+proident, sunt in culpa qui officia deserunt mollit anim id est laborum.
+
+[caption attachment_id="42" align="aligncenter" width="300" caption="This is a pelican"]<img src="/theme/img/xpelican.png.pagespeed.ic.Rjep0025-y.png"/>[/caption]
+
+[caption attachment_id="43" align="aligncenter" width="300"]<img src="/theme/img/xpelican-3.png.pagespeed.ic.m-NAIdRCOM.png" width="300" height="216" class="size-medium wp-image-1055" /> This also a pelican[/caption]
+
+[caption attachment_id="44" align="aligncenter" width="300"]<a href="https://getpelican.com/"><img src="/theme/img/xpelican.png.pagespeed.ic.Rjep0025-y.png" alt=""/> Yet another pelican[/caption]
+
+Lorem ipsum dolor sit amet, consectetur adipisicing elit, sed do eiusmod
+tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam,
+quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo
+consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse
+cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non
+proident, sunt in culpa qui officia deserunt mollit anim id est laborum.]]></content:encoded>
+        <excerpt:encoded><![CDATA[]]></excerpt:encoded>
+        <wp:post_id>176</wp:post_id>
+        <wp:post_date>2012-02-16 15:52:55</wp:post_date>
+        <wp:post_date_gmt>0000-00-00 00:00:00</wp:post_date_gmt>
+        <wp:comment_status>open</wp:comment_status>
+        <wp:ping_status>open</wp:ping_status>
+        <wp:post_name>caption-on-image</wp:post_name>
+        <wp:status>publish</wp:status>
+        <wp:post_parent>0</wp:post_parent>
+        <wp:menu_order>0</wp:menu_order>
+        <wp:post_type>post</wp:post_type>
+        <wp:post_password></wp:post_password>
+        <wp:is_sticky>0</wp:is_sticky>
+        <category domain="category" nicename="category-2"><![CDATA[Category 2]]></category>
+        <wp:postmeta>
+            <wp:meta_key>_edit_last</wp:meta_key>
+            <wp:meta_value><![CDATA[3]]></wp:meta_value>
+        </wp:postmeta>
+    </item>
     <item>
         <title>A custom post in category 4</title>
         <link>http://thisisa.test/?p=175</link>

pelican/tests/test_importer.py

@@ -334,6 +334,32 @@ class TestWordpressXmlImporter(unittest.TestCase):
             escaped_quotes = re.search(r'\\[\'"“”‘’]', md)
             self.assertFalse(escaped_quotes)
 
+    def test_convert_caption_to_figure(self):
+        def r(f):
+            with open(f, encoding='utf-8') as infile:
+                return infile.read()
+        silent_f2p = mute(True)(fields2pelican)
+        test_post = filter(
+            lambda p: p[0].startswith("Caption on image"),
+            self.posts)
+        with temporary_folder() as temp:
+            md = [r(f) for f in silent_f2p(test_post, 'markdown', temp)][0]
+
+        caption = re.search(r'\[caption', md)
+        self.assertFalse(caption)
+
+        for occurence in [
+            '/theme/img/xpelican.png.pagespeed.ic.Rjep0025-y.png',
+            '/theme/img/xpelican-3.png.pagespeed.ic.m-NAIdRCOM.png',
+            '/theme/img/xpelican.png.pagespeed.ic.Rjep0025-y.png',
+            'This is a pelican',
+            'This also a pelican',
+            'Yet another pelican',
+        ]:
+            # pandoc 2.x converts into ![text](src)
+            # pandoc 3.x converts into <figure>src<figcaption>text</figcaption></figure>
+            self.assertIn(occurence, md)
+
 
 class TestBuildHeader(unittest.TestCase):
     def test_build_header(self):

pelican/tools/pelican_import.py

@@ -107,6 +107,13 @@ def decode_wp_content(content, br=True):
             return re.sub(pattern, lambda m: dic[m.group()], string)
         content = _multi_replace(pre_tags, content)
 
+    # convert [caption] tags into <figure>
+    content = re.sub(
+        r'\[caption(?:.*?)(?:caption=\"(.*?)\")?\]'
+        r'((?:\<a(?:.*?)\>)?(?:\<img.*?\>)(?:\<\/a\>)?)\s?(.*?)\[\/caption\]',
+        r'<figure>\n\2\n<figcaption>\1\3</figcaption>\n</figure>',
+        content)
+
     return content