justinTM · September 29, 2021 01:00 · Sep 29, 2021
diff --git a/confluence_python_get_page_source.py b/confluence_python_get_page_source.py
@@ -0,0 +1,43 @@
+
+import os
+from atlassian import Confluence
+
+
+CONFLUENCE = Confluence(
+    url=f"https://{os.environ['CONFLUENCE_SITE']}.atlassian.net",
+    username=os.environ['CONFLUENCE_USER'],
+    password=os.environ['CONFLUENCE_TOKEN'],
+    cloud=True)
+
+
+def get_confluence_page_source(title: str = None, page_id: int = None):
+  """
+  Retrieve a string representing the body of a Confluence page as Confluence Storage Format.
+  see: https://confluence.atlassian.com/doc/confluence-storage-format-790796544.html
+
+  Useful to get macros and other formatting not found in the normal body contents.
+
+  Parameters:
+
+    title : (optional if page_id is given) the name of the page to retrieve (must have environment variable "CONFLUENCE_SPACE" set)
+    page_id : (optional if title is given) the page ID to retrieve, eg. 28280848470
+
+  Examples:
+
+    >>> CONFLUENCE = Confluence(
+            url=f"https://{os.environ['CONFLUENCE_SITE']}.atlassian.net",
+            username=os.environ['CONFLUENCE_USER'],
+            password=os.environ['CONFLUENCE_TOKEN'],
+            cloud=True)
+    >>> get_confluence_page_source(page_id=os.environ['CONFLUENCE_PARENT_PAGE_ID'])
+    '<ac:structured-macro ac:name="gallery" ac:schema-version="1" data-layout="full-width" ac:local-id="c2b8a095-a706-4752-a4ab-928de77c394e" ac:macro-id="3d51afcda9cf97aa41da0694cec0f5ad"><ac:parameter ac:name="columns">10</ac:parameter><ac:parameter ac:name="includeLabel">container_overview.json</ac:parameter><ac:parameter ac:name="sort">name</ac:parameter></ac:structured-macro><p />'
+  """
+  args = {'expand': 'body.storage'}
+  if title is None and page_id is None:
+    raise ValueError('must specify either title or page_id')
+  elif title is not None:
+    r = CONFLUENCE.get_page_by_title(title=title, space=CONFLUENCE_SPACE, expand='body.storage')
+  elif page_id is not None:
+    r = CONFLUENCE.get_page_by_id(id=page_id, expand='body.storage')
+
+  return r['body']['storage']['value']