Skip to content

Commit

Permalink
[Confluence] added new method get_space_export + docs + examples (atl…
Browse files Browse the repository at this point in the history
…assian-api#1466)


* added expand to get_issue method, added new method
* get_issue_status_changelog method
  • Loading branch information
gkowalc authored Oct 15, 2024
1 parent fb9c354 commit 470ee16
Show file tree
Hide file tree
Showing 3 changed files with 126 additions and 0 deletions.
98 changes: 98 additions & 0 deletions atlassian/confluence.py
Original file line number Diff line number Diff line change
Expand Up @@ -2657,6 +2657,103 @@ def get_page_as_word(self, page_id):
url = "exportword?pageId={pageId}".format(pageId=page_id)
return self.get(url, headers=headers, not_json_response=True)

def get_space_export(self, space_key: str, export_type: str) -> str:
"""
Export a Confluence space to a file of the specified type.
(!) This method was developed for Confluence Cloud and may not work with Confluence on-prem.
(!) This is an experimental method that does not trigger an officially supported REST endpoint. It may break if Atlassian changes the space export front-end logic.
:param space_key: The key of the space to export.
:param export_type: The type of export to perform. Valid values are: 'html', 'csv', 'xml', 'pdf'.
:return: The URL to download the exported file.
"""

def get_atl_request(url: str):
# Nested function used to get atl_token used for XSRF protection. this is only applicable to html/csv/xml space exports
try:
response = self.get(url, advanced_mode=True)
parsed_html = BeautifulSoup(response.text, "html.parser")
atl_token = parsed_html.find("input", {"name": "atl_token"}).get("value")
return atl_token
except Exception as e:
raise ApiError("Problems with getting the atl_token for get_space_export method :", reason=e)

# Checks if space_ke parameter is valid and if api_token has relevant permissions to space
self.get_space(space_key=space_key, expand="permissions")

try:
log.info(
"Initiated experimental get_space_export method for export type: "
+ export_type
+ " from Confluence space: "
+ space_key
)
if export_type == "csv":
form_data = {
"atl_token": get_atl_request(f"spaces/exportspacecsv.action?key={space_key}"),
"exportType": "TYPE_CSV",
"contentOption": "all",
"includeComments": "true",
"confirm": "Export",
}
elif export_type == "html":
form_data = {
"atl_token": get_atl_request(f"spaces/exportspacehtml.action?key={space_key}"),
"exportType": "TYPE_HTML",
"contentOption": "visibleOnly",
"includeComments": "true",
"confirm": "Export",
}
elif export_type == "xml":
form_data = {
"atl_token": get_atl_request(f"spaces/exportspacexml.action?key={space_key}"),
"exportType": "TYPE_XML",
"contentOption": "all",
"includeComments": "true",
"confirm": "Export",
}
elif export_type == "pdf":
url = "spaces/flyingpdf/doflyingpdf.action?key=" + space_key
log.info("Initiate PDF space export from space " + str(space_key))
return self.get_pdf_download_url_for_confluence_cloud(url)
else:
raise ValueError("Invalid export_type parameter value. Valid values are: 'html/csv/xml/pdf'")
url = self.url_joiner(url=self.url, path=f"spaces/doexportspace.action?key={space_key}")

# Sending a POST request that triggers the space export.
response = self.session.post(url, headers=self.form_token_headers, data=form_data)
parsed_html = BeautifulSoup(response.text, "html.parser")
# Getting the poll URL to get the export progress status
try:
poll_url = parsed_html.find("meta", {"name": "ajs-pollURI"}).get("content")
except Exception as e:
raise ApiError("Problems with getting the poll_url for get_space_export method :", reason=e)
running_task = True
while running_task:
try:
progress_response = self.get(poll_url)
log.info("Space" + space_key + " export status: " + progress_response["message"])
if progress_response["complete"]:
parsed_html = BeautifulSoup(progress_response["message"], "html.parser")
download_url = parsed_html.find("a", {"class": "space-export-download-path"}).get("href")
if self.url in download_url:
return download_url
else:
combined_url = self.url + download_url
# Ensure only one /wiki is included in the path
if combined_url.count("/wiki") > 1:
combined_url = combined_url.replace("/wiki/wiki", "/wiki")
return combined_url
time.sleep(30)
except Exception as e:
raise ApiError(
"Encountered error during space export status check from space " + space_key, reason=e
)

return "None" # Return None if the while loop does not return a value
except Exception as e:
raise ApiError("Encountered error during space export from space " + space_key, reason=e)

def export_page(self, page_id):
"""
Alias method for export page as pdf
Expand Down Expand Up @@ -2905,6 +3002,7 @@ def get_pdf_download_url_for_confluence_cloud(self, url):
and provides a link to download the PDF once the process completes.
This functions polls the long-running task page and returns the
download url of the PDF.
This method is used in get_space_export() method for space-> PDF export.
:param url: URL to initiate PDF export
:return: Download url for PDF file
"""
Expand Down
3 changes: 3 additions & 0 deletions docs/confluence.rst
Original file line number Diff line number Diff line change
Expand Up @@ -240,6 +240,9 @@ Get spaces info
# Get Space permissions set based on json-rpc call
confluence.get_space_permissions(space_key)
# Get Space export download url
confluence.get_space_export(space_key, export_type)
Users and Groups
----------------

Expand Down
25 changes: 25 additions & 0 deletions examples/confluence/confluence_get_space_export.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,25 @@
from atlassian import Confluence

# init the Confluence object
host = "<cloud_instance_url/wiki>"
username = "<user_email>"
password = "<API_TOKEN>"
confluence = Confluence(
url=host,
username=username,
password=password,
)
space_key = "TEST"
confluence.get_space_export(space_key=space_key, export_type="html")
# This method should be used to trigger the space export action.
# Provide `space_key` and `export_type` (html/pdf/xml/csv) as arguments.

# It was tested on Confluence Cloud and might not work properly with Confluence on-prem.
# (!) This is an experimental method that should be considered a workaround for the missing space export REST endpoint.
# (!) The method might break if Atlassian implements changes to their space export front-end logic.

# The while loop does not have an exit condition; it will run until the space export is completed.
# It is possible that the space export progress might get stuck. It is up to the library user to handle this scenario.

# Method returns the link to the space export file.
# It is up to the library user to handle the file download action.

0 comments on commit 470ee16

Please sign in to comment.