There may come a day when you’re asked to create a large number of Confluence pages. Rather than doing it by hand, why not script it?

This Python script essentially does two things: it reads the CSV file, and it sends page creation requests to a Confluence server.   

For each row in the CSV file, it assumes the page name should be the value in the first cell of the row.  It then generates an HTML table that is sent as part of the page creation request. 

Rather than generating HTML, this could be useful for setting up a large number of template pages, to be filled in by various departments.  It could also run as a job, and automatically create a certain selection of pages every week or month, to store meeting notes or reports.

Please note that in order to connect to the Confluence server, you’ll need to generate a Personal Access Token.

import csv
import requests
import json
import html
import logging

# Initialize logging
logging.basicConfig(level=logging.ERROR)

api_url = 'https://<url>.com/rest/api/content/'
#What's the URL to your Confluence DC instance?


file_path = "<your CSV file path>"
#where is the file stored locally?

parent_page_id = "<your parent page ID>"
#Which page should the new pages be created under?


space_key = "<your space key>"
#What is the key of the Space in which these pages should be created?

headers = {
    'Authorization': 'Bearer <PAT>',
    'Content-Type': 'application/json',
    'Accept': 'application/json',
}
#Create a set of headers to authenticate the request
#You'll need to create a Personal Access Token in your Confluence Instance, in order to connect to it


#Read the CSV file
with open(file_path, 'r') as file:
    reader = csv.reader(file)
    rows = list(reader)


header_row = rows[0]
# Assume the first row is the column headings


html_header_row = "<tr>"
for header in header_row:
    html_header_row += f"<th>{header}</th>"
html_header_row += "</tr>"
#Generate the HTML table and its first row



for row in rows[1:]:
#Generate the HTML from the CSV rows, but skip the first row
    
    
    page_title = row[0]
    #We assume that the title of each page is stored in the first cell in each row
    
    
    html_row = "<tr>"
    for value in row:
        html_row += f"<td>{value}</td>"
    html_row += "</tr>"
    #Add the HTML to the row object

    # Generate the complete HTML table
    html_table = f"<table>{html_header_row}{html_row}</table>"
    #Add the complete list of rows to the table

   
    page_data = {
        "type": "page",
        "title": page_title,
        "ancestors": [{
            "id": parent_page_id
        }],
        "space": {
            "key": space_key
        },
        "body": {
            "storage": {
                "value": html_table,
                "representation": "storage"
            }
        }
    }
    #Define the JSON that will be sent to create the Confluence page
    

    response = requests.post(api_url, headers=headers, json=page_data)
    #Send the POST request

    if response.status_code == 200:
        logging.info(f'Confluence page "{page_title}" created successfully.')
    else:
        logging.error(f'Failed to create Confluence page "{page_title}".')
        logging.error('Status code: %s', response.status_code)
        logging.error('Error: %s', response.text)