Automate Content Strategy with Jasper's Agent

1. 1
   Configure Your Brand Voice

   Inside your Jasper account, navigate to the 'Brand Voice' section. Create a new voice by providing documents like style guides, mission statements, and audience personas. The Content Strategy Agent uses this knowledge to ensure all generated ideas match your brand's tone.
2. 2
   Input Competitive Intelligence

   Within the Content Strategy Agent interface, provide the homepage URLs of 3-5 key competitors. The agent will analyze their content to benchmark their strategy and identify opportunities for you to outperform them.
3. 3
   Prepare Your Content Sitemap

   For the agent to perform a content audit, it needs a list of your existing URLs. Run the provided Python script to generate a `sitemap_urls.txt` file from your website's `sitemap.xml`. You will upload this file to the agent.
4. 4
   Generate and Review the Strategy

   With your brand voice, competitor data, and sitemap loaded, command the Content Strategy Agent to run. It will produce a report with a topical gap analysis and a draft editorial calendar. Review the suggestions for relevance and strategic fit before finalizing.

import requests
import argparse
from xml.etree import ElementTree

# sitemap_scraper.py
# Usage: python sitemap_scraper.py --url https://your-website.com/sitemap.xml

def fetch_and_parse_sitemap(sitemap_url):
    """Fetches sitemap, parses XML, and extracts URLs."""
    print(f"Fetching sitemap from {sitemap_url}...")
    headers = {'User-Agent': 'Mozilla/5.0'}
    try:
        response = requests.get(sitemap_url, headers=headers)
        response.raise_for_status() # Raise an exception for bad status codes
    except requests.exceptions.RequestException as e:
        print(f"Error fetching sitemap: {e}")
        return []

    print("Parsing XML and extracting URLs...")
    # We need to handle XML namespaces
    try:
        root = ElementTree.fromstring(response.content)
        # The namespace is often at the root of the sitemap file
        namespace = ''
        if '}' in root.tag:
            namespace = root.tag.split('}')[0].strip('{')
        
        urls = [elem.text for elem in root.findall(f"{{{namespace}}}url/{{{namespace}}}loc")]
        return urls
    except ElementTree.ParseError as e:
        print(f"Error parsing XML: {e}")
        return []

def main():
    parser = argparse.ArgumentParser(description="Scrape URLs from a sitemap.xml file.")
    parser.add_argument('--url', required=True, help='The full URL of the sitemap.xml file.')
    parser.add_argument('--output', default='sitemap_urls.txt', help='The name of the output file.')
    args = parser.parse_args()

    urls = fetch_and_parse_sitemap(args.url)

    if urls:
        with open(args.output, 'w') as f:
            for url in urls:
                f.write(f"{url}\n")
        print(f"Successfully saved {len(urls)} URLs to {args.output}")
    else:
        print("No URLs were extracted.")

if __name__ == "__main__":
    # To run this script, you need the 'requests' library.
    # Install it using: pip install requests
    main()