Jonathan Lalou's blog

Posts Tagged ‘blogger’

I’ve created a Python script that converts WordPress export files to Blogger/Atom XML format. Here’s how to use it:

The script takes two command-line arguments:

• wordpress_export.xml: Path to your WordPress export XML file
• blogger_export.xml : Path where you want to save the converted Blogger/Atom XML file

To run the script:

python wordpress_to_blogger.py wordpress_export.xml blogger_export.xml

The script performs the following conversions:

• Converts WordPress posts to Atom feed entries
• Preserves post titles, content, publication dates, and authors
• Maintains categories as Atom categories
• Handles post status (published/draft)
• Preserves HTML content formatting
• Converts dates to ISO format required by Atom

The script uses Python’s built-in xml.etree.ElementTree module for XML processing and includes error handling to make it robust.
Some important notes:

• The script only converts posts (not pages or other content types)
• It preserves the HTML content of your posts
• It maintains the original publication dates
• It handles both published and draft posts
• The output is a valid Atom XML feed that Blogger can import

The file:

#!/usr/bin/env python3
import xml.etree.ElementTree as ET
import sys
import argparse
from datetime import datetime
import re

def convert_wordpress_to_blogger(wordpress_file, output_file):
# Parse WordPress XML
tree = ET.parse(wordpress_file)
root = tree.getroot()

# Create Atom feed
atom = ET.Element('feed', {
'xmlns': 'http://www.w3.org/2005/Atom',
'xmlns:app': 'http://www.w3.org/2007/app',
'xmlns:thr': 'http://purl.org/syndication/thread/1.0'
})

# Add feed metadata
title = ET.SubElement(atom, 'title')
title.text = 'Blog Posts'

updated = ET.SubElement(atom, 'updated')
updated.text = datetime.now().isoformat()

# Process each post
for item in root.findall('.//item'):
if item.find('wp:post_type', {'wp': 'http://wordpress.org/export/1.2/'}).text != 'post':
continue

entry = ET.SubElement(atom, 'entry')

# Title
title = ET.SubElement(entry, 'title')
title.text = item.find('title').text

# Content
content = ET.SubElement(entry, 'content', {'type': 'html'})
content.text = item.find('content:encoded', {'content': 'http://purl.org/rss/1.0/modules/content/'}).text

# Publication date
pub_date = item.find('pubDate').text
published = ET.SubElement(entry, 'published')
published.text = datetime.strptime(pub_date, '%a, %d %b %Y %H:%M:%S %z').isoformat()

# Author
author = ET.SubElement(entry, 'author')
name = ET.SubElement(author, 'name')
name.text = item.find('dc:creator', {'dc': 'http://purl.org/dc/elements/1.1/'}).text

# Categories
for category in item.findall('category'):
category_elem = ET.SubElement(entry, 'category', {'term': category.text})

# Status
status = item.find('wp:status', {'wp': 'http://wordpress.org/export/1.2/'}).text
if status == 'publish':
app_control = ET.SubElement(entry, 'app:control', {'xmlns:app': 'http://www.w3.org/2007/app'})
app_draft = ET.SubElement(app_control, 'app:draft')
app_draft.text = 'no'
else:
app_control = ET.SubElement(entry, 'app:control', {'xmlns:app': 'http://www.w3.org/2007/app'})
app_draft = ET.SubElement(app_control, 'app:draft')
app_draft.text = 'yes'

# Write the output file
tree = ET.ElementTree(atom)
tree.write(output_file, encoding='utf-8', xml_declaration=True)

def main():
parser = argparse.ArgumentParser(description='Convert WordPress export to Blogger/Atom XML format')
parser.add_argument('wordpress_file', help='Path to WordPress export XML file')
parser.add_argument('output_file', help='Path to output Blogger/Atom XML file')

args = parser.parse_args()

try:
convert_wordpress_to_blogger(args.wordpress_file, args.output_file)
print(f"Successfully converted {args.wordpress_file} to {args.output_file}")
except Exception as e:
print(f"Error: {str(e)}")
sys.exit(1)

if __name__ == '__main__':
main()