This Python script generates a Blogger backup XML file from a collection of HTML files in a specified directory.

README.md

Usage: Place your HTML files in the posts directory. Run the script to generate the blogspot_backup.xml file.

• https://stackoverflow.com/questions/39361895/how-can-import-blogger-posts-using-custome-xml-or-any-other-way
• https://sneeit.com/spotdummy-blogger-demo-data-generator-for-template-developers/

blogger_backup_xml_generator.py

import os
import glob
import datetime
from xml.etree.ElementTree import Element, SubElement, tostring, ElementTree

# Define the directory containing the HTML files
html_dir = "posts"

ns = {
    'atom': "http://www.w3.org/2005/Atom",
}

feed = Element('feed', xmlns=ns['atom'])
generator = SubElement(feed, 'generator')
generator.text = 'Blogger'
updated = SubElement(feed, 'updated')
updated.text = datetime.datetime.now(datetime.timezone.utc).strftime('%Y-%m-%dT%H:%M:%SZ')

for i, html_file in enumerate(glob.glob(os.path.join(html_dir, '*.html')), start=1):
    with open(html_file, 'r', encoding='utf-8') as file:
        content = file.read()
    
    file_name = os.path.splitext(os.path.basename(html_file))[0]
    
    entry = SubElement(feed, 'entry')
    
    category1 = SubElement(entry, 'category', scheme="http://www.blogger.com/atom/ns#", term="recipe")
    category2 = SubElement(entry, 'category', scheme="http://schemas.google.com/g/2005#kind", term="http://schemas.google.com/blogger/2008/kind#post")
    
    post_id = SubElement(entry, 'id')
    post_id.text = f'post-{i}'
    
    author = SubElement(entry, 'author')
    name = SubElement(author, 'name')
    name.text = 'Book'
    
    content_element = SubElement(entry, 'content', type="html")
    content_element.text = content
    
    published = SubElement(entry, 'published')
    published.text = datetime.datetime.now(datetime.timezone.utc).strftime('%Y-%m-%dT%H:%M:%SZ')
    
    title = SubElement(entry, 'title', type="html")
    title.text = file_name

tree = ElementTree(feed)
with open('blogspot_backup.xml', 'wb') as xml_file:
    tree.write(xml_file, encoding='utf-8', xml_declaration=True)

print("Blogger backup XML created successfully.")

structure.xml

<?xml version='1.0' encoding='UTF-8'?>
<ns0:feed
	xmlns:ns0="http://www.w3.org/2005/Atom">
	<ns0:generator>Blogger</ns0:generator>
	<ns0:updated>2024-05-30T10:25:17Z</ns0:updated>
	<ns0:entry>
		<ns0:category scheme="http://www.blogger.com/atom/ns#" term="recipe" />
		<ns0:category scheme="http://schemas.google.com/g/2005#kind" term="http://schemas.google.com/blogger/2008/kind#post" />
		<ns0:id>post-10</ns0:id>
		<ns0:author>
			<ns0:name>Book</ns0:name>
		</ns0:author>
		<ns0:content type="html">Test content</ns0:content>
		<ns0:published>2024-05-23T21:42:16Z</ns0:published>
		<ns0:title type="html">Hello</ns0:title>
	</ns0:entry>
</ns0:feed>