Extracting post title, slug and content from a Ghost 2.x backup and import it to a write.as blog

convert_posts_to_markdown.py

#!/usr/bin/env python3
"""
Convert HTML posts that we extract via JQ, into Markdown formatted files (one file per post, title as filename)
"""

import json
import html2text
import sys
import argparse

if __name__ == "__main__":
    # Parsing arguments
    parser = argparse.ArgumentParser(
        prog='convert_posts_to_markdown.py'
    )
    parser.add_argument(
        '-f',
        '--file',
        type=str,
        help='Filename of Ghost 2.x export'
    )
    args = parser.parse_args()
    ghost_export = args.file

    h = html2text.HTML2Text()
    h.ignore_links = False
    h.body_width = 0
    #h.single_line_break = True

    with open(ghost_export, 'r') as f:
        posts = json.load(f)
    
    for post in posts:
        title = post['title']
        slug = post['slug']
        content = post['content']

        filename = '{}.md'.format(slug)
        fcontent = '<h1>{}</h1>{}'.format(title, content)
        mcontent = h.handle(fcontent)

        with open(filename, 'w') as mdown:
            mdown.write(mcontent)

extract_posts.sh

#!/bin/bash
# Extract post information via jq command line json processor https://stedolan.github.io/jq/

ghost_backup="${1}"
posts_extract="${2}"

cat ${ghost_backup} | jq '[.db[].data.posts[] | {title: .title, slug: .slug, date: .created_at, content: .html}]' > ${posts_extract}

remove_empty_lines.sh

#!/bin/bash
# Remove two empty lines at the beginning of the file

for file in *.md
do
    mv -v ${file} ${file}.old
    gsed '1,2{/^$/d}' ${file}.old > ${file}
    rm -v ${file}.old
done