jooray · December 5, 2024 22:51
diff --git a/learndash-course2html.py b/learndash-course2html.py
 #!/usr/bin/python3
 # This script converts a learndash course backup with lessons (but not
 # themes/topics!) to a single ordered HTML file with sections for easy reference

 import argparse
 import json

 def analyze_course_structure(course_file, lessons_file, course_id):
    with open(course_file, 'r', encoding='utf-8') as file:
        lines = file.readlines()

    course_title = "Untitled Course"
    course_sections = []
    lessons = {}
    lesson_ids_in_order = []

    # Parse course file for the given course_id
    for line in lines:
        try:
            obj = json.loads(line)
            if obj.get("wp_post", {}).get("ID") == course_id:
                wp_post_meta = obj.get("wp_post_meta", {})
                course_title = obj.get("wp_post", {}).get("post_title", "Untitled Course")
                course_sections_raw = wp_post_meta.get("course_sections", [])

                # Decode course_sections
                decoded_sections = []
                if (isinstance(course_sections_raw, list) and len(course_sections_raw) == 1 and isinstance(course_sections_raw[0], str)):
                    try:
                        decoded_sections = json.loads(course_sections_raw[0])
                    except json.JSONDecodeError:
                        decoded_sections = []
                elif isinstance(course_sections_raw, str):
                    try:
                        decoded_sections = json.loads(course_sections_raw)
                    except json.JSONDecodeError:
                        decoded_sections = []
                elif isinstance(course_sections_raw, list):
                    decoded_sections = course_sections_raw

                # Extract section headings
                for section in decoded_sections:
                    if isinstance(section, dict) and section.get("type") == "section-heading":
                        s_order = section.get("order", 0)
                        s_title = section.get("post_title", "Untitled Section")
                        course_sections.append({
                            "order": int(s_order),
                            "title": s_title
                        })

                # Extract lesson order from ld_course_steps
                steps = wp_post_meta.get("ld_course_steps", [])
                if steps and len(steps) > 0:
                    sfwd_lessons = steps[0].get("steps", {}).get("h", {}).get("sfwd-lessons", {})
                    lesson_ids_in_order = list(sfwd_lessons.keys())

                break
        except json.JSONDecodeError:
            pass

    # Parse lessons
    with open(lessons_file, 'r', encoding='utf-8') as f:
        for line in f:
            try:
                obj = json.loads(line)
                wp_post = obj.get("wp_post", {})
                lesson_id = str(wp_post.get("ID"))
                if lesson_id in lesson_ids_in_order:
                    lessons[lesson_id] = {
                        "title": wp_post.get("post_title", "Untitled Lesson"),
                        "content": wp_post.get("post_content", "")
                    }
            except json.JSONDecodeError:
                pass

    # Start with all lessons in order
    combined_structure = [lessons[lid]["title"] for lid in lesson_ids_in_order]

    # Sort sections by ascending order
    course_sections.sort(key=lambda x: x["order"])

    # Insert each section at its final desired position
    for sec in course_sections:
        insert_index = sec["order"]
        if insert_index > len(combined_structure):
            insert_index = len(combined_structure)
        combined_structure.insert(insert_index, "!" + sec["title"])

    return course_title, combined_structure, lessons

 def generate_html(course_title, structure, lessons):
    html_output = f"""
 <!DOCTYPE html>
 <html lang="en">
 <head>
    <meta charset="UTF-8">
    <meta name="viewport" content="width=device-width, initial-scale=1.0">
    <title>{course_title}</title>
    <link rel="stylesheet" href="https://cdn.jsdelivr.net/npm/bootstrap@5.3.0/dist/css/bootstrap.min.css">
    <style>
    .wp-block-embed {{ display: none; }}
    </style>
 </head>
 <body class="bg-light" id="top">
    <div class="container py-5">
        <h1 class="text-center mb-4">{course_title}</h1>
        <nav>
            <h2>Table of Contents</h2>
            <ul class="list-group mb-4">
    """
    for line in structure:
        if line.startswith("!"):
            html_output += f'<li class="list-group-item bg-secondary text-white"><strong>{line[1:]}</strong></li>'
        else:
            # Find the corresponding lesson ID
            lesson_id = next((lid for lid, l in lessons.items() if l["title"] == line), None)
            if lesson_id:
                html_output += f'<li class="list-group-item ms-3"><a href="#lesson-{lesson_id}">{line}</a></li>'

    html_output += """
            </ul>
        </nav>
    """

    for line in structure:
        if line.startswith("!"):
            # Section heading
            html_output += f'<h1 class="my-4 text-primary">{line[1:]}</h1>'
        else:
            # Lesson
            lesson_id = next((lid for lid, l in lessons.items() if l["title"] == line), None)
            lesson = lessons.get(lesson_id, {"title": "Unknown Lesson", "content": ""})
            html_output += f'<h2 id="lesson-{lesson_id}" class="mt-3">{lesson["title"]}</h2>\n'
            html_output += f'<p><a href="#top">Back to Table of Contents</a></p>\n'
            html_output += f'<div>{lesson["content"]}</div>\n'

    html_output += """
    </div>
    <script src="https://cdn.jsdelivr.net/npm/bootstrap@5.3.0/dist/js/bootstrap.bundle.min.js"></script>
 </body>
 </html>
    """

    return html_output

 def main():
    parser = argparse.ArgumentParser(description="Generate course HTML from LearnDash export files.")
    parser.add_argument("course_id", type=int, help="ID of the course to process")
    parser.add_argument("course_file", type=str, help="Path to the course file")
    parser.add_argument("lessons_file", type=str, help="Path to the lessons file")
    parser.add_argument("output_file", type=str, help="Path to the output HTML file")

    args = parser.parse_args()

    course_title, structure, lessons = analyze_course_structure(args.course_file, args.lessons_file, args.course_id)
    html_output = generate_html(course_title, structure, lessons)

    with open(args.output_file, "w", encoding="utf-8") as f:
        f.write(html_output)

    print(f"HTML output saved to {args.output_file}")

 if __name__ == "__main__":
    main()
	#!/usr/bin/python3
	# This script converts a learndash course backup with lessons (but not
	# themes/topics!) to a single ordered HTML file with sections for easy reference

	import argparse
	import json

	def analyze_course_structure(course_file, lessons_file, course_id):
	with open(course_file, 'r', encoding='utf-8') as file:
	lines = file.readlines()

	course_title = "Untitled Course"
	course_sections = []
	lessons = {}
	lesson_ids_in_order = []

	# Parse course file for the given course_id
	for line in lines:
	try:
	obj = json.loads(line)
	if obj.get("wp_post", {}).get("ID") == course_id:
	wp_post_meta = obj.get("wp_post_meta", {})
	course_title = obj.get("wp_post", {}).get("post_title", "Untitled Course")
	course_sections_raw = wp_post_meta.get("course_sections", [])

	# Decode course_sections
	decoded_sections = []
	if (isinstance(course_sections_raw, list) and len(course_sections_raw) == 1 and isinstance(course_sections_raw[0], str)):
	try:
	decoded_sections = json.loads(course_sections_raw[0])
	except json.JSONDecodeError:
	decoded_sections = []
	elif isinstance(course_sections_raw, str):
	try:
	decoded_sections = json.loads(course_sections_raw)
	except json.JSONDecodeError:
	decoded_sections = []
	elif isinstance(course_sections_raw, list):
	decoded_sections = course_sections_raw

	# Extract section headings
	for section in decoded_sections:
	if isinstance(section, dict) and section.get("type") == "section-heading":
	s_order = section.get("order", 0)
	s_title = section.get("post_title", "Untitled Section")
	course_sections.append({
	"order": int(s_order),
	"title": s_title
	})

	# Extract lesson order from ld_course_steps
	steps = wp_post_meta.get("ld_course_steps", [])
	if steps and len(steps) > 0:
	sfwd_lessons = steps[0].get("steps", {}).get("h", {}).get("sfwd-lessons", {})
	lesson_ids_in_order = list(sfwd_lessons.keys())

	break
	except json.JSONDecodeError:
	pass

	# Parse lessons
	with open(lessons_file, 'r', encoding='utf-8') as f:
	for line in f:
	try:
	obj = json.loads(line)
	wp_post = obj.get("wp_post", {})
	lesson_id = str(wp_post.get("ID"))
	if lesson_id in lesson_ids_in_order:
	lessons[lesson_id] = {
	"title": wp_post.get("post_title", "Untitled Lesson"),
	"content": wp_post.get("post_content", "")
	}
	except json.JSONDecodeError:
	pass

	# Start with all lessons in order
	combined_structure = [lessons[lid]["title"] for lid in lesson_ids_in_order]

	# Sort sections by ascending order
	course_sections.sort(key=lambda x: x["order"])

	# Insert each section at its final desired position
	for sec in course_sections:
	insert_index = sec["order"]
	if insert_index > len(combined_structure):
	insert_index = len(combined_structure)
	combined_structure.insert(insert_index, "!" + sec["title"])

	return course_title, combined_structure, lessons

	def generate_html(course_title, structure, lessons):
	html_output = f"""
	<!DOCTYPE html>
	<html lang="en">
	<head>
	<meta charset="UTF-8">
	<meta name="viewport" content="width=device-width, initial-scale=1.0">
	<title>{course_title}</title>
	<link rel="stylesheet" href="https://cdn.jsdelivr.net/npm/bootstrap@5.3.0/dist/css/bootstrap.min.css">
	<style>
	.wp-block-embed {{ display: none; }}
	</style>
	</head>
	<body class="bg-light" id="top">
	<div class="container py-5">
	<h1 class="text-center mb-4">{course_title}</h1>
	<nav>
	<h2>Table of Contents</h2>
	<ul class="list-group mb-4">
	"""
	for line in structure:
	if line.startswith("!"):
	html_output += f'<li class="list-group-item bg-secondary text-white"><strong>{line[1:]}</strong></li>'
	else:
	# Find the corresponding lesson ID
	lesson_id = next((lid for lid, l in lessons.items() if l["title"] == line), None)
	if lesson_id:
	html_output += f'<li class="list-group-item ms-3"><a href="#lesson-{lesson_id}">{line}</a></li>'

	html_output += """
	</ul>
	</nav>
	"""

	for line in structure:
	if line.startswith("!"):
	# Section heading
	html_output += f'<h1 class="my-4 text-primary">{line[1:]}</h1>'
	else:
	# Lesson
	lesson_id = next((lid for lid, l in lessons.items() if l["title"] == line), None)
	lesson = lessons.get(lesson_id, {"title": "Unknown Lesson", "content": ""})
	html_output += f'<h2 id="lesson-{lesson_id}" class="mt-3">{lesson["title"]}</h2>\n'
	html_output += f'<p><a href="#top">Back to Table of Contents</a></p>\n'
	html_output += f'<div>{lesson["content"]}</div>\n'

	html_output += """
	</div>
	<script src="https://cdn.jsdelivr.net/npm/bootstrap@5.3.0/dist/js/bootstrap.bundle.min.js"></script>
	</body>
	</html>
	"""

	return html_output

	def main():
	parser = argparse.ArgumentParser(description="Generate course HTML from LearnDash export files.")
	parser.add_argument("course_id", type=int, help="ID of the course to process")
	parser.add_argument("course_file", type=str, help="Path to the course file")
	parser.add_argument("lessons_file", type=str, help="Path to the lessons file")
	parser.add_argument("output_file", type=str, help="Path to the output HTML file")

	args = parser.parse_args()

	course_title, structure, lessons = analyze_course_structure(args.course_file, args.lessons_file, args.course_id)
	html_output = generate_html(course_title, structure, lessons)

	with open(args.output_file, "w", encoding="utf-8") as f:
	f.write(html_output)

	print(f"HTML output saved to {args.output_file}")

	if __name__ == "__main__":
	main()