Markdown Note Exporter: Recursively Scan and Extract Document IDs and Headings to Create Notes

gistfile1.txt

import os
import re

# Alias-Wörterbuch für Bibelbücher
bible_aliases = {
    "1. Mose": ["1. Mose", "1Mo", "1. Mo", "1 Mo", "Genesis"],
    "2. Mose": ["2. Mose", "2Mo", "2. Mo", "2 Mo", "Exodus"],
    "3. Mose": ["3. Mose", "3Mo", "3. Mo", "3 Mo", "Levitikus"],
    "4. Mose": ["4. Mose", "4Mo", "4. Mo", "4 Mo", "Numeri"],
    "5. Mose": ["5. Mose", "5Mo", "5. Mo", "5 Mo", "Deuteronomium"],
    "Josua": ["Josua", "Jos"],
    "Richter": ["Richter", "Ri"],
    "Ruth": ["Ruth", "Ru"],
    "1. Samuel": ["1. Samuel", "1Sa", "1. Sa", "1 Sam"],
    "2. Samuel": ["2. Samuel", "2Sam", "2. Sam", "2 Sam"],
    "1. Könige": ["1. Könige", "1Kö", "1. Kö", "1 Kön"],
    "2. Könige": ["2. Könige", "2Kö", "2. Kö", "2 Kön"],
    "1. Chronika": ["1. Chronika", "1Chr", "1. Chr", "1 Chr"],
    "2. Chronika": ["2. Chronika", "2Chr", "2. Chr", "2 Chr"],
    "Esra": ["Esra", "Esr"],
    "Nehemia": ["Nehemia", "Ne"],
    "Esther": ["Esther", "Est"],
    "Hiob": ["Hiob", "Hi"],
    "Psalmen": ["Psalmen", "Ps"],
    "Sprüche": ["Sprüche", "Spr"],
    "Prediger": ["Prediger", "Pr"],
    "Das Hohelied": ["Das Hohelied", "Das Lied Salomos", "Hoh"],
    "Jesaja": ["Jesaja", "Jes"],
    "Jeremia": ["Jeremia", "Jer"],
    "Klagelieder": ["Klagelieder", "Klg"],
    "Hesekiel": ["Hesekiel", "Hes"],
    "Daniel": ["Daniel", "Da"],
    "Hosea": ["Hosea", "Hos"],
    "Joel": ["Joel"],
    "Amos": ["Amos", "Am"],
    "Obadja": ["Obadja", "Ob"],
    "Jona": ["Jona", "Jon"],
    "Micha": ["Micha", "Mi"],
    "Nahum": ["Nahum", "Nah"],
    "Habakuk": ["Habakuk", "Hab"],
    "Zephanja": ["Zephanja", "Ze"],
    "Haggai": ["Haggai", "Hag"],
    "Sacharja": ["Sacharja", "Sach"],
    "Maleachi": ["Maleachi", "Mal"],
    "Matthäus": ["Matthäus", "Mat"],
    "Markus": ["Markus", "Mar"],
    "Lukas": ["Lukas", "Luk"],
    "Johannes": ["Johannes", "Joh"],
    "Apostelgeschichte": ["Apostelgeschichte", "Apg"],
    "Römer": ["Römer", "Rö"],
    "1. Korinther": ["1. Korinther", "1Kor", "1. Kor", "1 Kor"],
    "2. Korinther": ["2. Korinther", "2Kor", "2. Kor", "2 Kor"],
    "Galater": ["Galater", "Gal"],
    "Epheser": ["Epheser", "Eph"],
    "Philipper": ["Philipper", "Phil"],
    "Kolosser": ["Kolosser", "Kol"],
    "1. Thessalonicher": ["1. Thessalonicher", "1Thess", "1. Thess", "1 Thess"],
    "2. Thessalonicher": ["2. Thessalonicher", "2Thess", "2. Thess", "2 Thess"],
    "1. Timotheus": ["1. Timotheus", "1Tim", "1. Tim", "1 Tim"],
    "2. Timotheus": ["2. Timotheus", "2Tim", "2. Tim", "2 Tim"],
    "Titus": ["Titus", "Tit"],
    "Philemon": ["Philemon", "Phlm"],
    "Hebräer": ["Hebräer", "Heb"],
    "Jakobus": ["Jakobus", "Jak"],
    "1. Petrus": ["1. Petrus", "1Petr", "1. Petr", "1 Petr"],
    "2. Petrus": ["2. Petrus", "2Petr", "2. Petr", "2 Petr"],
    "1. Johannes": ["1. Johannes", "1Joh", "1. Joh", "1 Joh"],
    "2. Johannes": ["2. Johannes", "2Joh", "2. Joh", "2 Joh"],
    "3. Johannes": ["3. Johannes", "3Joh", "3. Joh", "3 Joh"],
    "Judas": ["Judas", "Jud"],
    "Offenbarung": ["Offenbarung", "Off"]
}

def extract_info(content):
    """Extract document ID, heading, and link from the content of a Markdown file."""
    document_match = re.search(r'document:\s*"\[\[(.*?)\]\]"', content)
    heading_match = re.search(r'heading:\s*(.*?)\n', content)
    link_match = re.search(r'link:\s*(https?://[^\s]+)', content)

    document_id = document_match.group(1) if document_match else None
    heading = heading_match.group(1) if heading_match else None
    link = link_match.group(1) if link_match else None

    return document_id, heading, link

def get_aliases(heading):
    """Get alias list based on the book name in the heading, combined with chapter and verse."""
    print(f"Input heading: {heading}")
    
    # Extract the book name and chapter/verse information
    match = re.match(r"([^0-9]+)\s(\d+:\d+)", heading)
    if not match:
        print(f"No match found for heading: {heading}")
        return [heading]

    book = match.group(1).strip()
    chapter_verse = match.group(2)
    print(f"Extracted book: {book}")
    print(f"Extracted chapter_verse: {chapter_verse}")

    # Get the base aliases for the book
    base_book = None
    for key, aliases in bible_aliases.items():
        if book in aliases:
            base_book = key
            break
    
    if base_book:
        aliases_with_chapter_verse = [f"{alias} {chapter_verse}" for alias in bible_aliases[base_book]]
        print(f"Generated aliases: {aliases_with_chapter_verse}")
    else:
        aliases_with_chapter_verse = [heading]
        print(f"No base book found, using original heading: {heading}")

    return aliases_with_chapter_verse

def create_new_note(export_folder_path, document_id, heading, link):
    """Create a new Markdown note in the export folder with the specified properties."""
    os.makedirs(export_folder_path, exist_ok=True)

    # Get the aliases based on the book name and chapter/verse in the heading
    aliases = get_aliases(heading)

    new_filename = os.path.join(export_folder_path, f"{document_id}.md")
    new_content = f"""---
tags:
  - 📝-type/vers
aliases:
"""
    for alias in aliases:
        new_content += f"  - {alias}\n"
    new_content += f"""
link: {link}
related:
created: 
last modified: 
---
"""
    with open(new_filename, 'w', encoding='utf-8') as file:
        file.write(new_content)

def process_folder(folder_path, export_folder_path):
    """Recursively scan all Markdown files in the folder and its subfolders, and create new notes in the export folder."""
    for root, _, files in os.walk(folder_path):
        for filename in files:
            if filename.endswith(".md"):
                file_path = os.path.join(root, filename)
                with open(file_path, 'r', encoding='utf-8') as file:
                    content = file.read()

                document_id, heading, link = extract_info(content)
                if document_id and heading and link:
                    aliases = get_aliases(heading)
                    print(f"Debug - Aliases for {heading}: {aliases}")  # Add this debug line
                    create_new_note(export_folder_path, document_id, heading, link)

# Pfade für den Quell- und Export-Ordner
folder_path = r"C:\Users\..."
export_folder_path = r"C:\Users\..."
process_folder(folder_path, export_folder_path)

Script only produces 1 aliases