Brancheneinstufung2/sync_docs_to_notion.py

import requests
import json
import os
import re

TOKEN_FILE = 'notion_api_key.txt'
PARENT_PAGE_ID = "2e088f42-8544-8024-8289-deb383da3818"
DOC_FILE = "notion_integration.md"

def parse_markdown_to_blocks(md_content):
    blocks = []
    lines = md_content.split('\n')
    
    in_code_block = False
    code_content = []
    
    for line in lines:
        # Don't strip indentation for code blocks, but do for logic checks
        stripped = line.strip()
        
        # Handle Code Blocks
        if stripped.startswith("```"):
            if in_code_block:
                # End of code block
                blocks.append({
                    "object": "block",
                    "type": "code",
                    "code": {
                        "rich_text": [{"type": "text", "text": {"content": "\n".join(code_content)}}],
                        "language": "plain text"
                    }
                })
                code_content = []
                in_code_block = False
            else:
                # Start of code block
                in_code_block = True
            continue
            
        if in_code_block:
            code_content.append(line)
            continue

        if not stripped:
            continue

        # Headings
        if line.startswith("# "):
            blocks.append({
                "object": "block",
                "type": "heading_1",
                "heading_1": {
                    "rich_text": [{"type": "text", "text": {"content": line[2:]}}]
                }
            })
        elif line.startswith("## "):
            blocks.append({
                "object": "block",
                "type": "heading_2",
                "heading_2": {
                    "rich_text": [{"type": "text", "text": {"content": line[3:]}}]
                }
            })
        elif line.startswith("### "):
            blocks.append({
                "object": "block",
                "type": "heading_3",
                "heading_3": {
                    "rich_text": [{"type": "text", "text": {"content": line[4:]}}]
                }
            })
        # List Items
        elif stripped.startswith("* ") or stripped.startswith("- "):
            content = stripped[2:]
            blocks.append({
                "object": "block",
                "type": "bulleted_list_item",
                "bulleted_list_item": {
                    "rich_text": [{"type": "text", "text": {"content": content}}]
                }
            })
        # Numbered List (Simple detection)
        elif re.match(r"^\d+\.", stripped):
            content = re.sub(r"^\d+\.\s*", "", stripped)
            blocks.append({
                "object": "block",
                "type": "numbered_list_item",
                "numbered_list_item": {
                    "rich_text": [{"type": "text", "text": {"content": content}}]
                }
            })
        # Tables (Very basic handling: convert to code block for preservation)
        elif stripped.startswith("|"):
             blocks.append({
                "object": "block",
                "type": "code",
                "code": {
                    "rich_text": [{"type": "text", "text": {"content": line}}],
                    "language": "plain text"
                }
            })
        # Paragraphs
        else:
            blocks.append({
                "object": "block",
                "type": "paragraph",
                "paragraph": {
                    "rich_text": [{"type": "text", "text": {"content": line}}]
                }
            })
            
    return blocks

def upload_doc(token):
    try:
        with open(DOC_FILE, 'r') as f:
            content = f.read()
    except FileNotFoundError:
        print(f"Error: Could not find '{DOC_FILE}'")
        return

    print(f"Parsing '{DOC_FILE}'...")
    children_blocks = parse_markdown_to_blocks(content)
    
    url = "https://api.notion.com/v1/pages"
    headers = {
        "Authorization": f"Bearer {token}",
        "Notion-Version": "2022-06-28",
        "Content-Type": "application/json"
    }

    payload = {
        "parent": { "page_id": PARENT_PAGE_ID },
        "properties": {
            "title": [
                {
                    "text": {
                        "content": "📘 Notion Integration Dokumentation"
                    }
                }
            ]
        },
        "children": children_blocks[:100] # Safe limit
    }

    print(f"Uploading to Notion under parent {PARENT_PAGE_ID}...")
    
    try:
        response = requests.post(url, headers=headers, json=payload)
        response.raise_for_status()
        
        data = response.json()
        print("\n=== SUCCESS ===")
        print(f"Documentation uploaded!")
        print(f"URL: {data.get('url')}")
        
    except requests.exceptions.HTTPError as e:
        print(f"\n=== ERROR ===")
        print(f"HTTP Error: {e}")
        print(f"Response: {response.text}")
    except Exception as e:
        print(f"\n=== ERROR ===")
        print(f"An error occurred: {e}")

def main():
    try:
        with open(TOKEN_FILE, 'r') as f:
            token = f.read().strip()
    except FileNotFoundError:
        print(f"Error: Could not find '{TOKEN_FILE}'")
        return

    upload_doc(token)

if __name__ == "__main__":
    main()