markdown_utils.py

import os
import re

def parse_markdown_files(file_paths):
    """
    Parses markdown files to extract content for translation.
    
    :param file_paths: List of markdown file paths
    :return: List of dictionaries containing filename and content
    """
    parsed_files = []
    for path in file_paths:
        with open(path, 'r', encoding='utf-8') as f:
            content = f.read()
        parsed_files.append({'filename': path, 'content': content})
    return parsed_files

def extract_translatable_text(content):
    """
    Extracts translatable text from markdown content.
    
    :param content: Markdown content
    :return: List of translatable text segments
    """
    code_block_pattern = re.compile(r'```.*?```', re.DOTALL)
    html_block_pattern = re.compile(r'<.*?>', re.DOTALL)
    url_pattern = re.compile(r'\[.*?\]\(.*?\)')
    
    # Remove code blocks, HTML blocks, and URLs
    content = re.sub(code_block_pattern, '', content)
    content = re.sub(html_block_pattern, '', content)
    content = re.sub(url_pattern, '', content)
    
    # Extract paragraphs and headers
    paragraphs = re.split(r'\n\s*\n', content)
    return [para.strip() for para in paragraphs if para.strip()]

def save_translated_files(translated_files):
    """
    Saves translated files to the local machine.
    
    :param translated_files: List of translated file data
    """
    for file in translated_files:
        directory = os.path.dirname(file['filename'])
        if not os.path.exists(directory):
            os.makedirs(directory)
        with open(file['filename'], 'w', encoding='utf-8') as f:
            f.write(file['content'])