카페24 어드민 API 문서를 쪼개 줍니다

separate_cafe24_docs_by_resource.py

#!/usr/bin/env python3
"""
Script to fetch Cafe24 API documentation and separate it by API resource (h1 level).
Each resource and all its endpoints will be in a single HTML file.
"""

import os
import re
import requests
from bs4 import BeautifulSoup
from urllib.parse import urljoin
import json
from pathlib import Path
from collections import defaultdict

class Cafe24DocResourceSeparator:
    def __init__(self, base_url, output_dir="cafe24_docs_by_resource"):
        self.base_url = base_url
        self.output_dir = Path(output_dir)
        self.output_dir.mkdir(exist_ok=True)
        self.session = requests.Session()
        self.session.headers.update({
            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36'
        })
        self.resources_processed = {}  # Track resource titles to numbers
        
    def sanitize_filename(self, name):
        """Convert a string into a valid filename."""
        name = re.sub(r'[<>:"/\\|?*]', '_', name)
        name = name.strip('. ')
        if len(name) > 100:
            name = name[:100]
        return name if name else "unnamed"
    
    def fetch_page(self, url):
        """Fetch a page and return its HTML content."""
        try:
            response = self.session.get(url, timeout=30)
            response.raise_for_status()
            return response.text
        except requests.RequestException as e:
            print(f"Error fetching {url}: {e}")
            return None
    
    def extract_resources_structure(self, soup):
        """Extract the resource structure (h1 level) from the documentation."""
        resources = defaultdict(list)
        current_category = "General"
        
        toc_element = soup.find('div', id='toc')
        if not toc_element:
            toc_element = soup.find('div', class_='toc-list')
        
        if toc_element:
            # Look for category headers (h4 with class toc-sub-title)
            for element in toc_element.descendants:
                if element.name == 'h4' and 'toc-sub-title' in element.get('class', []):
                    current_category = element.get_text(strip=True)
                elif element.name == 'a' and 'toc-h1' in element.get('class', []):
                    # This is a main resource
                    resource_info = {
                        'title': element.get('data-title', element.get_text(strip=True)),
                        'href': element.get('href', ''),
                        'resource': element.get('data-resource', ''),
                        'category': current_category,
                        'endpoints': []
                    }
                    
                    # Find all h2 endpoints under this resource
                    parent_li = element.find_parent('li')
                    if parent_li:
                        h2_links = parent_li.find_all('a', class_='toc-h2')
                        for h2_link in h2_links:
                            endpoint_info = {
                                'title': h2_link.get('data-title', h2_link.get_text(strip=True)),
                                'href': h2_link.get('href', '')
                            }
                            resource_info['endpoints'].append(endpoint_info)
                    
                    resources[current_category].append(resource_info)
        
        return resources
    
    def extract_section_content(self, soup, section_id):
        """Extract content for a specific section from the main page."""
        if not section_id:
            return "<p>No section ID provided</p>"
        
        # Remove the # if present
        section_id = section_id.lstrip('#')
        
        # Find the section
        section = soup.find(id=section_id)
        if not section:
            # Try finding in content div
            content_div = soup.find('div', class_='content')
            if content_div:
                section = content_div.find(id=section_id)
        
        if not section:
            return f"<p>Section '{section_id}' not found</p>"
        
        # Collect content until next major section
        content_parts = []
        
        # Add the section header
        content_parts.append(str(section))
        
        # Find the parent container
        parent = section.parent
        if parent:
            # Get all siblings after this section
            current = section
            while True:
                current = current.find_next_sibling()
                if not current:
                    break
                
                # Stop at next h1 or h2 with different resource
                if current.name == 'h1':
                    break
                if current.name == 'h2' and current.get('id'):
                    # Check if this h2 belongs to a different resource
                    current_id = current.get('id', '')
                    if not current_id.startswith(section_id.split('-')[0]):
                        break
                
                content_parts.append(str(current))
        
        return '\n'.join(content_parts)
    
    def create_resource_html(self, resource_info, all_content, original_soup, all_resources_by_category):
        """Create a standalone HTML file for a resource with all its endpoints."""
        title = resource_info['title']
        category = resource_info['category']
        
        # Extract styles from original page
        styles = []
        for style in original_soup.find_all('style'):
            styles.append(str(style))
        
        stylesheets = []
        for link in original_soup.find_all('link', rel='stylesheet'):
            stylesheets.append(str(link))
        
        # Build navigation for this resource
        nav_html = '<ul class="endpoint-nav">'
        for endpoint in resource_info['endpoints']:
            endpoint_title = endpoint['title'].strip()
            nav_html += f'<li><a href="#{endpoint["href"].lstrip("#")}">{endpoint_title}</a></li>'
        nav_html += '</ul>'
        
        # Build sidebar navigation with only same category resources
        sidebar_html = f'<div class="sidebar-category">'
        sidebar_html += f'<div class="sidebar-category-title">{category}</div>'
        sidebar_html += '<ul class="sidebar-list">'
        
        # Only show resources from the same category
        if category in all_resources_by_category:
            for res in all_resources_by_category[category]:
                res_filename = f"{self.resources_processed.get(res['title'], 999):03d}_{self.sanitize_filename(res['title'])}.html"
                active_class = 'active' if res['title'] == title else ''
                sidebar_html += f'<li class="{active_class}"><a href="{res_filename}">{res["title"]}</a></li>'
        
        sidebar_html += '</ul></div>'
        
        html_template = f"""<!DOCTYPE html>
<html lang="ko">
<head>
    <meta charset="UTF-8">
    <meta name="viewport" content="width=device-width, initial-scale=1.0">
    <title>{title} - Cafe24 API Documentation</title>
    {''.join(stylesheets)}
    {''.join(styles)}
    <style>
        body {{
            font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, 'Helvetica Neue', Arial, sans-serif;
            line-height: 1.6;
            padding: 0;
            margin: 0;
            background: #f5f7fa;
            display: flex;
        }}
        .sidebar {{
            width: 280px;
            background: white;
            border-right: 1px solid #dee2e6;
            height: 100vh;
            overflow-y: auto;
            position: fixed;
            left: 0;
            top: 0;
        }}
        .sidebar-category {{
            border-bottom: 1px solid #e9ecef;
        }}
        .sidebar-category-title {{
            background: #f8f9fa;
            padding: 10px 15px;
            font-weight: 600;
            color: #495057;
            font-size: 0.9em;
            text-transform: uppercase;
            letter-spacing: 0.5px;
        }}
        .sidebar-list {{
            list-style: none;
            padding: 0;
            margin: 0;
        }}
        .sidebar-list li {{
            border-bottom: 1px solid #f1f3f5;
        }}
        .sidebar-list li.active {{
            background: #e7f3ff;
        }}
        .sidebar-list li.active a {{
            color: #0052a3;
            font-weight: 600;
        }}
        .sidebar-list a {{
            display: block;
            padding: 6px 15px;
            color: #495057;
            text-decoration: none;
            font-size: 0.92em;
        }}
        .sidebar-list a:hover {{
            background: #f8f9fa;
            color: #0066cc;
        }}
        .main-wrapper {{
            margin-left: 280px;
            width: calc(100% - 280px);
            padding: 20px;
        }}
        .header-nav {{
            background: #f8f9fa;
            padding: 15px;
            border-radius: 8px;
            margin-bottom: 30px;
            position: sticky;
            top: 0;
            z-index: 100;
            box-shadow: 0 2px 8px rgba(0,0,0,0.1);
        }}
        .header-nav h1 {{
            margin: 0 0 10px 0;
            color: #333;
        }}
        .category-badge {{
            display: inline-block;
            background: #0066cc;
            color: white;
            padding: 3px 10px;
            border-radius: 15px;
            font-size: 0.85em;
            margin-bottom: 10px;
        }}
        .endpoint-nav {{
            list-style: none;
            padding: 0;
            margin: 10px 0;
            display: flex;
            flex-wrap: wrap;
            gap: 10px;
        }}
        .endpoint-nav li {{
            background: white;
            border: 1px solid #ddd;
            border-radius: 5px;
            padding: 5px 12px;
        }}
        .endpoint-nav a {{
            color: #0066cc;
            text-decoration: none;
            font-size: 0.9em;
        }}
        .endpoint-nav a:hover {{
            text-decoration: underline;
        }}
        .back-link {{
            display: inline-block;
            margin-bottom: 10px;
            color: #0066cc;
            text-decoration: none;
        }}
        .back-link:hover {{
            text-decoration: underline;
        }}
        .content {{
            background: white;
            padding: 30px;
            border-radius: 8px;
            box-shadow: 0 2px 4px rgba(0,0,0,0.1);
            max-width: 1600px;
            margin: 0 auto;
        }}
        /* Dynamic scroll padding will be set by JavaScript */
        h2 {{
            border-top: 2px solid #e1e4e8;
            padding-top: 30px;
            margin-top: 50px;
            color: #2c3e50;
        }}
        h2:first-child {{
            border-top: none;
            padding-top: 0;
            margin-top: 0;
        }}
        h3 {{
            color: #34495e;
            margin-top: 25px;
        }}
        /* Better table styling */
        table {{
            width: 100%;
            border-collapse: collapse;
            margin: 20px 0;
            font-size: 14px;
        }}
        th {{
            background: #f8f9fa;
            padding: 12px;
            text-align: left;
            font-weight: 600;
            border: 1px solid #dee2e6;
        }}
        td {{
            padding: 6px 12px;
            border: 1px solid #dee2e6;
        }}
        tr:nth-child(even) {{
            background: #f8f9fa;
        }}
        /* Code blocks */
        pre {{
            background: #f6f8fa;
            padding: 16px;
            border-radius: 6px;
            overflow-x: auto;
            border: 1px solid #e1e4e8;
        }}
        code {{
            background: #f6f8fa;
            padding: 2px 6px;
            border-radius: 3px;
            font-family: 'Monaco', 'Menlo', 'Ubuntu Mono', monospace;
            font-size: 0.9em;
        }}
        /* Better spacing for lists */
        ul, ol {{
            line-height: 1.8;
            margin: 15px 0;
        }}
        li {{
            margin: 8px 0;
        }}
        /* Highlight important sections */
        .highlight {{
            background: #fff9c4;
            padding: 15px;
            border-left: 4px solid #ffc107;
            margin: 20px 0;
        }}
        /* Better link styling */
        a {{
            color: #0066cc;
        }}
        a:hover {{
            color: #0052a3;
        }}
        /* Response/Request sections */
        .http-method {{
            display: inline-block;
            padding: 4px 8px;
            border-radius: 4px;
            font-weight: bold;
            font-size: 0.85em;
            margin-right: 8px;
        }}
        .http-method.get {{
            background: #61affe;
            color: white;
        }}
        .http-method.post {{
            background: #49cc90;
            color: white;
        }}
        .http-method.put {{
            background: #fca130;
            color: white;
        }}
        .http-method.delete {{
            background: #f93e3e;
            color: white;
        }}
        /* HR separator styling */
        hr {{
            border: none;
            border-top: 2px solid #e1e4e8;
            margin: 40px 0;
        }}
        /* Hide Cafe24 and YouTube chips */
        .chip-cafe24, .chip-youtube {{
            display: none !important;
        }}
        /* Hide duplicate method sections */
        #post-2, #get-2, #put-2, #delete-2 {{
            display: none !important;
        }}
        /* Hide elements with collapse-child-attr controls */
        [aria-controls="collapse-child-attr"] {{
            display: none !important;
        }}
    </style>
    <script>
        // Dynamically set scroll padding based on header height
        window.addEventListener('load', function() {{
            const header = document.querySelector('.header-nav');
            if (header) {{
                const updateScrollPadding = () => {{
                    const headerHeight = header.offsetHeight;
                    document.documentElement.style.scrollPaddingTop = (headerHeight + 20) + 'px';
                }};
                
                // Set initial padding
                updateScrollPadding();
                
                // Update on resize
                window.addEventListener('resize', updateScrollPadding);
                
                // Smooth scroll for anchor links
                document.querySelectorAll('a[href^="#"]').forEach(anchor => {{
                    anchor.addEventListener('click', function(e) {{
                        e.preventDefault();
                        const targetId = this.getAttribute('href').substring(1);
                        const targetElement = document.getElementById(targetId);
                        if (targetElement) {{
                            const headerHeight = header.offsetHeight;
                            const targetPosition = targetElement.getBoundingClientRect().top + window.pageYOffset - headerHeight - 20;
                            window.scrollTo({{
                                top: targetPosition,
                                behavior: 'smooth'
                            }});
                        }}
                    }});
                }});
            }}
        }});
    </script>
</head>
<body>
    <div class="sidebar">
        {sidebar_html}
    </div>
    <div class="main-wrapper">
        <div class="header-nav">
            <a href="index.html" class="back-link">← Back to API Index</a>
            <div class="category-badge">{category}</div>
            <h1>{title}</h1>
            <nav>
                <strong>Endpoints in this resource:</strong>
                {nav_html}
            </nav>
        </div>
        <div class="content">
            {all_content}
        </div>
    </div>
</body>
</html>"""
        return html_template
    
    def process_documentation(self):
        """Main method to process the documentation."""
        print(f"Fetching main page from {self.base_url}...")
        main_html = self.fetch_page(self.base_url)
        
        if not main_html:
            print("Failed to fetch main page")
            return
        
        soup = BeautifulSoup(main_html, 'html.parser')
        
        # Save the complete original page
        original_file = self.output_dir / "original_complete.html"
        with open(original_file, 'w', encoding='utf-8') as f:
            f.write(main_html)
        print(f"Saved original page to {original_file}")
        
        # Extract resource structure
        resources_by_category = self.extract_resources_structure(soup)
        
        total_resources = sum(len(resources) for resources in resources_by_category.values())
        print(f"Found {total_resources} API resources across {len(resources_by_category)} categories")
        
        # First pass: assign numbers to all resources
        resource_count = 0
        for category, resources in resources_by_category.items():
            for resource in resources:
                resource_count += 1
                self.resources_processed[resource['title']] = resource_count
        
        # Process each resource
        file_index = []
        resource_count = 0
        
        for category, resources in resources_by_category.items():
            print(f"\nProcessing category: {category} ({len(resources)} resources)")
            
            for resource in resources:
                resource_count += 1
                title = resource['title']
                
                # Create filename
                filename = f"{resource_count:03d}_{self.sanitize_filename(title)}.html"
                filepath = self.output_dir / filename
                
                print(f"  [{resource_count}/{total_resources}] Processing: {title}")
                print(f"    - {len(resource['endpoints'])} endpoints")
                
                # Collect all content for this resource
                all_content_parts = []
                
                # Add main resource content
                if resource['href'].startswith('#'):
                    main_content = self.extract_section_content(soup, resource['href'])
                    all_content_parts.append(main_content)
                
                # Add each endpoint content
                for endpoint in resource['endpoints']:
                    if endpoint['href'].startswith('#'):
                        endpoint_content = self.extract_section_content(soup, endpoint['href'])
                        all_content_parts.append(endpoint_content)
                
                # Combine all content
                all_content = '\n<hr>\n'.join(all_content_parts)
                
                # Create standalone HTML with all resources for sidebar
                standalone_html = self.create_resource_html(resource, all_content, soup, resources_by_category)
                
                # Save the file
                with open(filepath, 'w', encoding='utf-8') as f:
                    f.write(standalone_html)
                
                print(f"    ✓ Saved to {filepath}")
                
                # Add to index
                file_index.append({
                    'filename': filename,
                    'title': title,
                    'category': category,
                    'endpoint_count': len(resource['endpoints'])
                })
        
        # Create index file
        self.create_index_file(file_index, resources_by_category)
        
        print(f"\n✅ Processing complete! {resource_count} resource files saved to {self.output_dir}/")
    
    def create_index_file(self, file_index, resources_by_category):
        """Create an index HTML file with links to all resource documents."""
        # Group files by category
        files_by_category = defaultdict(list)
        for file_info in file_index:
            files_by_category[file_info['category']].append(file_info)
        
        index_html = """<!DOCTYPE html>
<html lang="ko">
<head>
    <meta charset="UTF-8">
    <meta name="viewport" content="width=device-width, initial-scale=1.0">
    <title>Cafe24 API Documentation - Resource Index</title>
    <style>
        body {
            font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, 'Helvetica Neue', Arial, sans-serif;
            line-height: 1.6;
            padding: 20px;
            max-width: 1400px;
            margin: 0 auto;
            background: #f5f7fa;
        }
        h1 {
            color: #333;
            border-bottom: 3px solid #0066cc;
            padding-bottom: 10px;
        }
        .stats {
            background: white;
            padding: 15px;
            border-radius: 8px;
            margin: 20px 0;
            box-shadow: 0 2px 4px rgba(0,0,0,0.1);
        }
        .stats span {
            margin-right: 30px;
            font-weight: bold;
        }
        .category-section {
            margin: 30px 0;
        }
        .category-title {
            background: #0066cc;
            color: white;
            padding: 10px 15px;
            border-radius: 8px 8px 0 0;
            font-size: 1.2em;
            font-weight: bold;
        }
        .resource-list {
            background: white;
            padding: 20px;
            border-radius: 0 0 8px 8px;
        }
        .resource-list ul {
            list-style: none;
            padding: 0;
            margin: 0;
        }
        .resource-list li {
            padding: 8px 0;
            border-bottom: 1px solid #e9ecef;
        }
        .resource-list li:last-child {
            border-bottom: none;
        }
        .resource-list a {
            color: #0066cc;
            text-decoration: none;
            font-size: 1.05em;
        }
        .resource-list a:hover {
            text-decoration: underline;
            color: #0052a3;
        }
        .original-link {
            margin-top: 20px;
            padding: 15px;
            background: #e7f3ff;
            border-radius: 8px;
        }
    </style>
</head>
<body>
    <h1>📚 Cafe24 API Documentation - By Resource</h1>
    
    <div class="stats">
        <span>📁 Total Resources: """ + str(len(file_index)) + """</span>
        <span>📑 Categories: """ + str(len(files_by_category)) + """</span>
    </div>
    
    <div class="original-link">
        <strong>Additional Resources:</strong> 
        <a href="original_complete.html">View Complete Original Documentation</a> | 
        <a href="https://developers.cafe24.com/docs/ko/api/admin/" target="_blank">Visit Live Documentation</a>
    </div>
"""
        
        # Add each category
        for category in files_by_category.keys():
            files = files_by_category[category]
            index_html += f"""
    <div class="category-section">
        <div class="category-title">{category} ({len(files)} resources)</div>
        <div class="resource-list">
            <ul>
"""
            
            for file_info in files:
                index_html += f"""
                <li><a href="{file_info['filename']}">{file_info['title']}</a></li>
"""
            
            index_html += """
            </ul>
        </div>
    </div>
"""
        
        index_html += """
</body>
</html>"""
        
        index_file = self.output_dir / "index.html"
        with open(index_file, 'w', encoding='utf-8') as f:
            f.write(index_html)
        print(f"\n✅ Created index file: {index_file}")


def main():
    url = "https://developers.cafe24.com/docs/ko/api/admin/"
    separator = Cafe24DocResourceSeparator(url)
    separator.process_documentation()


if __name__ == "__main__":
    main()

Use at your own risk