Create a content archive with Python

Creating a content archive with Python typically means collecting, organizing, and storing content—such as files, articles, or other digital assets—into a structured format for later access or retrieval. Below is a basic yet flexible example of how to build a content archive using Python.

Step-by-Step Guide: Building a Content Archive with Python

1. Define the Archive Structure

We’ll create a directory-based archive where each content item is stored in its own folder with metadata and content files.

python
CopyEdit
import os
import json
from datetime import datetime

ARCHIVE_ROOT = 'content_archive'

def init_archive():
    if not os.path.exists(ARCHIVE_ROOT):
        os.makedirs(ARCHIVE_ROOT)
    print(f"Archive initialized at '{ARCHIVE_ROOT}'")

2. Create and Save Content

Each content item will include:

• A metadata.json file (title, tags, date)

• A content.txt file for the main body

python
CopyEdit
def add_content(title, tags, content):
    timestamp = datetime.now().strftime('%Y%m%d_%H%M%S')
    slug = title.lower().replace(' ', '_')[:30]
    folder_name = f"{timestamp}_{slug}"
    content_path = os.path.join(ARCHIVE_ROOT, folder_name)
    os.makedirs(content_path, exist_ok=True)

    metadata = {
        'title': title,
        'tags': tags,
        'created_at': timestamp
    }

    with open(os.path.join(content_path, 'metadata.json'), 'w') as meta_file:
        json.dump(metadata, meta_file, indent=4)

    with open(os.path.join(content_path, 'content.txt'), 'w') as content_file:
        content_file.write(content)

    print(f"Content '{title}' saved in '{content_path}'")

3. List Archived Content

This function retrieves all archived items with their metadata.

python
CopyEdit
def list_contents():
    for folder in os.listdir(ARCHIVE_ROOT):
        folder_path = os.path.join(ARCHIVE_ROOT, folder)
        meta_file = os.path.join(folder_path, 'metadata.json')
        if os.path.isfile(meta_file):
            with open(meta_file, 'r') as f:
                meta = json.load(f)
                print(f"Title: {meta['title']}, Tags: {meta['tags']}, Date: {meta['created_at']}")

4. Search Content by Tag or Title

Allow searching based on metadata fields.

python
CopyEdit
def search_contents(keyword):
    results = []
    for folder in os.listdir(ARCHIVE_ROOT):
        folder_path = os.path.join(ARCHIVE_ROOT, folder)
        meta_file = os.path.join(folder_path, 'metadata.json')
        if os.path.isfile(meta_file):
            with open(meta_file, 'r') as f:
                meta = json.load(f)
                if keyword.lower() in meta['title'].lower() or keyword.lower() in [t.lower() for t in meta['tags']]:
                    results.append(meta)
    return results

5. View Specific Content

Display content and metadata of a given item.

python
CopyEdit
def view_content(title_keyword):
    for folder in os.listdir(ARCHIVE_ROOT):
        folder_path = os.path.join(ARCHIVE_ROOT, folder)
        meta_file = os.path.join(folder_path, 'metadata.json')
        content_file = os.path.join(folder_path, 'content.txt')
        if os.path.isfile(meta_file):
            with open(meta_file, 'r') as f:
                meta = json.load(f)
                if title_keyword.lower() in meta['title'].lower():
                    with open(content_file, 'r') as cf:
                        body = cf.read()
                    print(f"Title: {meta['title']}")
                    print(f"Tags: {meta['tags']}")
                    print(f"Date: {meta['created_at']}")
                    print("Content:n", body)
                    break

Example Usage

python
CopyEdit
init_archive()

add_content(
    title="Understanding Python Decorators",
    tags=["python", "programming", "decorators"],
    content="Decorators in Python are functions that modify the behavior of another function..."
)

add_content(
    title="SEO Tips for Content Creators",
    tags=["seo", "marketing", "content"],
    content="Search Engine Optimization (SEO) is essential for visibility in search results..."
)

list_contents()

results = search_contents("seo")
print("Search Results:", results)

view_content("SEO Tips")

Additional Enhancements

• Full-text search: Use a database or indexing tool like SQLite or Whoosh.

• GUI/CLI interface: Add a command-line menu or Tkinter interface.

• Export/Backup: Zip folders for backup or export.

• Web interface: Build a Flask or FastAPI app for web-based archive access.

This basic structure gives you a scalable and editable archive system for managing content effectively using only Python and local files.