خرد کردن خط فرمان با Amazon Q: ساخت یک مبدل متوسط ​​به dev.to

# Basic conversion
python3 medium2dev.py https://medium.com/aws-in-plain-english/aws-resource-tag-compliance-with-automation-64ae16e42a11

# Publish directly to DEV.to as a draft
python3 medium2dev.py https://medium.com/aws-in-plain-english/aws-resource-tag-compliance-with-automation-64ae16e42a11 --publish --api-key YOUR_DEVTO_API_KEY

# Or use environment variable for API key
export DEVTO_API_KEY=your_api_key
python3 medium2dev.py https://medium.com/aws-in-plain-english/aws-resource-tag-compliance-with-automation-64ae16e42a11 --publish

2025-05-03 15:07:49,696 - medium2dev - INFO - Fetching article from https://medium.com/aws-in-plain-english/aws-resource-tag-compliance-with-automation-64ae16e42a11
2025-05-03 15:07:51,100 - medium2dev - INFO - Original Medium content word count: 463
2025-05-03 15:07:51,100 - medium2dev - INFO - Downloaded 0 content images
2025-05-03 15:07:51,116 - medium2dev - INFO - Conversion complete! Output saved to /Users/vivekvelso/Documents/opensource/medium2dev/new/aws-resource-tag-compliance-with-automation-64ae16e42a11.md

Conversion successful! Output saved to: /Users/vivekvelso/Documents/opensource/medium2dev/aws-resource-tag-compliance-with-automation-64ae16e42a11.md
Images saved to: /Users/vivekvelso/Documents/opensource/medium2dev/images

Successfully published as draft to DEV.to!

Word Count Comparison:
| Platform | Word Count |
|----------|------------|
| Medium   | 463        |
| DEV.to   | 458        |

I am submitting an idea for this challenge. Crushing the Command Line
Build an automation with Amazon Q Developer CLI that makes your work easier, faster, or better.

My idea is to create a tool to convert medium posts to dev.to markdown posts preserving the title heading, formatting and inline images the same way. Please give exact steps and prompts by referring to collection from promptz tool if you find anything to enhance the solution, and also what prompts were given to automate the whole command line solution to q and how q responded, log all that in this blog post for submission, along with the code that is generated, then test it on the url https://medium.com/aws-in-plain-english/aws-resource-tag-compliance-with-automation-64ae16e42a11 and verify the markdown generated, and confirm that all text, image, formatting is same.

["CLI", "Markdown"]

class Medium2Dev:
    def __init__(self, url, output_dir=None, image_dir=None, api_key=None):
        """Initialize the converter with the Medium post URL."""
        self.url = url
        self.output_dir = output_dir or os.getcwd()
        self.image_dir = image_dir or os.path.join(self.output_dir, 'images')
        self.api_key = api_key
        # ...

    def fetch_article(self):
        """Fetch the Medium article content."""
        # ...

    def extract_content(self, html_content):
        """Extract the article content from the HTML."""
        # ...

    def download_images(self, content):
        """Download images and update their references in the content."""
        # ...

    def convert_to_markdown(self, content):
        """Convert HTML content to Markdown format suitable for DEV.to."""
        # ...

    def generate_frontmatter(self, title, date):
        """Generate DEV.to frontmatter."""
        # ...

    def convert(self):
        """Convert the Medium post to DEV.to markdown format."""
        # ...

    def publish_to_devto(self, title, markdown_content):
        """Publish the converted markdown as a draft post to DEV.to."""
        # ...

   # Create a new div to hold only the content we want
   content_div = soup.new_tag('div')

   # Find all the content sections (paragraphs, headings, code blocks, images)
   content_elements = article_tag.find_all(['p', 'h2', 'h3', 'h4', 'pre', 'figure', 'img', 'blockquote', 'ul', 'ol'])

   # Skip elements with author info, claps, etc.
   if element.find(string=re.compile(r'clap|follow|min read|sign up|bookmark|Listen|Share')):
       continue

   # Skip elements that just contain "--" or numbers at the beginning
   if element.name == 'p' and re.match(r'^\s*--\s*$|^\s*\d+\s*$', element.text.strip()):
       continue

   # For Medium images, try to get the full-size version
   if 'miro.medium.com' in img_url:
       # Remove size constraints from URL to get original image
       img_url = re.sub(r'/resize:[^/]+/', '/', img_url)

   # Remove Medium-specific footer text and links
   markdown = re.sub(r'\n\s*\[.*?\]\(https?://medium\.com/.*?\)\s*\n', '\n\n', markdown)

   # Remove clap indicators and other Medium UI elements
   markdown = re.sub(r'\d+\s*claps?', '', markdown)

   parser.add_argument('-p', '--publish', action='store_true', help='Publish to DEV.to as draft')
   parser.add_argument('-k', '--api-key', help='DEV.to API key (if not set via DEVTO_API_KEY environment variable)')

   def publish_to_devto(self, title, markdown_content):
       """Publish the converted markdown as a draft post to DEV.to."""
       if not self.api_key:
           logger.error("No DEV.to API key provided. Skipping publish.")
           return False

       logger.info("Publishing to DEV.to as draft...")

       api_url = "https://dev.to/api/articles"
       headers = {
           "api-key": self.api_key,
           "Content-Type": "application/json"
       }

       # Prepare the article data
       article_data = {
           "article": {
               "title": title,
               "body_markdown": markdown_content,
               "published": False  # Set as draft
           }
       }

       try:
           response = requests.post(api_url, headers=headers, json=article_data)
           response.raise_for_status()
           article_data = response.json()
           logger.info(f"Successfully published draft to DEV.to!")
           return True
       except requests.RequestException as e:
           logger.error(f"Error publishing to DEV.to: {e}")
           return False

   # Calculate the word count of the original content
   content_text = ' '.join([element.get_text() for element in content_div.contents])
   self.medium_word_count = len(content_text.split())
   logger.info(f"Original Medium content word count: {self.medium_word_count}")

   # Calculate DEV.to word count
   devto_word_count = len(re.sub(r'---.*?---\n', '', markdown_content, flags=re.DOTALL).split())

   # Display comparison when publishing
   print("\nWord Count Comparison:")
   print("| Platform | Word Count |")
   print("|----------|------------|")
   print(f"| Medium   | {converter.medium_word_count} |")
   print(f"| DEV.to   | {devto_word_count} |")

python3 medium2dev.py https://medium.com/aws-in-plain-english/aws-resource-tag-compliance-with-automation-64ae16e42a11

python3 medium2dev.py https://medium.com/@vivek-aws/aws-resource-tag-compliance-with-automation-64ae16e42a11

   headers = {
       'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36',
       'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
       # Additional headers...
   }

   # Try multiple approaches to find the content
   article_tag = soup.find('article')
   if not article_tag:
       article_tag = soup.select_one('div.section-content')
   if not article_tag:
       article_tag = soup.find('div', class_='postArticle-content')

   # Remove Medium-specific UI elements and metadata
   for element in content.select('.postMetaLockup, .graf--pullquote, .section-divider'):
       if element:
           element.decompose()

   # Get API key from environment or command line
   api_key = args.api_key or os.environ.get('DEVTO_API_KEY')

   # Convert "aws in plain english" to "awsinplainenglish"
   potential_tag = re.sub(r'[^a-zA-Z0-9]', '', potential_tag)

   # Calculate word counts and display comparison
   medium_word_count = converter.medium_word_count
   devto_word_count = len(re.sub(r'---.*?---\n', '', markdown_content, flags=re.DOTALL).split())