pipelines/utils/markdown.py

import re
from oac.oac import get_description_of_image


def generate_image_description_with_empty_description(oa_client, websites):
    # Expressão regular para encontrar o padrão ![](<link>)
    pattern = r'!\[\]\(([^)]+)\)'

    def replace_description_image(match):
        link = match.group(1)
        new_description = get_description_of_image(oa_client, link)
        return f'![{new_description}]({link})'

    texts_with_images_descriptions = []
    error_images_upload = []
    for website in websites:
        try:
            text_with_image_description = re.sub(
                pattern,
                replace_description_image,
                website["text_content"]
            )
            texts_with_images_descriptions.append({
                "id": website["text_id"],
                "content": text_with_image_description,
                "url": website["url"]
            })
        except Exception:
            error_images_upload.append(
                f"{website['text_id']}: {website['text_content']}")
            texts_with_images_descriptions.append({
                "id": website["text_id"],
                "content": website["text_content"],
                "url": website["url"]
            })

    return texts_with_images_descriptions, error_images_upload