Executando verificação de segurança...
2
from bs4 import BeautifulSoup
import json
import re


with open('example.html', 'r') as file:
    html_str = file.read()

soup = BeautifulSoup(html_str, 'html.parser')
h1_title = soup.find('h1').get_text()

script = json.loads(soup.find('script', {'id': 'article'}).get_text())
markdown = script.get('body')
pattern = re.compile(r'\[\s*`?(.*?)`?\s*]\((.*?)\)')
tools = [{"name": text, "link": link} for text, link in pattern.findall(markdown)]

match = re.search(r"json\s*(.*?)```\s*", markdown, re.DOTALL)
random_data = json.loads(match.group(1)).get('randomData') if match else {}

tags = script.get('tags', [])


json_data = {
    "heading": h1_title,
    "article": {
        "title": script.get('title', 'No Title Found'),
        "body": {
            "tools": tools,
            "moreData": random_data
        },
        "tags": tags
    }
}

json_str = json.dumps(json_data, indent=4)
print(json_str)

Carregando publicação patrocinada...