mirror of
https://github.com/VinciGit00/Scrapegraph-ai.git
synced 2026-06-23 21:00:30 +08:00
47 lines
1.5 KiB
Python
47 lines
1.5 KiB
Python
"""
|
|
Module for minimizing the code
|
|
"""
|
|
from bs4 import BeautifulSoup
|
|
from minify_html import minify
|
|
|
|
|
|
def cleanup_html(html_content: str, urls: list = []) -> str:
|
|
"""
|
|
Processes HTML content by removing unnecessary tags, minifying the HTML, and extracting the title and body content.
|
|
|
|
Args:
|
|
html_content (str): The HTML content to be processed.
|
|
|
|
Returns:
|
|
str: A string combining the parsed title and the minified body content. If no body content is found, it indicates so.
|
|
|
|
Example:
|
|
>>> html_content = "<html><head><title>Example</title></head><body><p>Hello World!</p></body></html>"
|
|
>>> cleanup_html(html_content)
|
|
'Title: Example, Body: <body><p>Hello World!</p></body>'
|
|
|
|
This function is particularly useful for preparing HTML content for environments where bandwidth usage needs to be minimized.
|
|
"""
|
|
|
|
soup = BeautifulSoup(html_content, 'html.parser')
|
|
|
|
# Title Extraction
|
|
title_tag = soup.find('title')
|
|
title = title_tag.get_text() if title_tag else ""
|
|
|
|
# Script and Style Tag Removal
|
|
for tag in soup.find_all(['script', 'style']):
|
|
tag.extract()
|
|
|
|
# Body Extraction (if it exists)
|
|
body_content = soup.find('body')
|
|
urls_content = ""
|
|
if urls:
|
|
urls_content = f", URLs in page: {urls}"
|
|
if body_content:
|
|
# Minify the HTML within the body tag
|
|
minimized_body = minify(str(body_content))
|
|
return "Title: " + title + ", Body: " + minimized_body + urls_content
|
|
|
|
return "Title: " + title + ", Body: No body content found" + urls_content
|