mirror of
https://github.com/bytedance/deer-flow.git
synced 2026-05-20 07:01:03 +00:00
He Tao
16 lines
454 B
Python
16 lines
454 B
Python
# Copyright (c) 2025 Bytedance Ltd. and/or its affiliates
|
|
# SPDX-License-Identifier: MIT
|
|
|
|
from readabilipy import simple_json_from_html_string
|
|
|
|
from .article import Article
|
|
|
|
|
|
class ReadabilityExtractor:
|
|
def extract_article(self, html: str) -> Article:
|
|
article = simple_json_from_html_string(html, use_readability=True)
|
|
return Article(
|
|
title=article.get("title"),
|
|
html_content=article.get("content"),
|
|
)
|