mirror of
https://gitee.com/wanwujie/deer-flow
synced 2026-04-14 18:54:46 +08:00
13 lines
364 B
Python
13 lines
364 B
Python
|
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"),
|
||
|
|
)
|