Files
deer-flow/backend/src/utils/readability.py
2026-01-14 07:17:22 +08:00

67 lines
2.1 KiB
Python

import re
from urllib.parse import urljoin
from markdownify import markdownify as md
from readabilipy import simple_json_from_html_string
class Article:
url: str
def __init__(self, title: str, html_content: str):
self.title = title
self.html_content = html_content
def to_markdown(self, including_title: bool = True) -> str:
markdown = ""
if including_title:
markdown += f"# {self.title}\n\n"
if self.html_content is None or not str(self.html_content).strip():
markdown += "*No content available*\n"
else:
markdown += md(self.html_content)
return markdown
def to_message(self) -> list[dict]:
image_pattern = r"!\[.*?\]\((.*?)\)"
content: list[dict[str, str]] = []
markdown = self.to_markdown()
if not markdown or not markdown.strip():
return [{"type": "text", "text": "No content available"}]
parts = re.split(image_pattern, markdown)
for i, part in enumerate(parts):
if i % 2 == 1:
image_url = urljoin(self.url, part.strip())
content.append({"type": "image_url", "image_url": {"url": image_url}})
else:
text_part = part.strip()
if text_part:
content.append({"type": "text", "text": text_part})
# If after processing all parts, content is still empty, provide a fallback message.
if not content:
content = [{"type": "text", "text": "No content available"}]
return content
class ReadabilityExtractor:
def extract_article(self, html: str) -> Article:
article = simple_json_from_html_string(html, use_readability=True)
html_content = article.get("content")
if not html_content or not str(html_content).strip():
html_content = "No content could be extracted from this page"
title = article.get("title")
if not title or not str(title).strip():
title = "Untitled"
return Article(title=title, html_content=html_content)