All the things

This commit is contained in:
2025-01-25 22:42:04 -06:00
parent d556823350
commit 0db1065d10
16 changed files with 678 additions and 55 deletions

View File

@@ -1,16 +1,8 @@
import asyncio
import aiohttp
from bs4 import BeautifulSoup
from typing import Optional
from dataclasses import dataclass
from datetime import datetime
class PageInfoFetcher:
async def get_page_title(self, url: str) -> Optional[str]:
try:
async with aiohttp.ClientSession() as session:
async with session.get(url, timeout=5) as response:
if response.status == 200:
html = await response.text()
soup = BeautifulSoup(html, 'html.parser')
return soup.title.string if soup.title else None
except:
return None
@dataclass
class PageInfo:
url: str
html: str
timestamp: datetime