43 lines
1.3 KiB
Python
43 lines
1.3 KiB
Python
import aiohttp
|
|
import html.parser
|
|
import asyncio
|
|
import urllib.parse
|
|
|
|
class TitleExtractor(html.parser.HTMLParser):
|
|
def __init__(self):
|
|
super().__init__()
|
|
self.current_data = None
|
|
self.latest_title = None
|
|
|
|
def handle_data(self, data):
|
|
self.current_data = data
|
|
|
|
def handle_endtag(self, tag):
|
|
if tag == "title":
|
|
self.latest_title = self.current_data
|
|
|
|
async def get_preview(url):
|
|
url = url.replace("youtube.com/shorts/", "youtube.com/watch?v=")
|
|
url_parsed = urllib.parse.urlparse(url)
|
|
url_no_fragment = url_parsed._replace(fragment="").geturl()
|
|
session = aiohttp.ClientSession()
|
|
session.headers["user-agent"] = "Mozilla/5.0 XmppPreviewer/1.0"
|
|
resp = await session.get(url_no_fragment)
|
|
title = None
|
|
print(url_no_fragment, resp.status)
|
|
if resp.headers["content-type"].startswith("text/html"):
|
|
parser = TitleExtractor()
|
|
while chunk := await resp.content.read(4096):
|
|
parser.feed(chunk.decode("utf-8")) # assume utf-8
|
|
if parser.latest_title:
|
|
title = parser.latest_title
|
|
break
|
|
resp.close()
|
|
await session.close()
|
|
return title
|
|
|
|
if __name__ == "__main__":
|
|
async def main():
|
|
print(await get_preview("https://youtu.be/WNFahAioGP8"))
|
|
|
|
asyncio.run(main())
|