Test cat images

urlpreview.py

@@ -0,0 +1,39 @@
+import aiohttp
+import html.parser
+import asyncio
+
+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):
+    session = aiohttp.ClientSession()
+    session.headers["user-agent"] = "Mozilla/5.0 XmppPreviewer/1.0"
+    resp = await session.get(url)
+    title = None
+    print(url, 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/YUMaoIt1rDU"))
+
+    asyncio.run(main())