feat: use full concurrency (no semaphores)

1 files changed, 18 insertions, 15 deletions

diff --git a/main.py b/main.py
index d874d42..f653a7d 100644
--- a/main.py
+++ b/main.py
@@ -33,7 +33,18 @@ def get_urls(filename: str, limit: int | None = None) -> list[str]:
         return urls
 
 
-async def ping(urls: list[str], max_concurrency=None) -> None:
+async def fetch(session: aiohttp.ClientSession, url: str) -> str:
+    try:
+        async with session.get(url) as response:
+            if response.ok:
+                return "😁"
+            else:
+                return "😓"
+    except aiohttp.ClientError:
+        return "🤮"
+
+
+async def ping(urls: list[str], max_concurrency=None) -> list[str]:
     """Make a GET request to members of URLS.
 
     If MAX_CONCURRENCY is None, browse every site at once.
@@ -44,19 +55,11 @@ async def ping(urls: list[str], max_concurrency=None) -> None:
 
     """
 
-    async with aiohttp.ClientSession(max_field_size=8190 * 2, timeout=1.0) as session:
-        for url in urls:
-            try:
-                async with session.get(url) as response:
-                    print(f"Status: {response.status}")
-
-                    if not response.ok:
-                        print(f"Got code {response.status} from URL; skipping")
-                        continue
-
-                    print(f"Content-Type: {response.headers['content-type']}")
-            except aiohttp.ClientError as e:
-                print(f"Something bad happened with URL: {e}; skipping")
+    async with aiohttp.ClientSession(
+        max_field_size=8190 * 2, timeout=aiohttp.ClientTimeout(30)
+    ) as session:
+        tasks = [fetch(session, url) for url in urls]
+        return await asyncio.gather(*tasks)
 
 
 def main():
@@ -68,7 +71,7 @@ def main():
     urls = get_urls("majestic_million.csv", limit)
 
     start_time = time.perf_counter()
-    asyncio.run(ping(urls))
+    print(asyncio.run(ping(urls)))
     end_time = time.perf_counter()
 
     elapsed_time = end_time - start_time