Add CPU data extraction script using requests and BeautifulSoup

2025-02-17 00:05:47 +01:00
parent 9848b6fa51
commit 7c6a64a82f
2 changed files with 446 additions and 0 deletions
@@ -0,0 +1,27 @@
+import requests
+from bs4 import BeautifulSoup
+import pandas as pd
+import time
+
+BASE_URL = "https://www.cpubenchmark.net"
+LOOKUP_URL = f"{BASE_URL}/cpu_lookup.php"
+
+headers = {
+    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36",
+    "Referer": "https://www.cpubenchmark.net/",
+    "Accept-Language": "en-US,en;q=0.9",
+    "Accept-Encoding": "gzip, deflate, br",
+    "DNT": "1",  # No rastrear
+    "Connection": "keep-alive",
+}
+
+# Obtener la lista de CPUs desde la página principal
+response = requests.get(LOOKUP_URL, headers=headers)
+if response.status_code != 200:
+    print(response.text)
+    exit()
+
+soup = BeautifulSoup(response.text, "html.parser")
+
+# Obtener la lista de CPUs
+