init efcore

WeaponGrabber/WeaponScraper.py

@@ -0,0 +1,54 @@
+"""Print every CS2 weapon listed on the Counter-Strike wiki.
+
+Requires: pip install curl_cffi beautifulsoup4
+
+Uses curl_cffi instead of requests because the wiki sits behind Cloudflare,
+which blocks Python's default TLS fingerprint with a 403 even when the
+User-Agent header looks like a browser.
+"""
+import re
+
+from bs4 import BeautifulSoup
+from curl_cffi import requests
+
+URL = "https://counterstrike.fandom.com/wiki/Weapons"
+TAB_HASH = "Global_Offensive_&_Counter-Strike_2"
+ANNOTATION_RE = re.compile(r"\s*\((?:CT|T)\)\s*$")
+STOCK_PREFIX_RE = re.compile(r"^Stock\s+")
+
+
+def cs2_weapons():
+    resp = requests.get(URL, impersonate="chrome", timeout=30)
+    resp.raise_for_status()
+    soup = BeautifulSoup(resp.text, "html.parser")
+
+    weapons, seen = [], set()
+    for tabber in soup.select("div.tabber"):
+        tabs = tabber.select("li.wds-tabs__tab")
+        idx = next(
+            (i for i, t in enumerate(tabs) if t.get("data-hash") == TAB_HASH),
+            None,
+        )
+        if idx is None:
+            continue
+        contents = tabber.find_all("div", class_="wds-tab__content")
+        if idx >= len(contents):
+            continue
+        for cap in contents[idx].select("div.lightbox-caption"):
+            name = cap.get_text(" ", strip=True)
+            name = ANNOTATION_RE.sub("", name)
+            name = STOCK_PREFIX_RE.sub("", name).strip()
+            if not name:
+                continue
+            if name not in seen:
+                seen.add(name)
+                weapons.append(name)
+    return weapons
+
+
+if __name__ == "__main__":
+    weaps = cs2_weapons()
+    for w in weaps:
+        print(w)
+    
+    print(len(weaps))