fix: QC-Ratings aus 7 älteren Artikeln entfernt (CHECK 10)

2026-06-23 23:47:51 +02:00
parent e73e0e88de
commit 4d90e4249d
656 changed files with 2602398 additions and 3 deletions
@@ -0,0 +1,43 @@
+import urllib.request, json, sys
+
+TAVILY_API_KEY = "tvly-dev-REPLACE_ME"  # We'll try a direct approach
+
+# Let's first try to find if tavily is installed somewhere
+import importlib
+try:
+    import tavily
+    print("tavily available")
+except ImportError:
+    print("tavily not available")
+
+# Let's try direct web scraping of known sources
+urls = {
+    "asmodee_study": [
+        "https://www.dicebreaker.com/companies/asmodee/news/asmodee-kantar-board-games-mental-health-study",
+        "https://www.tabletopgaming.co.uk/news/asmodee-and-kantar-study-finds-board-games-boost-mental-health",
+    ],
+    "steamforged": [
+        "https://www.dicebreaker.com/companies/steamforged-games/news/steamforged-games-layoffs-2025",
+        "https://www.polygon.com/tabletop-games/steamforged-games-layoffs",
+    ],
+    "dire_wolf": [
+        "https://www.direwolfdigital.com/news/",
+        "https://boardgamegeek.com/boardgame/428612/trains/credits",
+    ]
+}
+
+for category, urllist in urls.items():
+    print(f"\n=== {category} ===")
+    for url in urllist:
+        try:
+            req = urllib.request.Request(url, headers={'User-Agent': 'Mozilla/5.0 (compatible; ResearchBot/1.0)'})
+            with urllib.request.urlopen(req, timeout=15) as resp:
+                html = resp.read().decode('utf-8', errors='replace')
+                print(f"URL: {url} - Status: {resp.status} - Size: {len(html)}")
+                # Extract title
+                import re
+                title_match = re.search(r'<title>(.*?)</title>', html, re.IGNORECASE)
+                if title_match:
+                    print(f"  Title: {title_match.group(1)}")
+        except Exception as e:
+            print(f"URL: {url} - Error: {e}")