för att man inte kan ladda upp fler filer

crawler.py

@@ -0,0 +1,99 @@
+import requests
+from bs4 import BeautifulSoup
+import json
+import os
+from selenium import webdriver
+from selenium.webdriver.chrome.options import Options
+
+# CONFIGURATION
+NATIONER_URL = "https://www.nationsguiden.se/"  # Example URL, replace with actual
+DISCORD_WEBHOOK_URL = "https://discord.com/api/webhooks/1437888900747104317/TI2RfDGC5dzoi5JGz6UO2aD23teYNwa6pLQOskhaDnsSVe3cr8_rly0L3K0VyIYARgeR"
+
+
+def fetch_nationer_open_times(url):
+    import re
+    print(f"DEBUG: Current working directory is {os.getcwd()}")
+    # Use headless browser to get rendered DOM and extract event data
+    chrome_options = Options()
+    chrome_options.add_argument('--headless')
+    chrome_options.add_argument('--disable-gpu')
+    chrome_options.add_argument('--no-sandbox')
+    driver = webdriver.Chrome(options=chrome_options)
+    driver.get(url)
+    import time
+    time.sleep(5)  # Wait for JS to load events
+
+    nationer_data = []
+    # Find all event blocks (adjust selector as needed)
+    event_blocks = driver.find_elements("css selector", "div.flex.flex-col.justify-evenly")
+    print(f"DEBUG: Found {len(event_blocks)} event blocks in DOM.")
+    for block in event_blocks:
+        try:
+            event_title = block.find_element("css selector", "h4 a").text.strip()
+        except Exception:
+            event_title = ""
+        try:
+            organiser = block.find_element("css selector", "a.text-primary, p.text-primary").text.strip()
+        except Exception:
+            organiser = ""
+        try:
+            open_time = block.find_element("css selector", "time").text.strip()
+        except Exception:
+            open_time = ""
+        try:
+            permalink = block.find_element("css selector", "h4 a").get_attribute("href")
+        except Exception:
+            permalink = ""
+        if event_title:
+            print(f"DEBUG: Event: {event_title}, Organiser: {organiser}, Time: {open_time}")
+            nationer_data.append({
+                "event": event_title,
+                "nation": organiser,
+                "open_time": open_time,
+                "permalink": permalink
+            })
+    driver.quit()
+    # Write debug file for extracted events
+    debug_path = os.path.abspath("/mnt/serverdata/html/crawlernation/events_debug.json")
+    try:
+        with open(debug_path, "w", encoding="utf-8") as f:
+            json.dump(nationer_data, f, ensure_ascii=False, indent=2)
+        print(f"Wrote debug event data to {debug_path}")
+    except Exception as e:
+        print(f"Error writing debug file: {e}")
+    return nationer_data
+
+
+def send_to_discord_webhook(data, webhook_url):
+    if not webhook_url:
+        raise ValueError("DISCORD_WEBHOOK_URL not set")
+    content = "Nationer Öppna Idag:\n"
+    for item in data:
+        content += f"**{item['nation']}**\nEvent: {item['event']}\nTid: {item['open_time']}\n---\n"
+    # Discord message limit is 2000 characters
+    if len(content) > 1900:
+        content = content[:1900] + "... (truncated)"
+    payload = {"content": content}
+    try:
+
+        response = requests.post(webhook_url, json=payload)
+        response.raise_for_status()
+        return response.status_code
+    except requests.exceptions.HTTPError as e:
+        print(f"Discord webhook error: {e}\nPayload: {payload}")
+        return None
+
+
+def main():
+    nationer_data = fetch_nationer_open_times(NATIONER_URL)
+    if nationer_data:
+        send_to_discord_webhook(nationer_data, DISCORD_WEBHOOK_URL)
+    else:
+        send_to_discord_webhook([
+            {"nation": "Inga aktiviteter hittades.", "event": "", "open_time": ""}
+        ], DISCORD_WEBHOOK_URL)
+
+
+if __name__ == "__main__":
+    main()
+