ligenparser hinzugefügt

Ligenlinks.py

@@ -0,0 +1,68 @@
+import requests
+from bs4 import BeautifulSoup
+from urllib.parse import urljoin
+from collections import defaultdict
+
+def extract_gesamt_links_club(base_url, club_name="Eschweiler SG"):
+    resp = requests.get(base_url)
+    resp.raise_for_status()
+    soup = BeautifulSoup(resp.text, "html.parser")
+
+    grouped_results = defaultdict(list)
+    current_section = "Unbekannt"
+
+    for tr in soup.select("table tr"):
+        tds = tr.find_all("td")
+
+        # Abschnittsüberschrift (z.B. "Nordrhein 25/26")
+        if len(tds) == 1 or (len(tds) == 2 and tds[0].has_attr("colspan")):
+            current_section = tds[0].get_text(strip=True)
+            continue
+
+        if len(tds) >= 2:
+            team_name = tds[0].get_text(strip=True)
+
+            # Liga-Link
+            liga_link_tag = tds[1].find("a", href=True)
+            if not liga_link_tag:
+                continue
+            liga_url = urljoin(base_url, liga_link_tag["href"])
+
+            # Liga-Seite abrufen
+            liga_resp = requests.get(liga_url)
+            liga_resp.raise_for_status()
+            liga_soup = BeautifulSoup(liga_resp.text, "html.parser")
+
+            # Gesamt-Spielplan
+            gesamt = liga_soup.find("a", string=lambda s: s and "Gesamt" in s)
+            gesamt_url = urljoin(liga_url, gesamt["href"]) if gesamt else None
+
+            # Mannschafts-Portrait
+            portrait = liga_soup.find("a", href=True, string=lambda s: s and club_name in s)
+            portrait_url = urljoin(liga_url, portrait["href"]) if portrait else None
+
+            grouped_results[current_section].append({
+                "team": team_name,
+                "portrait_url": portrait_url,
+                "liga_url": liga_url,
+                "gesamt_url": gesamt_url
+            })
+
+    return grouped_results
+
+
+if __name__ == "__main__":
+    club_url = "https://hnr-handball.liga.nu/cgi-bin/WebObjects/nuLigaHBDE.woa/wa/clubTeams?club=74726"
+    grouped = extract_gesamt_links_club(club_url, club_name="Eschweiler SG")
+
+    output_file = "ligenlinks.md"
+    with open(output_file, "w", encoding="utf-8") as f:
+        for section, teams in grouped.items():
+            f.write(f"## {section}\n\n")
+            for item in teams:
+                f.write(f"### {item['team']}\n")
+                f.write(f"- [Mannschafts-Portrait]({item['portrait_url']})\n" if item['portrait_url'] else "- Mannschafts-Portrait: Nicht gefunden\n")
+                f.write(f"- [Liga-Seite]({item['liga_url']})\n")
+                f.write(f"- [Gesamt-Spielplan]({item['gesamt_url']})\n\n")
+
+    print(f"✅ Markdown-Datei erstellt: {output_file}")