...
\s*
(.*?)
',
re.DOTALL
)
for row_m in row_pattern.finditer(block):
cell = row_m.group(1)
# Titel aus
...
title_m = re.search(r'
(.*?)', cell, re.DOTALL)
if not title_m:
continue
title = _strip_tags(title_m.group(1)).strip()
if not title:
continue
# Datum: erste DD.MM.YYYY nach dem
-Block
after_b = cell[title_m.end():]
date_m = re.search(r'(\d{1,2}\.\d{1,2}\.\d{4})', after_b)
if not date_m:
continue
date_str = _parse_date(date_m.group(1))
if not date_str:
continue
# PLZ + Ort: "12345 Stadtname"
ort = ""
ort_m = re.search(r'(\d{5})\s+([^<\n\r]+)', after_b)
if ort_m:
ort = ort_m.group(2).strip()
events.append({
"titel": title,
"datum": date_str,
"ort_name": ort,
"link": "https://www.vdh.de/ausstellungen/",
})
return events
# ── PARSER 2: /hundesport/termine/ ───────────────────────────────────────────
# Struktur: Kategorie
dann -
#
- DD.MM.YYYY - DD.MM.YYYY
Titel
Ort: Stadt
def _parse_sport(html: str) -> list[dict]:
events = []
# - -Blöcke extrahieren
li_pattern = re.compile(r'
- (.*?)
', re.DOTALL)
for li_m in li_pattern.finditer(html):
cell = li_m.group(1)
# Datum: erstes DD.MM.YYYY oder DD.MM.YYYY - DD.MM.YYYY
date_m = re.search(r'(\d{1,2}\.\d{1,2}\.\d{4}(?:\s*-\s*\d{1,2}\.\d{1,2}\.\d{4})?)', cell)
if not date_m:
continue
date_str = _parse_date(date_m.group(1))
if not date_str:
continue
# Text nach dem Datum ohne Tags
after_date = cell[date_m.end():]
# "Ort:" aus Ort: Stadt entfernen wir für den Titel
parts = [p.strip() for p in re.split(r'|[^<]*', after_date) if p.strip()]
parts = [_strip_tags(p) for p in parts if _strip_tags(p)]
title = ""
ort = ""
for part in parts:
if re.match(r'^Ort:\s*', part, re.IGNORECASE):
ort = re.sub(r'^Ort:\s*', '', part, flags=re.IGNORECASE).strip()
elif not title and not re.match(r'^\d', part):
title = part
if not title:
continue
events.append({
"titel": title,
"datum": date_str,
"ort_name": ort,
"link": "https://www.vdh.de/hundesport/termine/",
})
return events
async def fetch_vdh_events() -> list[dict]:
"""
Scrapt VDH-Veranstaltungen von ausstellungen/liste und hundesport/termine.
Gibt eine Liste von Dicts zurück: {titel, datum, ort_name, typ, link, external_id}
"""
sources = [
("https://www.vdh.de/ausstellungen/liste/typ/spezial/", _parse_spezial),
("https://www.vdh.de/hundesport/termine/", _parse_sport),
]
headers = {
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 Chrome/124.0.0.0 Safari/537.36",
"Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8",
"Accept-Language": "de-DE,de;q=0.9,en;q=0.5",
}
raw_events: list[dict] = []
timeout = httpx.Timeout(connect=15.0, read=60.0, write=10.0, pool=10.0)
async with httpx.AsyncClient(timeout=timeout, follow_redirects=True) as client:
for url, parse_fn in sources:
try:
resp = await client.get(url, headers=headers)
resp.raise_for_status()
found = parse_fn(resp.text)
if found:
logger.info(f"VDH-Scraper: {len(found)} Events von {url}")
raw_events.extend(found)
else:
logger.info(f"VDH-Scraper: Keine Events auf {url}")
except httpx.HTTPStatusError as e:
logger.warning(f"VDH-Scraper HTTP-Fehler {e.response.status_code} für {url}: {e}")
except httpx.TimeoutException as e:
logger.warning(f"VDH-Scraper Timeout für {url}: {type(e).__name__}")
except Exception as e:
logger.warning(f"VDH-Scraper Fehler für {url}: {type(e).__name__}: {e}")
if not raw_events:
logger.warning("VDH-Scraper: Keine Daten — verwende Fallback-Events.")
return list(FALLBACK_EVENTS)
today = datetime.today().strftime("%Y-%m-%d")
result = []
seen_ids: set[str] = set()
for ev in raw_events:
datum = ev.get("datum", "")
if datum < today:
continue
titel = ev.get("titel", "").strip()
if not titel or len(titel) < 3:
continue
entry = {
"titel": titel,
"datum": datum,
"ort_name": ev.get("ort_name") or None,
"typ": _guess_typ(titel),
"link": ev.get("link", "https://www.vdh.de"),
"external_id": _build_external_id(ev),
}
if entry["external_id"] not in seen_ids:
seen_ids.add(entry["external_id"])
result.append(entry)
if not result:
logger.warning("VDH-Scraper: Nach Filterung 0 Events — verwende Fallback.")
return list(FALLBACK_EVENTS)
logger.info(f"VDH-Scraper: {len(result)} zukünftige Events nach Normalisierung.")
return result