Crawler-Parser: og/product:price-Meta (toom 799 €, Hornbach) + Hornbach.ch als erste Ausland-Live-Quelle (cc)

This commit is contained in:
2026-06-28 09:50:50 +00:00
parent 5b0d0e6a19
commit c5adbb34db
2 changed files with 22 additions and 1 deletions
+19 -1
View File
@@ -36,6 +36,22 @@ def _num(s):
g=m.groups() g=m.groups()
return float(g[0]) + (float(g[1])/100 if len(g)>1 and g[1] else 0) return float(g[0]) + (float(g[1])/100 if len(g)>1 and g[1] else 0)
def clean_price(v):
v=(v or "").strip()
if not v: return None
if "," in v: v=v.replace(".","").replace(",",".")
m=re.search(r"\d+(?:\.\d+)?", v)
return float(m.group()) if m else None
def price_from_meta(h):
for pat in ("product:price:amount","og:price:amount"):
m=re.search(r'<meta[^>]+(?:property|name)=["\']'+pat+r'["\'][^>]+content=["\']([^"\']+)', h, re.I) or \
re.search(r'<meta[^>]+content=["\']([^"\']+)["\'][^>]+(?:property|name)=["\']'+pat+r'["\']', h, re.I)
if m:
p=clean_price(m.group(1))
if p: return p
return None
def parse(htmltext): def parse(htmltext):
# 1) JSON-LD Offer # 1) JSON-LD Offer
price=None; avail=None price=None; avail=None
@@ -56,6 +72,8 @@ def parse(htmltext):
low=htmltext.lower() low=htmltext.lower()
in_store = ("vorrätig" in low or "verfügbar" in low) and not ("nicht vorrätig" in low or "nicht verfügbar" in low) in_store = ("vorrätig" in low or "verfügbar" in low) and not ("nicht vorrätig" in low or "nicht verfügbar" in low)
online = ("in den warenkorb" in low) or ("lieferung" in low and "nicht möglich" not in low) or (avail and "instock" in avail.lower()) online = ("in den warenkorb" in low) or ("lieferung" in low and "nicht möglich" not in low) or (avail and "instock" in avail.lower())
if price is None:
price=price_from_meta(htmltext)
if price is None: if price is None:
mp=_num(htmltext[:200000]) mp=_num(htmltext[:200000])
price=mp price=mp
@@ -75,7 +93,7 @@ async def fetch_one(client, src):
if r.status_code!=200: if r.status_code!=200:
return {**src,"price":None,"availability":"unknown","status":r.status_code} return {**src,"price":None,"availability":"unknown","status":r.status_code}
price, avail = parse(r.text) price, avail = parse(r.text)
return {"chain":src["chain"],"kind":src["kind"],"productId":src["productId"],"name":src["name"], return {"chain":src["chain"],"kind":src["kind"],"cc":src.get("cc","DE"),"productId":src["productId"],"name":src["name"],
"url":src["url"],"price":price,"availability":avail} "url":src["url"],"price":price,"availability":avail}
except Exception as e: except Exception as e:
log.warning("fetch fail %s: %s", src["url"], e) log.warning("fetch fail %s: %s", src["url"], e)
+3
View File
@@ -15,6 +15,9 @@ SOURCES = [
"url":"https://toom.de/p/mobiles-klimageraet-portasplit-12000-btuh/9350668"}, "url":"https://toom.de/p/mobiles-klimageraet-portasplit-12000-btuh/9350668"},
{"chain":"toom","kind":"baumarkt","productId":"midea-portasplit-cool-8000","name":"Midea PortaSplit Cool 8.000 BTU", {"chain":"toom","kind":"baumarkt","productId":"midea-portasplit-cool-8000","name":"Midea PortaSplit Cool 8.000 BTU",
"url":"https://toom.de/p/split-klimaanlage-portasplit-cool-8000btuh/10515238"}, "url":"https://toom.de/p/split-klimaanlage-portasplit-cool-8000btuh/10515238"},
# Ausland (live, Hornbach international gleiche Plattform wie .de):
{"chain":"Hornbach","cc":"CH","kind":"baumarkt","productId":"midea-portasplit-12000","name":"Midea PortaSplit 12.000 BTU (CH)",
"url":"https://www.hornbach.ch/de/p/mobile-split-klimaanlage-midea-portasplit-ch-12000-btu-42m-weiss/12613899/"},
] ]
# Elektroketten / Online -> offizielle APIs nötig (mit Keys von Till): # Elektroketten / Online -> offizielle APIs nötig (mit Keys von Till):
# Amazon Product Advertising API 5.0 (Access/Secret/Partner-Tag) # Amazon Product Advertising API 5.0 (Access/Secret/Partner-Tag)