Live-Crawler scharf: Frontend-Overlay (LIVE-gescrapte OBI/Bauhaus-Preise im Monitor) + 404/410-Erkennung (Produktseite entfernt) – Edge, den braucheklima nicht hat

This commit is contained in:
2026-06-28 07:39:39 +00:00
parent bca2107ad8
commit bb7991bbd3
2 changed files with 26 additions and 2 deletions
+9 -2
View File
@@ -55,7 +55,11 @@ def parse(htmltext):
async def fetch_one(client, src): async def fetch_one(client, src):
try: try:
r= await client.get(src["url"], headers=UA, timeout=20, follow_redirects=True) r= await client.get(src["url"], headers=UA, timeout=20, follow_redirects=True)
if r.status_code!=200: if r.status_code in (404,410):
# Produktseite verschwunden -> als entfernt kennzeichnen (das kann braucheklima nicht)
return {"chain":src["chain"],"kind":src["kind"],"productId":src["productId"],"name":src["name"],
"url":src["url"],"price":None,"availability":"discontinued","status":r.status_code}
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"],"productId":src["productId"],"name":src["name"],
@@ -83,13 +87,16 @@ async def crawl():
p=prev.get((o["chain"],o["productId"])) p=prev.get((o["chain"],o["productId"]))
if p and p.get("availability")=="out_of_stock" and o.get("availability") in ("in_stock","online_available"): if p and p.get("availability")=="out_of_stock" and o.get("availability") in ("in_stock","online_available"):
hist["events"].append({"chain":o["chain"],"productId":o["productId"],"name":o["name"],"at":now}) hist["events"].append({"chain":o["chain"],"productId":o["productId"],"name":o["name"],"at":now})
if p and p.get("availability")!="discontinued" and o.get("availability")=="discontinued":
hist["events"].append({"chain":o["chain"],"productId":o["productId"],"name":o["name"],"at":now,"type":"discontinued"})
hist["events"]=hist["events"][-200:] hist["events"]=hist["events"][-200:]
# Preis-Aggregat je Produkt # Preis-Aggregat je Produkt
byp={} byp={}
for o in results: for o in results:
if o.get("price"): byp.setdefault(o["productId"],[]).append(o["price"]) if o.get("price"): byp.setdefault(o["productId"],[]).append(o["price"])
agg={k:{"min":min(v),"max":max(v),"n":len(v)} for k,v in byp.items()} agg={k:{"min":min(v),"max":max(v),"n":len(v)} for k,v in byp.items()}
snap={"generatedAt":now,"source":"kuehlfinder-livecrawler","intervalMin":INTERVAL_MIN, gone=[o for o in results if o.get("availability")=="discontinued"]
snap={"generatedAt":now,"source":"kuehlfinder-livecrawler","intervalMin":INTERVAL_MIN,"discontinued":len(gone),
"offers":results,"priceByProduct":agg,"feed":hist["events"][-20:][::-1]} "offers":results,"priceByProduct":agg,"feed":hist["events"][-20:][::-1]}
json.dump(snap, open(LIVE,"w"), ensure_ascii=False) json.dump(snap, open(LIVE,"w"), ensure_ascii=False)
json.dump(hist, open(HIST,"w"), ensure_ascii=False) json.dump(hist, open(HIST,"w"), ensure_ascii=False)
+17
View File
@@ -123,6 +123,7 @@ const jsonld={'@context':'https://schema.org','@type':'WebApplication',name:'Kü
.osrc b{font-size:.82rem}.osrc .num{font-size:.92rem}.osrc small{font-size:.71rem;color:var(--slate)} .osrc b{font-size:.82rem}.osrc .num{font-size:.92rem}.osrc small{font-size:.71rem;color:var(--slate)}
.osrc.wucher{border-color:var(--danger);background:var(--danger-bg)}.osrc.wucher .num{color:var(--danger)} .osrc.wucher{border-color:var(--danger);background:var(--danger-bg)}.osrc.wucher .num{color:var(--danger)}
.trust{font-size:.68rem;color:var(--slate)} .trust{font-size:.68rem;color:var(--slate)}
.livebadge{display:inline-flex;align-items:center;gap:.4rem;font-size:.8rem;font-weight:600;color:var(--ok-dot);background:var(--ok-bg);border:1px solid var(--ok-dot);border-radius:999px;padding:.35rem .7rem;align-self:center}
.tablewrap{margin-top:.8rem;padding:0;overflow:hidden} .tablewrap{margin-top:.8rem;padding:0;overflow:hidden}
.mtab{width:100%;border-collapse:collapse;font-size:.9rem} .mtab{width:100%;border-collapse:collapse;font-size:.9rem}
.mtab thead th{text-align:left;font-size:.72rem;text-transform:uppercase;letter-spacing:.04em;color:var(--slate);font-weight:600;padding:.7rem .8rem;border-bottom:1px solid var(--line);background:var(--card);white-space:nowrap} .mtab thead th{text-align:left;font-size:.72rem;text-transform:uppercase;letter-spacing:.04em;color:var(--slate);font-weight:600;padding:.7rem .8rem;border-bottom:1px solid var(--line);background:var(--card);white-space:nowrap}
@@ -142,6 +143,7 @@ const jsonld={'@context':'https://schema.org','@type':'WebApplication',name:'Kü
<script> <script>
import maplibregl from 'maplibre-gl'; import maplibregl from 'maplibre-gl';
const FLAG={DE:'🇩🇪',AT:'🇦🇹',CH:'🇨🇭',NL:'🇳🇱',PL:'🇵🇱',DK:'🇩🇰'}; const FLAG={DE:'🇩🇪',AT:'🇦🇹',CH:'🇨🇭',NL:'🇳🇱',PL:'🇵🇱',DK:'🇩🇰'};
const LIVE_URL='http://vnqwgi4gq520hs1p4bsgi4w6.46.224.49.66.sslip.io';
const fmt=(n,c)=>n==null?'':new Intl.NumberFormat('de-DE',{style:'currency',currency:c||'EUR',maximumFractionDigits:0}).format(n); const fmt=(n,c)=>n==null?'':new Intl.NumberFormat('de-DE',{style:'currency',currency:c||'EUR',maximumFractionDigits:0}).format(n);
const $=s=>document.querySelector(s),$$=s=>Array.from(document.querySelectorAll(s)); const $=s=>document.querySelector(s),$$=s=>Array.from(document.querySelectorAll(s));
let DATA=null,center=null,shown=120; let DATA=null,center=null,shown=120;
@@ -211,6 +213,21 @@ const jsonld={'@context':'https://schema.org','@type':'WebApplication',name:'Kü
$$('#countrychips .chip').forEach(b=>b.addEventListener('click',()=>{const c=b.dataset.cc;state.countries.has(c)?(state.countries.delete(c),b.classList.remove('on')):(state.countries.add(c),b.classList.add('on'));render();})); $$('#countrychips .chip').forEach(b=>b.addEventListener('click',()=>{const c=b.dataset.cc;state.countries.has(c)?(state.countries.delete(c),b.classList.remove('on')):(state.countries.add(c),b.classList.add('on'));render();}));
if(state.model!=='all')$('#model').value=state.model; if(state.model!=='all')$('#model').value=state.model;
if(state.q)$('#q').value=state.q; if(state.q)$('#q').value=state.q;
loadLive();
}
function loadLive(){
fetch(LIVE_URL+'/api/live').then(r=>r.json()).then(d=>{
if(!d||!d.offers||!d.offers.length)return;
const when=d.generatedAt?new Date(d.generatedAt):null;
const mins=when?Math.max(1,Math.round((Date.now()-when)/60000)):'?';
const items=d.offers.filter(o=>o.price).map(o=>{
const av=o.availability==='in_stock'?'im Markt':(o.availability==='online_available'?'online':(o.availability==='discontinued'?'⚠ Seite entfernt (404)':'vergriffen'));
const cls=(o.availability==='out_of_stock')?'':'';
return `<a class="osrc ${o.availability==='discontinued'?'wucher':''}" href="${o.url}" target="_blank" rel="sponsored nofollow noopener"><b>${o.chain} · LIVE</b><span class="num">${fmt(o.price)}</span><small>${o.name} · ${av}</small></a>`;
}).join('');
const bar=$('#onlinebar');
bar.insertAdjacentHTML('afterbegin', `<span class="livebadge" title="eigener Live-Crawler"><span class="dot ok live"></span> LIVE gescrapt · Stand vor ${mins} Min</span>`+items);
}).catch(()=>{});
} }
map.on('load',()=>{ map.on('load',()=>{
map.addSource('all',{type:'geojson',data:{type:'FeatureCollection',features:[]},cluster:true,clusterRadius:46,clusterMaxZoom:9}); map.addSource('all',{type:'geojson',data:{type:'FeatureCollection',features:[]},cluster:true,clusterRadius:46,clusterMaxZoom:9});