210311a7b3
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
266 lines
18 KiB
Python
266 lines
18 KiB
Python
"""
|
|
Rohlik.cz Price Scraper - Category Tree
|
|
Version: 1.0.0
|
|
Date: 2026-05-31
|
|
|
|
Complete hardcoded category tree for Rohlik.cz (14 main categories, ~170+ leaves).
|
|
Only leaf categories (without children) contain the full product listing.
|
|
"""
|
|
|
|
CATEGORY_TREE = [
|
|
{
|
|
"name": "Ovoce a zelenina", "id": "300102000", "url": "/c300102000-ovoce-a-zelenina",
|
|
"children": [
|
|
{"name": "Zelenina", "id": "300102008", "url": "/c300102008-zelenina", "children": [
|
|
{"name": "Okurky, cukety a lilky", "id": "300102013", "url": "/c300102013-okurky-cukety-a-lilky"},
|
|
{"name": "Mrkev a kořenová zelenina", "id": "300102012", "url": "/c300102012-mrkev-a-korenova-zelenina"},
|
|
{"name": "Cibule, česnek a pórek", "id": "300102010", "url": "/c300102010-cibule-cesnek-a-porek"},
|
|
{"name": "Papriky a chilli", "id": "300102015", "url": "/c300102015-papriky-a-chilli"},
|
|
{"name": "Saláty", "id": "300102021", "url": "/c300102021-salaty"},
|
|
{"name": "Rajčata", "id": "300102014", "url": "/c300102014-rajcata"},
|
|
{"name": "Brambory", "id": "300102009", "url": "/c300102009-brambory"},
|
|
{"name": "Ostatní zelenina", "id": "300102020", "url": "/c300102020-ostatni-zelenina"},
|
|
{"name": "Květák a košťálová zelenina", "id": "300102016", "url": "/c300102016-kvetak-a-kostalova-zelenina"},
|
|
{"name": "Dýně a tykve", "id": "300102011", "url": "/c300102011-dyne-a-tykve"},
|
|
{"name": "Kukuřice a lusky", "id": "300102017", "url": "/c300102017-kukurice-a-lusky"},
|
|
{"name": "Bio zelenina", "id": "300102040", "url": "/c300102040-bio-zelenina"},
|
|
{"name": "Baby zelenina", "id": "300102018", "url": "/c300102018-baby-zelenina"},
|
|
{"name": "Rychlá příprava a předvařená zelenina", "id": "300112157", "url": "/c300112157-rychla-priprava-a-predvarena-zelenina"},
|
|
]},
|
|
{"name": "Ovoce", "id": "300102001", "url": "/c300102001-ovoce"},
|
|
{"name": "Bylinky a microgreens", "id": "300102026", "url": "/c300102026-bylinky-a-microgreens"},
|
|
{"name": "Kuchařské boxy, hotové saláty a ready to cook", "id": "300124625", "url": "/c300124625-kucharske-boxy-hotove-salaty-a-ready-to-cook"},
|
|
{"name": "Houby", "id": "300102022", "url": "/c300102022-houby"},
|
|
{"name": "Květiny", "id": "300112201", "url": "/c300112201-kvetiny"},
|
|
{"name": "Čerstvě sklizeno", "id": "300120435", "url": "/c300120435-cerstve-sklizeno"},
|
|
{"name": "Český chřest", "id": "300114291", "url": "/c300114291-cesky-chrest"},
|
|
{"name": "BIO ovoce a zelenina", "id": "300114343", "url": "/c300114343-bio-ovoce-a-zelenina"},
|
|
{"name": "Kunratická stodola", "id": "300124164", "url": "/c300124164-kunraticka-stodola"},
|
|
{"name": "Speciality ze světa", "id": "300102038", "url": "/c300102038-speciality-ze-sveta"},
|
|
]
|
|
},
|
|
{
|
|
"name": "Mléčné a chlazené", "id": "300105000", "url": "/c300105000-mlecne-a-chlazene",
|
|
"children": [
|
|
{"name": "Sýry", "id": "300105026", "url": "/c300105026-syry"},
|
|
{"name": "Jogurty a mléčné dezerty", "id": "300105008", "url": "/c300105008-jogurty-a-mlecne-dezerty"},
|
|
{"name": "Vejce a droždí", "id": "300105053", "url": "/c300105053-vejce-a-drozdi"},
|
|
{"name": "Smetany, šlehačky a tvarohy", "id": "300105021", "url": "/c300105021-smetany-slehacky-a-tvarohy"},
|
|
{"name": "Máslo, tuky a margaríny", "id": "300105048", "url": "/c300105048-maslo-tuky-a-margariny"},
|
|
{"name": "Majonézy, tatarské omáčky a dresingy", "id": "300105058", "url": "/c300105058-majonezy-tatarske-omacky-a-dresingy"},
|
|
{"name": "Mléko a mléčné nápoje", "id": "300105001", "url": "/c300105001-mleko-a-mlecne-napoje"},
|
|
{"name": "Bez laktózy, A2 a High protein", "id": "300121231", "url": "/c300121231-bez-laktozy-a2-a-high-protein"},
|
|
]
|
|
},
|
|
{
|
|
"name": "Maso a ryby", "id": "300103000", "url": "/c300103000-maso-a-ryby",
|
|
"children": [
|
|
{"name": "Drůbež", "id": "300115247", "url": "/c300115247-drubez"},
|
|
{"name": "Hovězí a telecí", "id": "300117217", "url": "/c300117217-hovezi-a-teleci"},
|
|
{"name": "Vepřové", "id": "300103009", "url": "/c300103009-veprove"},
|
|
{"name": "Ryby a mořské plody", "id": "300117385", "url": "/c300117385-ryby-a-morske-plody"},
|
|
{"name": "BIO maso a ryby", "id": "300121424", "url": "/c300121424-bio-maso-a-ryby"},
|
|
{"name": "Maso na gril, steaky a burgery", "id": "300117355", "url": "/c300117355-maso-na-gril-steaky-a-burgery"},
|
|
{"name": "Zvěřina, jehněčí, králičí a speciality", "id": "300122988", "url": "/c300122988-zverina-jehneci-kralici-a-speciality"},
|
|
]
|
|
},
|
|
{
|
|
"name": "Pekárna a cukrárna", "id": "300101000", "url": "/c300101000-pekarna-a-cukrarna",
|
|
"children": [
|
|
{"name": "Slané pečivo", "id": "300101012", "url": "/c300101012-slane-pecivo"},
|
|
{"name": "Chléb", "id": "300101007", "url": "/c300101007-chleb"},
|
|
{"name": "Sladké pečivo", "id": "300101024", "url": "/c300101024-sladke-pecivo"},
|
|
{"name": "Dorty a zákusky", "id": "300101033", "url": "/c300101033-dorty-a-zakusky"},
|
|
{"name": "Racio a Knäckebrot", "id": "300101043", "url": "/c300101043-racio-a-knaeckebrot"},
|
|
{"name": "Tortilly a pita chleby", "id": "300101019", "url": "/c300101019-tortilly-a-pita-chleby"},
|
|
{"name": "Pečicí směsi a strouhanka", "id": "300101049", "url": "/c300101049-pecici-smesi-a-strouhanka"},
|
|
{"name": "Bezlepková pekárna a cukrárna", "id": "300118595", "url": "/c300118595-bezlepkova-pekarna-a-cukrarna"},
|
|
]
|
|
},
|
|
{
|
|
"name": "Uzeniny a lahůdky", "id": "300104000", "url": "/c300104000-uzeniny-a-lahudky",
|
|
"children": [
|
|
{"name": "Šunky a slaniny", "id": "300104001", "url": "/c300104001-sunky-a-slaniny"},
|
|
{"name": "Párky, klobásy a špekáčky", "id": "300104012", "url": "/c300104012-parky-klobasy-a-spekacky"},
|
|
{"name": "Salámy", "id": "300104007", "url": "/c300104007-salamy"},
|
|
{"name": "Hotová jídla a přílohy", "id": "300104049", "url": "/c300104049-hotova-jidla-a-prilohy"},
|
|
{"name": "Lahůdky", "id": "300104039", "url": "/c300104039-lahudky"},
|
|
{"name": "Paštiky a masné výrobky", "id": "300104016", "url": "/c300104016-pastiky-a-masne-vyrobky"},
|
|
{"name": "Saláty, pomazánky a pesta", "id": "300104032", "url": "/c300104032-salaty-pomazanky-a-pesta"},
|
|
{"name": "Zabijačkové speciality", "id": "300104020", "url": "/c300104020-zabijackove-speciality"},
|
|
{"name": "Dárkové koše a kazety", "id": "300121878", "url": "/c300121878-darkove-kose-a-kazety"},
|
|
]
|
|
},
|
|
{
|
|
"name": "Mražené", "id": "300107000", "url": "/c300107000-mrazene",
|
|
"children": [
|
|
{"name": "Pizza", "id": "300107020", "url": "/c300107020-pizza"},
|
|
{"name": "Zmrzlina a led", "id": "300107035", "url": "/c300107035-zmrzlina-a-led"},
|
|
{"name": "Ovoce a zelenina", "id": "300122993", "url": "/c300122993-ovoce-a-zelenina"},
|
|
{"name": "Bramborové výrobky", "id": "300107024", "url": "/c300107024-bramborove-vyrobky"},
|
|
{"name": "Hotová jídla", "id": "300107028", "url": "/c300107028-hotova-jidla"},
|
|
{"name": "Pečivo, dezerty a dorty", "id": "300107041", "url": "/c300107041-pecivo-dezerty-a-dorty"},
|
|
{"name": "Ryby a mořské plody", "id": "300107014", "url": "/c300107014-ryby-a-morske-plody"},
|
|
{"name": "Maso a drůbež", "id": "300107010", "url": "/c300107010-maso-a-drubez"},
|
|
]
|
|
},
|
|
{
|
|
"name": "Grilování", "id": "300117503", "url": "/c300117503-grilovani",
|
|
"children": [
|
|
{"name": "Rohlík doporučuje", "id": "300124865", "url": "/c300124865-rohlik-doporucuje"},
|
|
{"name": "Maso a ryby", "id": "300117505", "url": "/c300117505-maso-a-ryby"},
|
|
{"name": "Klobásy a slanina", "id": "300124497", "url": "/c300124497-klobasy-a-slanina"},
|
|
{"name": "Sýry", "id": "300121109", "url": "/c300121109-syry"},
|
|
{"name": "Pekárna", "id": "300117581", "url": "/c300117581-pekarna"},
|
|
{"name": "Zelenina, houby a bylinky", "id": "300124458", "url": "/c300124458-zelenina-houby-a-bylinky"},
|
|
{"name": "Sterilovaná zelenina a olivy", "id": "300124864", "url": "/c300124864-sterilovana-zelenina-a-olivy"},
|
|
{"name": "Plant based", "id": "300122070", "url": "/c300122070-plant-based"},
|
|
{"name": "Omáčky a koření", "id": "300117565", "url": "/c300117565-omacky-a-koreni"},
|
|
{"name": "Nápoje", "id": "300124465", "url": "/c300124465-napoje"},
|
|
{"name": "Příslušenství na grilování", "id": "300124489", "url": "/c300124489-prislusenstvi-na-grilovani"},
|
|
]
|
|
},
|
|
{
|
|
"name": "Plant Based", "id": "300121429", "url": "/c300121429-plant-based",
|
|
"children": [
|
|
{"name": "Trvanlivé", "id": "300121448", "url": "/c300121448-trvanlive"},
|
|
{"name": "Nápoje", "id": "300121430", "url": "/c300121430-napoje"},
|
|
{"name": "Alternativy mléčného a chlazeného", "id": "300121486", "url": "/c300121486-alternativy-mlecneho-a-chlazeneho"},
|
|
{"name": "Alternativy uzenin a lahůdek", "id": "300121493", "url": "/c300121493-alternativy-uzenin-a-lahudek"},
|
|
{"name": "Pekárna a cukrárna", "id": "300121491", "url": "/c300121491-pekarna-a-cukrarna"},
|
|
{"name": "Mražené", "id": "300121492", "url": "/c300121492-mrazene"},
|
|
{"name": "Bezmasé a nerybí výrobky", "id": "300121488", "url": "/c300121488-bezmase-a-nerybi-vyrobky"},
|
|
{"name": "Ovoce a zelenina", "id": "300121436", "url": "/c300121436-ovoce-a-zelenina"},
|
|
{"name": "Dítě", "id": "300121470", "url": "/c300121470-dite"},
|
|
{"name": "Drogerie a kosmetika", "id": "300121621", "url": "/c300121621-drogerie-a-kosmetika"},
|
|
]
|
|
},
|
|
{
|
|
"name": "Trvanlivé", "id": "300106000", "url": "/c300106000-trvanlive",
|
|
"children": [
|
|
{"name": "Sladkosti", "id": "300106128", "url": "/c300106128-sladkosti"},
|
|
{"name": "Přísady na pečení", "id": "300106001", "url": "/c300106001-prisady-na-peceni"},
|
|
{"name": "Konzervy, hotovky a instantní pokrmy", "id": "300123466", "url": "/c300123466-konzervy-hotovky-a-instantni-pokrmy"},
|
|
{"name": "Slané, snacky a ořechy", "id": "300123392", "url": "/c300123392-slane-snacky-a-orechy"},
|
|
{"name": "Koření a ochucovadla", "id": "300106031", "url": "/c300106031-koreni-a-ochucovadla"},
|
|
{"name": "Rýže, těstoviny, luštěniny, soja", "id": "300106096", "url": "/c300106096-ryze-testoviny-lusteniny-soja"},
|
|
{"name": "Džemy, medy, oříškové krémy, sladké pomazánky a sirupy", "id": "300106124", "url": "/c300106124-dzemy-medy-oriskove-kremy-sladke-pomazanky-a-sirupy"},
|
|
{"name": "Kečupy, hořčice a omáčky", "id": "300123436", "url": "/c300123436-kecupy-horcice-a-omacky"},
|
|
{"name": "Oleje a octy", "id": "300123421", "url": "/c300123421-oleje-a-octy"},
|
|
{"name": "Müsli, cereálie, kaše a tyčinky", "id": "300106117", "url": "/c300106117-muesli-cerealie-kase-a-tycinky"},
|
|
]
|
|
},
|
|
{
|
|
"name": "Nápoje", "id": "300108000", "url": "/c300108000-napoje",
|
|
"children": [
|
|
{"name": "Vody a minerálky", "id": "300122110", "url": "/c300122110-vody-a-mineralky"},
|
|
{"name": "Limonády a energy", "id": "300122167", "url": "/c300122167-limonady-a-energy"},
|
|
{"name": "Piva a cidery", "id": "300108052", "url": "/c300108052-piva-a-cidery"},
|
|
{"name": "Džusy, ovocné nápoje a sirupy", "id": "300122136", "url": "/c300122136-dzusy-ovocne-napoje-a-sirupy"},
|
|
{"name": "Víno", "id": "300108064", "url": "/c300108064-vino"},
|
|
{"name": "Horké nápoje", "id": "300123000", "url": "/c300123000-horke-napoje"},
|
|
{"name": "Lihoviny", "id": "300108072", "url": "/c300108072-lihoviny"},
|
|
{"name": "Vozíme chlazené", "id": "300124505", "url": "/c300124505-vozime-chlazene"},
|
|
{"name": "Dětské nápoje", "id": "300122626", "url": "/c300122626-detske-napoje"},
|
|
]
|
|
},
|
|
{
|
|
"name": "Speciální výživa", "id": "300112393", "url": "/c300112393-specialni-vyziva",
|
|
"children": [
|
|
{"name": "Bezlaktózové výrobky", "id": "300112395", "url": "/c300112395-bezlaktozove-vyrobky"},
|
|
{"name": "Fitness výživa", "id": "300115595", "url": "/c300115595-fitness-vyziva"},
|
|
{"name": "Bezlepkové výrobky", "id": "300112399", "url": "/c300112399-bezlepkove-vyrobky"},
|
|
{"name": "Potraviny se sníženým obsahem cukru", "id": "300112403", "url": "/c300112403-potraviny-se-snizenym-obsahem-cukru"},
|
|
{"name": "Veggie", "id": "300112843", "url": "/c300112843-veggie"},
|
|
{"name": "Alternativní strava", "id": "300124517", "url": "/c300124517-alternativni-strava"},
|
|
{"name": "Doplňky stravy", "id": "300115585", "url": "/c300115585-doplnky-stravy"},
|
|
{"name": "Nízkobílkovinové výrobky", "id": "300122547", "url": "/c300122547-nizkobilkovinove-vyrobky"},
|
|
]
|
|
},
|
|
{
|
|
"name": "Kosmetika", "id": "300124206", "url": "/c300124206-kosmetika",
|
|
"children": [
|
|
{"name": "Vlasová péče", "id": "300124300", "url": "/c300124300-vlasova-pece"},
|
|
{"name": "Ústní hygiena", "id": "300124215", "url": "/c300124215-ustni-hygiena"},
|
|
{"name": "Pleťová péče a dekorativní kosmetika", "id": "300124327", "url": "/c300124327-pletova-pece-a-dekorativni-kosmetika"},
|
|
{"name": "Dámská hygiena", "id": "300124245", "url": "/c300124245-damska-hygiena"},
|
|
{"name": "Sprchové gely a mýdla a přísady do koupele", "id": "300124259", "url": "/c300124259-sprchove-gely-a-mydla-a-prisady-do-koupele"},
|
|
{"name": "Tělová péče", "id": "300124320", "url": "/c300124320-telova-pece"},
|
|
{"name": "Holení a depilace", "id": "300124337", "url": "/c300124337-holeni-a-depilace"},
|
|
{"name": "Deodoranty a parfémy", "id": "300124281", "url": "/c300124281-deodoranty-a-parfemy"},
|
|
{"name": "Pánský svět", "id": "300124350", "url": "/c300124350-pansky-svet"},
|
|
{"name": "Pro intimní chvíle", "id": "300124361", "url": "/c300124361-pro-intimni-chvile"},
|
|
{"name": "Kosmetické dárkové balíčky", "id": "300124366", "url": "/c300124366-kosmeticke-darkove-balicky"},
|
|
{"name": "Cestovní balení a produkty na léto", "id": "300124367", "url": "/c300124367-cestovni-baleni-a-produkty-na-leto"},
|
|
]
|
|
},
|
|
{
|
|
"name": "Drogerie", "id": "300109000", "url": "/c300109000-drogerie",
|
|
"children": [
|
|
{"name": "Papírová a vatová hygiena", "id": "300109010", "url": "/c300109010-papirova-a-vatova-hygiena"},
|
|
{"name": "Prací prostředky", "id": "300109001", "url": "/c300109001-praci-prostredky"},
|
|
{"name": "Mytí nádobí", "id": "300109042", "url": "/c300109042-myti-nadobi"},
|
|
{"name": "Čisticí prostředky", "id": "300109028", "url": "/c300109028-cistici-prostredky"},
|
|
{"name": "Ekologická a šetrná drogerie", "id": "300124564", "url": "/c300124564-ekologicka-a-setrna-drogerie"},
|
|
{"name": "Dětské praní", "id": "300124266", "url": "/c300124266-detske-prani"},
|
|
{"name": "Velká balení", "id": "300124287", "url": "/c300124287-velka-baleni"},
|
|
]
|
|
},
|
|
{
|
|
"name": "Domácnost a zahrada", "id": "300111000", "url": "/c300111000-domacnost-a-zahrada",
|
|
"children": [
|
|
{"name": "Úklidové potřeby", "id": "300124615", "url": "/c300124615-uklidove-potreby"},
|
|
{"name": "Dům, byt a garáž", "id": "300123083", "url": "/c300123083-dum-byt-a-garaz"},
|
|
{"name": "Kuchyňské potřeby", "id": "300124614", "url": "/c300124614-kuchynske-potreby"},
|
|
{"name": "Zahrada a květiny", "id": "300111043", "url": "/c300111043-zahrada-a-kvetiny"},
|
|
{"name": "Kancelář a papírnictví", "id": "300111034", "url": "/c300111034-kancelar-a-papirnictvi"},
|
|
{"name": "Dekorace, svíčky a vůně", "id": "300124685", "url": "/c300124685-dekorace-svicky-a-vune"},
|
|
{"name": "Trafika", "id": "300111091", "url": "/c300111091-trafika"},
|
|
{"name": "Oslavy a párty", "id": "300124678", "url": "/c300124678-oslavy-a-party"},
|
|
{"name": "Punčocháče a ponožky", "id": "300124722", "url": "/c300124722-puncochace-a-ponozky"},
|
|
{"name": "Knihy", "id": "300124157", "url": "/c300124157-knihy"},
|
|
]
|
|
},
|
|
]
|
|
|
|
|
|
def get_leaf_categories(tree: list[dict] | None = None, parent_path: list[str] | None = None) -> list[dict]:
|
|
if tree is None:
|
|
tree = CATEGORY_TREE
|
|
if parent_path is None:
|
|
parent_path = []
|
|
|
|
leaves = []
|
|
for cat in tree:
|
|
current_path = parent_path + [cat["name"]]
|
|
children = cat.get("children")
|
|
if children:
|
|
leaves.extend(get_leaf_categories(children, current_path))
|
|
else:
|
|
leaves.append({
|
|
"id": cat["id"],
|
|
"name": cat["name"],
|
|
"url": cat["url"],
|
|
"path": current_path,
|
|
"parent_id": tree[0].get("id") if parent_path else None,
|
|
})
|
|
return leaves
|
|
|
|
|
|
def get_all_categories_flat(tree: list[dict] | None = None, parent_id: str | None = None) -> list[dict]:
|
|
if tree is None:
|
|
tree = CATEGORY_TREE
|
|
|
|
result = []
|
|
for cat in tree:
|
|
result.append({
|
|
"category_id": cat["id"],
|
|
"name": cat["name"],
|
|
"url": cat["url"],
|
|
"parent_id": parent_id,
|
|
"has_children": bool(cat.get("children")),
|
|
})
|
|
if cat.get("children"):
|
|
result.extend(get_all_categories_flat(cat["children"], parent_id=cat["id"]))
|
|
return result
|