Dumps the full Wallapop category tree to data/wallapop_categories.json

fetch_wallapop_categories.py

"""
fetch_wallapop_categories.py
Dumps the full Wallapop category tree to data/wallapop_categories.json
"""
import requests
import json

HEADERS = {
    'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36',
    'Accept': 'application/json, text/plain, */*',
    'Accept-Language': 'es-ES,es;q=0.9',
    'Referer': 'https://es.wallapop.com/',
}


def walk(node, path):
    current_path = path + [node['name']]
    children = node.get('subcategories', [])
    yield str(node['id']), {
        'name': node['name'],
        'path': current_path,
        'leaf': not bool(children),
    }
    for child in children:
        yield from walk(child, current_path)


r = requests.get('https://api.wallapop.com/api/v3/categories', headers=HEADERS, timeout=10)
tree = {}
for top in r.json()['categories']:
    for cat_id, data in walk(top, []):
        tree[cat_id] = data

with open('data/wallapop_categories.json', 'w', encoding='utf-8') as f:
    json.dump(tree, f, indent=2, ensure_ascii=False)

print(f'Guardado: {len(tree)} categorías en data/wallapop_categories.json')