import requests, re, collections
HDRS={"User-Agent":"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 Chrome/126 Safari/537.36"}
def fetch(u):
    try: return requests.get(u,headers=HDRS,timeout=20).text
    except: return ""
def urls_from(x): return re.findall(r"<loc>\s*(.*?)\s*</loc>", x)
def expand(root, depth=0):
    xml=fetch(root); locs=urls_from(xml)
    if "<sitemapindex" in xml and depth<2:
        out=[]
        for l in locs[:40]: out+=expand(l,depth+1)
        return out
    return locs
for site in ["https://www.ideecadeauquebec.com","https://acheterquebecois.ca","https://distilleriesduquebec.com","https://bieresdemicroduquebec.ca","https://terroiretsaveurs.com"]:
    for sm in ["/sitemap.xml","/sitemap_index.xml","/wp-sitemap.xml"]:
        urls=expand(site+sm)
        if urls:
            pat=collections.Counter()
            for u in urls:
                m=re.search(r"://[^/]+(/[^/]*)", u)
                if m: pat[m.group(1)+"/*"]+=1
            print("="*50); print(site+sm, "total:", len(urls))
            for k,v in pat.most_common(14): print(f"  {v:6d}  {k}")
            break