import requests, re, collections
from urllib.parse import urlparse
HDRS={"User-Agent":"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/126 Safari/537.36"}
def fetch(u):
    try: return requests.get(u,headers=HDRS,timeout=20).text
    except Exception as e: return ""
def urls_from(xml):
    return re.findall(r"<loc>\s*(.*?)\s*</loc>", xml)
def expand(root, depth=0):
    xml = fetch(root)
    locs = urls_from(xml)
    out=[]
    if "<sitemapindex" in xml and depth<2:
        for l in locs: out += expand(l, depth+1)
    else:
        out = locs
    return out
SITEMAPS = {
 "alimentsduquebec": "https://alimentsduquebec.com/sitemaps-1-sitemap.xml",
 "lesproduitsduquebec": "https://lesproduitsduquebec.com/sitemap.xml",
 "metiersdart": "https://www.metiersdart.ca/sitemap.xml",
 "vinsduquebec": "https://vinsduquebec.com/sitemap.xml",
 "cidreduquebec": "https://cidreduquebec.com/wp-sitemap.xml",
 "ambq": "https://ambq.ca/sitemap.xml",
 "fromagesdici": "https://www.fromagesdici.com/sitemap.xml",
 "erabledici": "https://www.erabledici.ca/sitemap_index.xml",
 "terroiretsaveurs": "https://terroiretsaveurs.com/sitemap_index.xml",
 "marchespublics": "https://www.marchespublicsduquebec.ca/sitemap.xml",
 "artisansaloeuvre": "https://artisansaloeuvre.com/sitemap_index.xml",
}
for name, sm in SITEMAPS.items():
    urls = expand(sm)
    pat = collections.Counter()
    for u in urls:
        p = urlparse(u).path
        segs = [s for s in p.split("/") if s]
        pat["/"+segs[0]+"/*" if segs else "/"] += 1
    print("="*60); print(name, "total:", len(urls))
    for k,v in pat.most_common(12): print(f"  {v:6d}  {k}")